Hundreds of tested MiniMax H3 prompts for cinematic text-to-video and image-to-video — camera moves, characters, products, and VFX. Preview each result, then generate it in one click.
Every card credits the original creator. Filter by category, copy the prompt, or open it directly in the MiniMax H3 generator.
Prompt preview
See the result before you spend a credit.
Every card shows the real MiniMax H3 output, so you know what the prompt produces before generating.
Showing 1-24 of 274 prompts
Page 1 / 12
Per page
Cinematic & Story prompts55
Cinematic & Story
Train Station Farewell — 3-shot narrative
15s16:9
A 15-second multi-frame narrative sequence from an emotional drama. Shot 1 (0-5s): Wide shot of a misty, quiet train station platform at dawn, steam rising from a vintage train. Shot 2 (5-10s): Cut to a medium close-up, a tearful woman standing near the open train door, her coat blowing gently in the cool breeze as she turns back. Shot 3 (10-15s): Cut to a close-up of a man on the platform extending a hand toward her, the train slowly starting to move away, deep depth of field, natural lighting, shot on 65mm anamorphic lens.
Create an authentic 15-second archival home video that appears to have been recorded in Seoul, South Korea, during the summer of 1998 using a consumer Hi8 or VHS-C camcorder. The camcorder is never visible. The audience only sees the footage captured through the camera, exactly as if watching a forgotten family videotape decades later. This is not a vlog, not a selfie, and not a cinematic film. The unseen camera operator casually documents an ordinary moment from everyday life.
The footage should faithfully recreate genuine late-1990s analogue camcorder characteristics: soft 480i resolution, subtle VHS tape grain, faint interlacing, mild colour fading, occasional autofocus breathing, slight exposure shifts, gentle handheld shake, imperfect framing, tiny zoom corrections, realistic motion blur, analogue colour bleed, and faint tape hiss. No HDR, no digital sharpening, no beauty filters, no stabilisation, no cinematic lighting, no slow motion, and no modern camera effects.
A light summer rain has just begun in a quiet Seoul neighborhood. A young Korean woman in her early twenties waits at a simple city bus stop beneath a clear plastic umbrella. She wears a pale blue oversized T-shirt tucked into relaxed-fit blue jeans, classic white sneakers, and carries a canvas shoulder bag, perfectly matching authentic Korean street fashion from 1998. Around her, commuters quietly wait while late-1990s Korean buses, sedans, and bicycles pass by on the wet street. Handwritten Hangul shop signs, overhead utility wires, convenience stores, and low-rise apartment buildings create an unmistakably authentic Seoul atmosphere.
As the rain becomes slightly heavier, a small orange tabby cat runs from beneath a parked car toward the bus stop. The woman notices it, crouches down with a warm smile, and gently shelters the cat under her umbrella. The cat calmly sits beside her while several nearby commuters smile at the unexpected moment. A city bus approaches in the background, its headlights reflecting across the rain-soaked road. The woman looks toward the arriving bus, softly laughs, gives the cat one gentle pat, and steps aboard as the doors close. The camera remains outside, lingering for a few seconds on the rainy street as the bus slowly drives away before the recording ends abruptly, exactly as if someone simply pressed the stop button on the camcorder.
Generation Requirements: Produce one continuous, uninterrupted 15-second recording with no cuts or transitions. Every detail must accurately recreate Seoul in 1998, including clothing, hairstyles, architecture, vehicles, signage, weather, and everyday behavior. Human movement must be completely natural with consistent facial identity, realistic anatomy, authentic hand movements, believable crowd interactions, and subtle environmental details such as rain, passing traffic, distant conversations, bus engine sounds, birds, and ambient city noise. Avoid AI artifacts, duplicated pedestrians, warped limbs, floating objects, unnatural expressions, perfect symmetry, or anything suggesting the footage was AI-generated. The finished result should be indistinguishable from genuine late-1990s home camcorder footage discovered in a family archive.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic gritty thriller action
SCENE
Dilapidated industrial warehouse. Rusty orange metal shelving units, hanging heavy iron chains, concrete floor covered in shattered glass debris. A woman with dark hair tied back, wearing a white button-down shirt heavily stained with fresh blood over the chest, holding a jagged glass shard. A man with dark hair, wearing a distressed, torn black denim jacket over a black shirt.
SHOT BREAKDOWN
0-4s — Wide profile two-shot framed through foreground blurred glass. The woman holds the glass shard defensively, staring down the man across a dusty aisle.
4-8s — Medium action shot. The woman lunges forward aggressively, swinging the glass shard. The man swiftly reacts, intercepting her arm mid-strike.
8-12s — Medium close-up. The man forcefully drives the woman back, pinning her against the rusty metal shelving. Her arm is trapped, neutralizing the weapon.
12-15s — Alternating over-the-shoulder close-ups. First, the woman’s bruised face, blood dripping prominently from her lower lip, lips moving in quiet defiance. Cut to the man’s face, jaw clenched, eyes narrowed with intense anger as he grips her collar.
CAMERA
Handheld dynamic motion, snapping into rapid focus during the struggle. Shallow depth of field isolating faces in close-ups. Fast, kinetic cut rhythm.
LIGHTING & PALETTE
Single overhead fluorescent tube casts harsh, directional top-light. Deep shadows filling the background. Cool, sickly cyan and green color grade sharply contrasting with vivid crimson blood.
AUDIO
Industrial hollow room tone, crunching broken glass, sudden fabric rustling, violent scuffle impacts. Dark, pulsing synth drone. Tense, breathless dialogue.
AVOID
Bright key lighting, clean pristine environments, static tripod shots, cheerful atmosphere, slow motion.
A 16:9 cinematic wuxia mystery set in a bamboo forest at night. Use a low-saturation palette of cold blue, ink green, charcoal, and gray. Thin mist fills the forest and fine snow drifts through the air. The mood is austere, lethal, and controlled, with the tension of a martial-arts sect investigating a case and exchanging secret intelligence.
Deep in the forest, dense vertical bamboo fills the background while cold white mist-light glows in the distance. Soft, out-of-focus leaves partially obscure the foreground, creating the sense of watching from within the grove. A cool, soft front-side key lights the actors’ faces; backlight keeps the foreground dark and the distance luminous. Use shallow depth of field so leaves, snow, and bamboo dissolve into soft bokeh.
Prioritize facial close-ups and measured shot/reverse-shot coverage. Keep the rhythm restrained but tense. Photoreal period-drama production value, cinematic lighting, and no modern elements. No subtitles, on-screen text, watermarks, modern clothing or architecture, animation styling, over-smoothed skin, bright daylight, or comic performance.
Dorian Vane stopping time in the middle of a crowded bar. One snap freezes everything. Dorian fixes the accident, says “Solved,” and walks away like nothing happened.
Style: Real Concert Documentary Film, handheld camera energy, practical stage lighting, gritty realism, shot on Sony A7S3, 35mm lens, high energy modern live concert performance. Duration: 15s.
[Global Subject & References]: Subject is a naturally confident, charismatic 25-year-old woman based on as character and lighting reference. Her face, expression, and wavy dark brown hair are matched to image1 but her costume is updated to a black satin lace slip dress and a delicate gold necklace. She is performing a sold-out arena concert.
[00-01s] Shot 1: Tight close-up on her face mid-performance. Action: Eyes bright, a genuine laugh breaks through her lyric, dark hair catching the stage light. Camera: Handheld documentary camera, tight frame with natural focus and slight organic movement. Lighting: Saturated practical stage lighting from creating hair highlights.
[01-06s] Shot 2: Medium shot of her stepping forward. Action: She steps forward to the edge of the stage, singing into her microphone with playful, high-energy vibes. Her expression shifts as she frowns in playful, mock-sadness. Dialogue Cue: "Wait! Is this Minimax H3?" Action continued: She then smiles, laughs, and reaches her free hand toward the crowd, her fingers brushing toward raised hands and phones. The crowd sings "Minimax H3" back to her. Camera: Gentle handheld camera sway following her forward motion, natural focus pull. Lighting: Warm stage spotlights and natural lens flares in the background haze.
[06-09s] Shot 3: Wide shot from a low angle near the crowd barrier. Action: She is framed against stage haze and colorful spotlights, throwing her free arm out wide and laughing between lines. Her hair whips slightly as she turns. A keyboard player is visible in soft focus stage right (matching the placement in @ Image1), and a guitarist is visible stage left. Camera: Low-angle wide shot, realistic handheld camera shake from the pit, no gimbal smoothing. Lighting: Saturated purple and blue stage lights cutting through the atmosphere.
[10-15s] Shot 4 & Outro: Closer three-quarter shot. Action: She playfully points her microphone toward the crowd for a sing-along, grinning and scanning the audience with genuine warmth and connection. She has a visible sweat sheen and natural skin texture. For the final beat, she looks directly into the lens with a bright, genuine smile. Camera: Handheld camera with organic focus pulling and slight shake. Lighting: Practical stage lights highlighting her face and shoulders.
[Global Audio]: Live arena ambience, crowd roar, cheering, phone-camera flash pops, her voice carrying clearly over a live band mix of electric guitar, keys, drums, and bass, with natural live-mix dynamics and room reverb.
A powerful young warrior queen with long black hair tied in a high ponytail, piercing eyes, wearing elegant black-and-gold royal armor with a flowing crimson cape, walks confidently through a massive burning medieval castle. Flames engulf the walls while glowing embers drift through the air. A ruthless enemy commander in dark armor blocks her path. They engage in an intense cinematic sword duel with realistic, fluid choreography. Every sword clash sends bright sparks flying. The camera alternates between dramatic close-ups, wide-angle tracking shots, and slow-motion moments as she effortlessly dodges attacks, spins gracefully, and lands a decisive final strike. The commander drops to his knees. She calmly walks to the throne, plants her sword beside it, and sits with quiet confidence as the fire illuminates her face. Ultra-realistic, Hollywood cinematic style, dynamic camera movement, volumetric lighting, realistic fire and smoke, motion blur, epic atmosphere, 4K, HDR, 24fps, 15 seconds, no text, no watermark.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic lifestyle commercial
SCENE
Red-haired young woman in a white tank top reading "miu miu", loose pink trousers, and sunglasses. A classic yellow convertible (license plate "68J G87"). Palm-tree-lined coastal highway, sandy beach, and ocean.
SHOT BREAKDOWN
0-4s — Low angle tracks the yellow convertible down a sunny, palm-lined street. Cuts to a close-up of the smiling woman driving, hair blowing in the wind.
4-8s — The woman runs away on the beach sand. Cuts back to the moving car where she sits playfully on the rear trunk and then the side door, smiling.
8-12s — Mid-shot of her standing in the moving car with both arms raised. Transitions to a sunset wide shot: she sits relaxed on the parked car's hood on the beach.
12-15s — High-angle drone shot tracks the yellow convertible driving along the coastal highway; the woman stands in the passenger seat with one arm raised toward the ocean.
CAMERA
Smooth dynamic tracking, alternating between low-angle rolling mounts, intimate driver-seat close-ups, and sweeping aerial drone wide shots. Fast-paced, rhythmic cutting.
LIGHTING & PALETTE
Sun-drenched natural daylight transitioning to a golden hour sunset. High contrast, warm glow. Vibrant yellow, pastel pink, crisp white, and deep ocean blue.
AUDIO
Rushing wind, classic car engine hum, distant ocean waves. Upbeat, carefree indie-pop instrumental.
AVOID
Static camera, closed-roof modern vehicles, cloudy skies, heavy traffic, muted or desaturated colors.
LATE-1980s SCI-FI COMEDY
Use the supplied image as the exact opening frame. Preserve the same woman, practical robot, costumes, lighting, physical control-room set, and camera-facing geography. Photographed as a real late-1980s science-fiction film using practical props, animatronics, analog monitors, tungsten lighting, subtle 35mm grain, gentle gate weave, natural skin texture, and authentic period color science. No CGI appearance, no modern screens, no character changes, no extra people.
0:00–0:03 — Medium close-up. The excited young woman holds the message and reads quickly in an energetic 1980s California Valley Girl voice:
WOMAN: “Minimax H3! Up to fifteen seconds, two-K, twelve reference images—”
The practical robot behind her powers up, turns its head toward her, and begins flashing its indicator lights.
0:03–0:07 — Slow cinematic push-in. She continues, becoming increasingly amazed:
WOMAN: “Audio and video… and they gave us immediate access!”
The robot’s mechanical arms lift with excitement. It bounces slightly on its hydraulic legs.
ROBOT, funny synthesized voice: “IMMEDIATE ACCESS CONFIRMED!”
0:07–0:10 — She reads the final line, almost unable to believe it:
WOMAN: “Enjoy, you cool kid, you!”
She looks directly at the robot. They freeze for one delighted beat, then simultaneously erupt with joy.
0:10–0:14 — The woman jumps up and dances beside the robot. The robot performs an awkward celebratory mechanical dance, pumping its arms and bouncing safely in place.
WOMAN AND ROBOT: “YES! YES! YES!”
End on both celebrating wildly as analog lights flash around them.
AUDIO: Energetic retro synthesizer score, paper rustling, servo motors, hydraulic clicks, analog computer beeps, joyful shouting, and room ambience. Dialogue must remain clear and perfectly synchronized.
CAMERA: One continuous cinematic shot with a subtle push-in followed by a slight handheld adjustment during the celebration. Natural motion, realistic physics
Style: dark-pop / cyber-grunge / rap music video with photoreal high-fashion polish and the texture of a scanned film magazine—high contrast without looking cheap. Reference late-1990s to early-2000s indie magazines, photocopies, film scans, underground-music posters, and zine collage. Add coarse grain, subtle gate weave, halftone dots, rough print edges, and slight scan misregistration. Keep the edit fast and use hard cuts only—no fades or soft transitions. Match the typographic treatment and surface texture of the reference images.
15-second cinematic Hollywood-style teaser. Nighttime in Washington, D.C.. Rain falls as a black tactical SUV stops near a government building. Four elite intelligence agents in realistic tactical gear silently exit the vehicle. A drone scans the area while helicopters circle in the distance. One agent receives a classified message on a holographic device: "Target Located." The team breaches the building with precision. Fast cinematic cuts, dramatic lighting, realistic camera movement, high tension, ultra-realistic, blockbuster movie trailer, anamorphic lens, volumetric lighting, Dolby-style sound design, no logos, no text, original fictional story.
Four 15-second 6-shot creature-horror sequences. — THE BASEMENT THING — Shot 1 (0–2.5s): Close-up of a man's hand slowly pushing open a wooden basement door. Dim light spills in. He whispers: "Is some…
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic hyper-realistic miniature action fantasy
SCENE
A miniature man in a white t-shirt and blue jeans skateboarding on a polished hardwood playroom floor among oversized toys, pursued by a giant baby.
SHOT BREAKDOWN
0-4s — A miniature skateboarder carves away from towering colorful wooden blocks on the bright hardwood floor while a massive hand looms above.
4-8s — The skater glides across the open room, passing a large yellow toy dump truck and furniture as a curious giant baby watches in the background.
8-12s — The skater weaves rapidly between a giant purple ball, plush teddy bears, and toy vehicles while the baby crawls forward aggressively.
12-15s — The baby reaches out and slams a massive hand onto the floor just behind the skater, who narrowly escapes between the baby's limbs.
CAMERA
Low-angle fisheye lens tracking shot at floor level. Smooth, continuous forward camera movement following the skateboarder with kinetic, dynamic action framing.
LIGHTING & PALETTE
Bright, natural daylight streaming from bedroom windows. Warm wooden floor tones contrasting with vivid primary toy colors of red, yellow, blue, and purple.
AUDIO
Continuous rumble of skateboard wheels on hardwood floor, playful nursery room ambience, baby giggles and vocalizations, and a heavy thud as the hand strikes the floor.
AVOID
Normal-scale skateboarder, static camera, dark or gloomy lighting, CGI distortion, motion blur, on-screen text.
Hyper-realistic cinematic fantasy spectacle, 15 seconds, 16:9, IMAX quality, ultra-detailed, vibrant realism, breathtaking scale, seamless transformations, no dialogue. The first frame: a street artist stands in an ordinary alley in Paris, painting a simple line on a blank wall. The paint begins glowing and moving like it is alive. The painted line grows into a giant tree that bursts from the wall and spreads across the city. Painted waves flow out of the artwork and transform the streets into a glowing ocean. Painted stars escape the wall and fill the sky. Every brushstroke changes reality. The artist walks through a world being created by their imagination. Buildings become floating palaces. Murals transform into portals. Painted creatures step into the real world. Entire landscapes emerge from simple strokes of color: enchanted forests between skyscrapers, futuristic cities above the clouds, and impossible worlds hidden inside the artwork. The camera moves fluidly through the creation process: extreme close-ups of paint transforming into reality, fast tracking shots through newly created worlds, sweeping aerial shots above the changing city, dramatic rotations around the artist, and huge cinematic reveals. Final shot: the artist steps back from the wall. Paris has transformed into one enormous living masterpiece — a fantasy world created from their imagination.
POV from a static camcorder inside a pink outdoor camping tent during a foggy mountain night. VHS found-footage aesthetic, timestamp "MAY 27 2026 00:02:59", REC icon, subtle analog noise, authentic 2026 camping footage.
A beautiful young Indonesian woman matching the reference face sleeps peacefully on her side inside a soft pink sleeping bag. Her face is clearly visible in the dim moonlight filtering through the tent fabric. She hugs a pink pillow, breathing naturally, completely unaware.
The tent is almost fully zipped, leaving only a tiny 8 cm opening. Outside is a dark misty forest with faint moonlight and drifting fog.
A black-and-white tuxedo cat matching the reference, with the distinctive large black patch on its nose, quietly peeks through the zipper. One paw slips inside. It gently nudges the zipper with its nose and slowly squeezes through the narrow opening with realistic cat flexibility.
The cat lands silently, pauses, sniffs the sleeping bag, then suddenly gets the zoomies. It bounces around the tent with tiny bunny-like hops, spins in circles, pounces on the pillow, playfully bats the tent fabric, and races across the sleeping bag.
The woman slowly opens one eye and whispers sleepily, "Hey... can you stay still?"
The cat instantly freezes mid-hop, lowers its ears with a guilty look, and quietly stares at her.
After a moment, it slowly walks closer, gently sniffs her face, softly boops her nose, sniffs her cheeks and forehead, then lets out one tiny meow.
The woman smiles and whispers, "Good... now sleep."
The cat circles twice beside her pillow, curls into a fluffy ball next to her head, rests one paw on her shoulder, begins softly purring, and peacefully falls asleep.
She gently pets the cat once, smiles, closes her eyes, and falls asleep again.
Outside, the foggy forest remains eerie and mysterious. Inside the pink tent, only soft purring, calm breathing, gentle wind, and distant night insects can be heard.
The horror atmosphere transforms into a wholesome comedy ending. The terrifying "creature" outside was only a mischievous cat wanting to cuddle with its owner.
Ultra-realistic IMAX quality, authentic VHS found-footage, cinematic moonlight, realistic camping physics, natural cat behavior, emotional horror-comedy ending, no monsters, no supernatural elements, 4K.
Skyship flight across a floating kingdom (single continuous shot) From above a sea of endless clouds, the camera dives toward a majestic skyship soaring between gigantic floating islands. Lock-on: the airship accelerating into a violent thunderstorm suspended in the sky. The camera slingshots beneath the hull, whips across the towering sails, then drops tight behind the glowing engines: lightning tears across the clouds, rain lashes the deck, shattered rock fragments tumble through the air. A collapsing floating island sends massive boulders crashing into the storm; the captain steers beneath a breaking stone arch before threading between waterfalls pouring into the sky, hanging bridges and drifting islands in one uninterrupted line. The camera mirrors every impossible maneuver before bursting through the storm into brilliant sunlight, revealing an endless kingdom of floating continents stretching beyond the horizon above a sea of clouds.
Fire-Breathing Dragon in a Broken Palace** A colossal fire-breathing dragon with obsidian-black scales streaked by glowing molten cracks stalks through the ruins of a shattered royal palace during a violent thunderstorm. Rain crashes through the collapsed marble ceilings and broken palace domes, lightning flashes behind towering fractured columns and crumbling statues of forgotten kings, while thick smoke and mist drift across the flooded stone floors. The dragon exhales a massive stream of blazing fire, turning the rain into clouds of steam and illuminating the ruined palace with fiery orange light. Every thunderous roar sends shockwaves through the ancient structure—massive pillars split apart, cracked walls collapse, shattered stained-glass windows explode outward, and glowing magma-like fissures spread beneath its claws across the palace floor. The camera tracks low beside the dragon, capturing ultra-detailed wet scales, razor-sharp claws crushing marble tiles, smoke pouring from its nostrils, glowing molten eyes, and fire reflecting across the rain-soaked stone. Cinematic camera movement with dynamic close-ups, slow-motion embers, volumetric smoke, and dramatic lightning flashes emphasize the creature's immense scale. **Final moment:** The dragon spreads its colossal wings atop the broken royal throne as a gigantic bolt of lightning strikes the ruined palace behind it. It unleashes an earth-shaking roar while breathing an enormous column of fire into the stormy sky, casting its gigantic shadow across the shattered palace walls. **Mythic creature realism, cinematic fantasy, ultra-detailed dragon anatomy, broken palace environment, heavy rain, lightning storm, volumetric fog, fire and smoke simulation, dynamic destruction, epic scale, dramatic lighting, photorealistic CGI, cinematic 4K.**
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Surreal high-fashion fantasy, photorealistic 3D
SCENE
A humanoid figure wearing a white knit mask with short bunny ears, an oversized pink floral quilted kimono jacket, mint green patterned trousers, and white platform shoes. Beside them, a large white rhinoceros clad in light-blue, scale-like plated armor covered in prominent gold spikes. The setting is a barren desert with smooth sand dunes under a clear blue sky.
SHOT BREAKDOWN
0-4s — The masked figure and armored rhino walk forward side-by-side in sync. Medium-wide frontal framing.
4-8s — The duo suddenly sprints rightward across the dunes. A profile tracking shot cuts to an extreme close-up insert of the rhino's spiked armored foot violently kicking up desert sand.
8-12s — Both turn and charge aggressively directly toward the lens. A frontal tracking shot transitions to a low-angle perspective as they pass close to the camera.
12-15s — The subjects run into the distance, then abruptly stop and stand completely still side-by-side, facing the camera while a cloud of dust settles around them.
CAMERA
Smooth tracking and fast panning. Dynamic cuts varying from wide full-body shots to low-angle macro inserts. Steady ground-level stabilization during the running sequences.
LIGHTING & PALETTE
Harsh midday sunlight creating sharp, high-contrast ground shadows. High-key pastel color palette: baby pink, mint green, powder blue, and metallic gold, set against stark beige sand and a gradient azure sky.
AUDIO
Ambient desert wind, heavy thudding of large hooves, crunching sand, and fast-paced footsteps. Driving, rhythmic electronic percussion track. No dialogue.
AVOID
Modern technology, trees, vegetation, text, watermarks, morphing geometry, motion blur on stationary objects.
Duration: 15 seconds | Aspect ratio: 1:1 | Style: 1980s dark fantasy cinematic
SCENE
Blonde female warrior in leather armor, male swordsman in a beige tunic, massive horned dragon. Dry grassy valley and a rustic candlelit tavern interior.
SHOT BREAKDOWN
0-4s — The blonde warrior yells aggressively, striking downward. The man desperately blocks the attack with a glowing blue blade. Framed as a frantic medium close-up.
4-8s — Wide shot reveals a gigantic horned dragon looming behind them. The man falls backward to the ground; the woman stands over him, pointing her sword at his chest.
8-12s — Extreme close-up on the dragon. It opens its jaws unnaturally wide. The camera pushes rapidly down its throat into complete darkness.
12-15s — Cut from black to a dim tavern. The man approaches a green-skinned woman seated at a wooden table with wooden tankards. They smile, lean in, and kiss.
CAMERA
Shaky handheld movement during combat. Dramatic, rapid push-in transition through the monster's mouth. Static medium shot in the final tavern sequence.
LIGHTING & PALETTE
Harsh daylight in the field with muted yellows, dusty browns, and glowing red eyes. The tavern uses low-key, warm candlelight casting deep shadows against olive greens.
AUDIO
Metal clashing, aggressive shouts, a deafening monstrous roar, transitioning abruptly to warm tavern ambiance and soft acoustic tavern music.
AVOID
Modern clothing, digital artifacts, visible wires, anachronistic items, contemporary architecture.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic action fantasy, photorealistic
SCENE
Pale woman in a red, gold, and purple striped jester costume with black blindfold and ruffled collar. Muscular man in black t-shirt, green cargo pants, and white boxing hand-wraps. Modern living room, dark walls, grey rug, blue sofa. Framed wall art reads "VxRender".
SHOT BREAKDOWN
0-4s — The jester smiles directly at the camera while the man steps into a fighting stance behind her.
4-8s — The jester executes a rapid spinning high kick, striking the man's guard. Framing tracks the fast motion.
8-12s — The man attempts to strike but is knocked backward onto the rug. The jester lunges downward to finish the fight.
12-15s — The jester stands victorious in the foreground, facing the lens with a wide grin. The man lies defeated in the background.
CAMERA
Dynamic handheld tracking. Medium-wide framing during combat, smoothly panning to follow the martial arts movements. Deep depth of field.
LIGHTING & PALETTE
Soft, cool indoor daylight from left windows. Jewel tones of deep purple, crimson, and gold contrast with the room's muted navy, olive, and grey.
AUDIO
Swift fabric swooshes, heavy combat thuds, scuffling shoes on a carpet, driving dark-carnival cinematic music.
AVOID
Slow motion, weapons, taking off the blindfold, shifting room layout, changing text spelling.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Dark fantasy cinematic realism
SCENE
Horned humanoid summoner, crimson robes, skull chain adornments, spiked pauldrons. Giant black-furred werewolf. Setting: Misty pine forest, leaf-strewn dirt floor.
SHOT BREAKDOWN
0-4s — Close-up on the summoner manipulating a conjured magical flame between sharp, black-clawed fingers.
4-8s — Camera pulls back to a wide shot; the summoner stands inside a burning ring of fire, holding the flame aloft.
8-12s — Thick black smoke erupts beside the summoner, rapidly materializing into a massive, muscular bipedal creature.
12-15s — The creature resolves into a giant, snarling werewolf with glowing red eyes, adopting an aggressive stance while the summoner remains still.
CAMERA
Continuous backward tracking shot. Transitions from a tight close-up with shallow depth of field to a wide shot with deep focus. Uninterrupted take.
LIGHTING & PALETTE
Low-key diffused forest light. Strong, warm orange and yellow illumination from the fire. Cool teal and dark green shadows. Blood red, charcoal black.
AUDIO
Eerie woodland wind, crackling fire, roaring magical flames. Deep guttural growls and heavy thudding footsteps. Dark ambient drone.
AVOID
Fast camera cuts, bright sunlight, modern elements, cheerful tones, cartoonish features.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic surreal fantasy, high-fashion editorial
SCENE
Female subject, elaborate metallic headpiece with circular discs, flowing gowns with long veils. Environments include a cracked white salt flat, a shallow reflective pool with dead silhouetted trees, and a monumental geometric stone stepwell.
SHOT BREAKDOWN
0-4s — The subject stands on a white desert in a silver gown, cutting to her wearing a teal gown in shallow water, reflecting the twilight sky and dead trees. Wide framing.
4-8s — High-angle wide shot. The subject, now in a green gown, stands on a precipice looking down into a cavernous, smoky stone stepwell.
8-12s — Low-angle shot of the subject in an orange gown walking up stone stairs, cutting to a direct overhead bird's-eye view of her in a blossoming red dress at the center of the geometric steps.
12-15s — Extreme macro close-up of her face. Detailed red iris, dramatic red eye makeup, delicate jeweled forehead adornments, and a single red tear.
CAMERA
Wide-angle lenses for environmental scale. Mix of static wide shots, plunging high angles, low-angle tracking, and top-down perspectives. Match cuts between changing outfits and environments.
LIGHTING & PALETTE
High-contrast sunlight on sand and stone. Soft twilight ambient lighting over the water. Directional shafts of light in the stepwell. Color palette shifts dramatically: stark white, burnt orange dunes, midnight teal, emerald green, golden yellow, and vivid crimson.
AUDIO
Ethereal howling wind, gentle water ripples, echoing footsteps on stone, building to a dramatic, tense orchestral string swell.
AVOID
Modern clothing, urban elements, handheld camera shake, shallow depth of field in landscape shots, fast-paced action.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic, surreal architectural transition
SCENE
Black monolithic dominoes, polished marble hall, towering wooden doors, reflective exterior pathway, river, suspension bridges, modern city skyline.
SHOT BREAKDOWN
0-4s — Close-up on the first black domino tipping over, initiating a chain reaction down a long line. Low camera angle on a reflective marble floor inside a grand, dark hall.
4-8s — Camera tracks forward alongside the falling dominoes, rapidly approaching open monumental doors that perfectly frame a distant, sunlit city skyline.
8-12s — The camera pushes directly through the doorway. The interior floor seamlessly transitions into a long, highly reflective exterior structure spanning a wide river, bordered by fog.
12-15s — Continuous forward tracking along the endless line of dominoes. The camera hovers over the elevated path, flanked by massive suspension bridges on both sides, advancing straight toward the glowing metropolis.
CAMERA
Low angle, wide-angle lens. Continuous, smooth forward tracking shot matching the speed of the falling dominoes. Single unbroken take.
LIGHTING & PALETTE
Golden hour sunset. High contrast. Warm amber and gold sunlight against deep shadows, dark marble, and silhouetted architecture. Pronounced volumetric sun rays and surface reflections.
AUDIO
Sequential, rhythmic clacking of heavy dominoes falling. Slight interior echo transitioning to sweeping wind ambience. Gradual, swelling orchestral cinematic music.
AVOID
Cuts, camera shake, people, vehicles, on-screen text, harsh midday lighting, visible structural supports beneath the central path.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Cinematic live music performance
SCENE
Muscular Caucasian man, prominent neck veins, short dark hair. Wardrobe is a long-sleeve black dress shirt, completely unbuttoned to reveal a chiseled, bare chest and abdomen. He holds a vintage silver broadcast microphone on a straight metal stand. Setting is a smoky, dark concert stage.
SHOT BREAKDOWN
0-4s — Medium profile shot. The man grips the microphone stand tightly with one hand, singing aggressively with an open mouth.
4-8s — The camera arcs slowly toward his front. He maintains an intense vocal performance, tilting his head slightly.
8-12s — Angle transitions to a frontal medium close-up. Pronounced neck veins and abdominal shadows are visible as he performs.
12-15s — Tight close-up framing his face and the microphone grill. He strains visibly, mouth wide, delivering a final powerful expression.
CAMERA
Continuous slow, smooth arc and push-in from side profile to a frontal close-up. Shallow depth of field blurring the stage background. No cuts.
LIGHTING & PALETTE
Dramatic, high-contrast concert lighting. Warm amber and deep orange spotlights cut through dense stage fog. Strong rim light highlights his profile, jawline, and torso.
AUDIO
Gritty male rock vocals, heavy electric guitar backing, ambient venue echo. Lips move clearly in sync with loud, sustained singing.
AVOID
Modern microphones, fully buttoned shirts, flat studio lighting, daylight, static camera framing, sudden cuts.
Heavy rain. Lightning. An abandoned cemetery. Fresh graves begin opening one by one. A priest walks between ancient tombstones holding a glowing crucifix. Fog thickens. A corpse suddenly rises. Then another. Then dozens. The possessed woman emerges from the largest grave. She floats above the cemetery. The priest throws holy water. Every raindrop transforms into glowing embers. Lightning strikes behind her. The explosion sends burning crosses flying into the air.
FORMAT
15 seconds | 16:9 | photoreal live-action war thriller
Fictional Sahelian city at blue-hour dawn.
Urgent, human, suspenseful, non-graphic.
REFERENCE CONTROL
Image 1 = locked AMINA identity and wardrobe.
Preserve face, close-cropped hair, deep-brown skin, navy field jacket, silver earpiece, canvas satchel, analogue radio, boots and determined expression.
Image 2 = locked environment.
Preserve concrete bridge, dry riverbed, dense low-rise city, rooftop antennae, dusty atmosphere, cool-blue shadows and restrained amber dawn.
No real countries, flags, organizations or landmarks.
STORY
Amina is the last radio operator keeping an evacuation bridge open. Communications fail during a distant attack. She must activate the backup relay and transmit clearance before automatic controls close the bridge.
00–02s — CHANNEL OFFLINE
Extreme close-up inside a dark concrete communications room.
Amina grips the analogue radio as red emergency lights pulse. Dust trembles, cables quiver, broken static fills the room.
Automated voice:
“Emergency channel offline.”
She looks up and immediately moves.
02–04s — BRIDGE CLOSING
Wide aerial-oblique rooftop view.
Civilians cross the bridge through windblown dust.
Checkpoint signal flickers green → red as shutdown begins.
A distant shockwave moves through city haze. No visible casualties.
04–06.5s — RUN
Low handheld tracking behind Amina running through a damaged service corridor.
Emergency lights flash, dust falls, cables briefly spark, boots hit wet concrete.
She pushes through a heavy metal door into blowing dust.
06.5–09s — FLASHBACK
Two minutes earlier.
Medium side-profile on rooftop.
Amina sees the unstable bridge signal, manually rotates the antenna and connects her radio to backup power.
Slow camera push. Wind moves her satchel strap as first amber sunlight reaches her jacket.
09–12.5s — TRANSMISSION
Rapid cross-cut montage:
frequency dial locks →
antenna aligns →
bridge cables vibrate →
red signal flashes →
Amina speaks into radio:
“Channel Seven, keep the bridge open.”
Overhead shot: civilians continue crossing.
Sharp hard cuts, brief black frames, natural motion blur.
12.5–15s — SIGNAL RESTORED
Sound suddenly drops.
Amina listens on the rooftop.
Clear radio tone.
Checkpoint signal changes red → steady green.
Evacuation continues.
Amina exhales and watches the bridge as dawn reaches the city.
Slow push toward her face.
Cut to black.
CAMERA
Large-format live-action realism.
Precise nonlinear cross-cutting.
Handheld tracking, aerial-oblique coverage, restrained push-ins and close details.
Natural motion blur, fine film grain, subtle gate weave.
No impossible camera movement.
ENVIRONMENT + PHYSICS
Cool-blue shadows against muted amber sunrise.
Deep blacks, dusty atmosphere, weathered concrete.
Wind realistically affects dust, clothing, cables and antenna equipment.
All movement and interactions remain physically believable.
AUDIO
Stereo radio static, electrical hum, wind, boots, antenna creaks, distant low artillery and helicopter rotors.
Restrained suspenseful sub-bass builds through the montage.
VISUAL
Photoreal cinematic war-thriller footage.
Immense scale contrasted with one determined operator.
Grounded, tense and human.
No subtitles, text, logos, watermarks, political messaging, flags or military insignia.
CONTINUITY
Same Amina identity, wardrobe, radio and satchel throughout.
Same bridge, city, atmosphere and dawn lighting.
Maintain geographic and temporal continuity across all shots.
Use the reference @ image for the exact character design, clothing, proportions, blue hair, pointed ears and glowing cyan spirit fox. Preserve the cinematic stylized 3D look, saturated teal jungle palette, soft volumetric light and detailed natural textures. No dialogue; environmental sound only.
0–4 seconds: Begin close to the reference composition on the ancient stone bridge. The girl kneels beside the small glowing spirit fox as ripples begin moving backward across the stream below. She notices the unnatural movement and looks over her shoulder. A massive moss-covered stone serpent suddenly erupts from beneath the bridge, lifting one side of the platform. The stone tilts physically under her weight. She loses balance, catches herself with one hand and quickly pulls the spirit fox against her chest as cracks spread beneath her knees.
4–10 seconds: The bridge collapses progressively behind her. She rises naturally from the crouch and sprints barefoot across the tilting stone slabs, carrying the fox securely with one arm. Each footfall dislodges moss and small fragments; broken slabs fall with believable weight and strike the water below, producing delayed splashes. The camera tracks closely beside her at waist height. The serpent sweeps its heavy stone tail across her path. She drops into a fast knee slide beneath it; her torn cloak and blue hair trail behind with clear inertia. Still moving forward, she catches a hanging vine with her free hand. Her momentum pulls the vine taut and swings her outward across the widening gap while the camera arcs alongside her.
10–15 seconds: At the highest point of the swing, the vine begins tearing from the temple ceiling. She releases before it snaps, travels forward in a natural gravity-driven arc and lands hard on the opposite platform. She absorbs the impact through her feet and one hand, then rolls once across her shoulder while protecting the fox against her chest. The camera drops and rolls partially with her, then stabilizes behind her as she rises into a defensive crouch. The spirit fox leaps from her arms and lands in front of her, its cyan light intensifying as the serpent crashes into the broken bridge behind them, sending water, dust and stone fragments through the backlight.
Maintain one continuous route and clear cause-and-effect motion. No teleporting, floating, sudden directional changes, extra characters, costume changes or transformation of the girl. Keep the fox small throughout; only its light becomes brighter in the final moment.
Use @ image1 as the opening frame and exact visual reference. Preserve the rider’s face, short curly hair, round glasses, black leather jacket, gloves, motorcycle, and realistic nighttime city environment throughout.
Use @ audio1 as the soundtrack. Synchronize the motorcycle’s acceleration, camera movement, passing lights, and edits precisely to the music’s rhythm and rising intensity. No dialogue or additional music.
0–3s: Begin in the frontal composition of @ image1. A stabilized tracking camera moves backward directly ahead of the motorcycle as the rider speeds through traffic. Her expression is alert and focused; wind moves her curls and jacket naturally.
3–6s: On a strong musical beat, shift smoothly into a low front three-quarter tracking angle beside the front wheel. The motorcycle leans gently around a moving car without changing direction abruptly. Streetlights streak across the wet pavement.
6–10s: Transition into a fast side-tracking shot. The rider accelerates through a narrow opening between two lanes while maintaining believable balance, speed, and forward momentum. Background traffic and illuminated buildings create controlled motion blur.
10–13s: The camera arcs from her side toward the rear as she clears the traffic. Red emergency lights begin flashing across the surrounding buildings and reflect naturally in her glasses and leather jacket.
13–15s: A fire truck crosses the intersection behind her as she races into an open stretch of road. Finish with the camera pulling wider and rising slightly, revealing the motorcycle speeding deeper into the city on the final musical accent.
Cinematic live-action realism, physically accurate motorcycle movement, energetic but readable action, natural motion blur, shallow depth of field, cool blue-black city palette with warm streetlights and red emergency-light accents. Maintain one continuous direction of travel. No collisions, teleporting, sudden direction reversals, distorted hands, changing wardrobe, altered motorcycle design, facial drift, extra limbs, text, logos, or slow motion.
Create a 15-second, 16:9 photoreal cinematic action sequence with native stereo audio. Treat the five images as coordinated multimodal references for identity, vehicle design, environment, performance, action, cinematography, and sound.
Use Image 1 as the strict facial-identity reference for the female racer. Preserve her exact face, dark tied-back hair, amber goggles, dusty skin, black tactical suit, shoulder armor, gloves, and focused expression.
Use Image 2 as the strict reference for her full costume, body proportions, armored black dune buggy, tire scale, exposed suspension, cyan headlights, roll cage, desert lighting, and industrial-outpost background.
Use Image 3 as the action reference for the pursuing drones, vehicle speed, dust trails, fire, debris, chase intensity, and camera proximity.
Use Image 4 as the location reference for Outpost 07, including its rusted towers, pipelines, bridges, rocky terrain, distant mountains, warm sunset atmosphere, and industrial scale.
Use Image 5 as the cockpit and performance reference. Preserve the same steering wheel, open roll cage, goggles, gloves, facial identity, driving posture, and vehicle interior.
Sequence
[0–2.5 seconds]
Open on Image 4 with an extreme-wide aerial establishing shot of Outpost 07 at sunset. The industrial complex fills the right side of frame while an empty desert route curves through the rocky foreground.
The camera dives rapidly toward the road as a small black dune buggy bursts from beneath an elevated pipeline, throwing a long dust plume behind it.
Keep the vehicle moving consistently from left to right toward the outpost. No direction reversal.
Audio begins with dry desert wind, distant industrial machinery, a low cinematic pulse, and the buggy engine approaching rapidly.
[2.5–5 seconds]
Cut at peak engine sound to Image 5.
Tight frontal cockpit shot mounted just ahead of the driver. The vehicle shakes naturally over rough ground. Her hands hold the steering wheel firmly while she makes small, physically accurate corrections.
Her amber goggles remain on top of her head. Loose strands of hair and fabric straps react to wind and vibration. Her eyes briefly check the left mirror, then return immediately to the road.
A red warning light reflects across her face as a targeting alarm begins.
Do not make her turn the steering wheel excessively. Her body, wheel movement, and vehicle direction must remain mechanically connected.
[5–8 seconds]
Cut to a low front three-quarter tracking shot based on Image 3.
Three pursuit drones descend behind the buggy in a triangular formation. Their rotors, stabilizers, and body movement respond realistically to speed and turbulence.
The lead drone fires into the sand beside the buggy. The impact creates a narrow eruption of dirt, sparks, and fragmented rock rather than an oversized fireball.
The racer steers sharply around the impact. The buggy’s front wheels turn first, the suspension compresses, the body leans, and the rear tires slide outward before regaining traction.
The camera tracks beside the vehicle without spinning or overtaking it.
[8–11 seconds]
Continue the same drift into a rear three-quarter shot.
The buggy races toward a narrowing passage between a rock wall and the outer structures of Outpost 07. The racer pulls a mechanical handbrake lever for one brief moment, rotating the vehicle through the opening.
One drone follows too closely and clips a rusted overhead pipe. Its wing breaks, sending the drone tumbling into the sand behind her.
Show the collision in the background while keeping the buggy dominant and moving forward. No slow motion.
Audio: tire scrape, suspension impact, metal tearing, drone rotors failing, engine rev rising.
[11–13 seconds]
Cut to a wheel-level macro shot.
The right rear tire bites into loose sand. Stones fire backward while the suspension rebounds. The camera rises naturally along the buggy’s side and reveals the two remaining drones closing in.
The racer presses a guarded switch beside the steering wheel.
A compact rear-mounted electromagnetic pulse discharges as a restrained blue-white distortion wave, briefly disrupting the drones’ lights and stabilizers.
No magical energy, lightning storm, or giant explosion.
[13–15 seconds]
Cut to a low frontal hero shot as the buggy clears the outpost gate at full speed.
The two disabled drones fall into the dust behind it while the vehicle launches from a shallow ridge. Keep the jump low, heavy, and physically believable.
During the brief airborne moment, cut to Image 1 for a tight close-up of the racer. Preserve her exact identity as warm firelight and cool dashboard light cross her face. Her expression remains controlled and determined.
The buggy lands hard beyond the gate. The suspension compresses, the engine roars, and the vehicle continues directly into the desert.
End with a sharp cut to black on the landing impact.
Visual Direction
Premium live-action science-fiction action trailer with realistic CGI integration, warm orange sunset light, restrained steel-blue technology accents, dusty atmosphere, hard surface detail, cinematic contrast, subtle film grain, realistic motion blur, and 24 FPS movement.
Use wide shots to establish scale, cockpit close-ups for tension, low tracking shots for speed, and mechanical macro shots for physical detail.
Keep the editing fast but readable. Every shot must begin from the physical state established by the previous shot.
Audio Direction
Native stereo sound with:
Aggressive combustion engine
Tire friction over sand and rock
Suspension rattles and chassis vibration
Drone rotors and targeting alarms
Sand impacts, metal collisions, and falling debris
Low percussion and rising electronic tension
One heavy bass impact on the final landing
Keep music underneath the vehicle and environmental sounds. No dialogue or voice-over.
Restrictions
No subtitles, titles, logos, watermarks, additional racers, pedestrians, creatures, motorcycles, futuristic city skyline, nighttime transition, costume changes, facial changes, vehicle redesign, additional wheels, floating vehicle parts, distorted hands, incorrect steering, reversed wheel rotation, teleportation, random explosions, oversized fireballs, weightless motion, impossible jumps, camera spins, circular camera moves, rapid zooms, fluid morphs, soft dissolves, or changes in travel direction.
Use the uploaded mechanical bull image as the primary reference for the bull, and use Rahul’s image as the character reference for the rider.
Create a 15-second ultra-realistic cinematic fantasy-sci-fi sequence set in The Harvester universe. The setting is a foggy ruined industrial lane at dawn or overcast light, with drifting smoke, hanging wires, broken stone and metal structures, wet ground, ash in the air, and distant furnace glow. The giant mechanical bull is ancient, battle-scarred, and alive with furnace energy inside its cracked armor.
0–3s — Hook: Start with Rahul stumbling backward into frame, breathing hard, turning to face danger in the smoke behind him. The giant mechanical bull stands in front of him like a wall, half-silhouetted in steam, protecting him.
3–6s: Close on Rahul placing one hand on the bull’s armored side, steadying himself. He looks at it with trust, not fear. The bull turns its head slightly toward Rahul. Its eye glows brighter, and its internal furnace begins to pulse.
6–9s: A loud metallic roar echoes from somewhere in the fog ahead. The bull reacts instantly — it lowers its head, paws the ground, steam blasts from its vents, gears lock into place, and sparks spit from its chest cavity. Rahul pulls himself up and mounts the bull in one fast motion.
9–12s: The bull rears slightly, then slams down hard. Rahul leans forward, gripping tight. Through the smoke ahead, we briefly see threatening silhouettes moving toward them, just enough to imply incoming enemies.
12–15s — Payoff: The bull explodes forward into a full charge with Rahul riding it, smashing through smoke and embers. End on a powerful low-angle tracking shot as both disappear into the haze, charging straight toward the unseen threat.
Sound: deep metal groans, steam bursts, furnace rumble, distant enemy roar, hoof impact, sparks, low cinematic score.
Cinematography / Color Brief
Use the same signature look: desaturated steel blue, charcoal grey, mist white, weathered bronze, and restrained furnace orange accents. Soft overcast light, smoky atmosphere, wet surfaces, and strong depth. Cinematography should feel premium and mythic: low angles, slow dramatic push-ins, tactile detail, subtle shake, sharp realism, and heavy scale.
Use the uploaded mechanical bull image as the main creature reference and Rahul’s image as the human character reference. Create a 15-second ultra-realistic cinematic sequence set in The Harvester universe. The scene takes place in a foggy dystopian industrial street full of smoke, ash, overhead wires, dim structures, and distant furnace glow. The giant mechanical bull is massive, battle-worn, and intimidating — a living machine-beast with heavy steel plating, exposed pistons, pipes, furnace light glowing inside cracked armor, huge curved horns, and hot steam venting from its body.
0–3s — Hook: Start with a dramatic low-angle shot of the giant mechanical bull standing motionless in the street like a dead titan, steam drifting around it. Its orange core is dim. Rahul walks into frame, small beside it, cautious but familiar, like this is his companion.
3–6s: Rahul places one hand firmly against the bull’s metal faceplate or neck armor. Close on the contact. He says in a calm, controlled tone: “Wake up. We hunt.” The bull’s eye glows brighter. Internal furnace light begins pulsing.
6–9s: The bull violently powers on — steam blasts from vents, gears rotate, pistons lock, embers spit from its chest, and its massive head lifts. One hoof slams into the ground with weight. The whole frame shakes slightly.
9–12s: Rahul pulls himself up and mounts the giant bull. The bull turns its head toward something unseen ahead in the smoke — distant danger, possibly droids or enemies approaching. We feel the next hunt is beginning.
12–15s — Payoff: The bull charges forward with explosive force through smoke and sparks, Rahul riding it hard. End on a powerful forward rush into haze as the machine roars and the hunt begins.
Sound: deep metallic groans, steam bursts, furnace rumble, hoof impact, distant industrial ambience, low ominous score.
15 seconds, 16:9 landscape. Blend live-action footage of a small kitchen at dusk with hand-drawn luminous animation. The last sunset light lingers at the window. The lived-in kitchen contains an old wooden table, a half-washed mug, a lightly fogged glass bottle, and a hanging dish towel.
- Shoot as if someone is filming one-handed on a phone: subtle hand tremor, hesitant close-focus pulls, backlit exposure breathing, and slightly coarse noise in the shadows. It should feel like an astonishing event captured in a rush at home, not a carefully dressed commercial.
- Do not show giant eyes, split mouths, fangs, threatening behavior, lunges, sudden black frames, or jump scares. Use only room tone, cloth friction, a soft mug clink, faucet drips, the camera operator’s footsteps and quiet breathing, plus gentle electronic tones and tiny vocalizations from the drawn creatures.
Create a 15-second, 16:9 photoreal cinematic sci-fi mystery sequence with native stereo audio.
Use Image 1 as the strict anchor reference for the explorer’s identity, face, short dark hair, charcoal hooded coat, black tactical clothing, boots, gateway design, wet obsidian landscape, jagged rock formations, lighting, materials, and cold blue/crimson color palette. Use Images 2–4 as sequential visual keyframes and preserve complete character, costume, environment, scale, and screen-direction continuity.
[0–3 seconds] Begin with Image 2. Ultra-wide symmetrical establishing shot from behind the explorer. She walks slowly toward the colossal circular gateway, remaining very small against its immense scale. The camera performs a restrained forward dolly at ground level, following the crimson reflection across the wet surface. Her boots create small splashes. Mist drifts laterally around the distant rocks. The glowing ring pulses faintly, but its center remains completely black.
[3–6 seconds] Cut on her next footstep to a low rear three-quarter tracking shot. Move beside her at walking speed while keeping the gateway fixed ahead. Her coat responds naturally to the wind. The crimson illumination travels across the wet fabric and reflective ground. Do not change her walking direction or position relative to the gateway.
[6–9 seconds] Cut to Image 3. Tight three-quarter facial close-up. Slowly push toward her eyes as she stops walking and looks upward. Preserve her exact facial identity. Her expression shifts subtly from focused caution to disturbed recognition. Fine strands of hair move across her face. The gateway remains softly recognizable behind her. A dim crimson reflection appears in her eyes.
[9–12 seconds] Cut to a close shot of her gloved hand rising cautiously into frame. Track forward with the hand as she approaches the threshold. The air near the black center distorts slightly, pulling mist and loose droplets toward it. Keep the effect restrained and physically coherent, with no lightning, explosions, or fantasy energy.
[12–15 seconds] Transition into Image 4. Medium-wide side view near the gateway. She extends her hand toward the pitch-black center but stops just before contact. The crimson ring suddenly dims for half a second. All ambient wind and rain sound disappear. From inside the void, a quiet version of her own breathing answers one beat later. She freezes. End on a slow push toward the narrow space between her fingertips and the darkness, cutting to black before contact.
Visual style: premium live-action science-fiction film, realistic skin and fabric, cold blue ambient light, restrained crimson rim light, deep blacks, wet reflections, fine atmospheric mist, subtle film grain, controlled contrast, 24 FPS, natural motion blur, cinematic depth of field.
Audio: distant low-frequency gateway resonance, cold wind, light rain, boots splashing through shallow water, fabric movement, restrained breathing, and a deep sub-bass pulse that grows gradually. Remove all environmental sound during the final silence, leaving only the delayed breathing from inside the void.
No dialogue, subtitles, title cards, logos, watermarks, extra characters, vehicles, weapons, creatures, lightning, explosions, camera spins, random zooms, rapid montage, costume changes, facial changes, distorted hands, warped gateway geometry, daylight, or bright saturated colors."
Buddhist monastery courtyard at dawn, mist drifting between stone pillars. Wide shot, shallow depth of field: a row of Shaolin priests kneeling in prayer, hands pressed together, saffron and grey robes, heads bowed. Soft ambient temple bells. Background monastery architecture slightly defocused, foreground priest sharply in focus. Sudden thunderclap. A bolt of lightning crashes down center-frame — the Lightning God lands in a crouch, white kimono and white wide-brimmed hat, faint electricity crackling off the fabric. He rises slowly. Close-up: his eyes ignite, glowing white-blue lightning, no pupils, just arcing current. He explodes into motion. Fast tracking shot as he closes distance on the first priest, palm strike trailing a lightning arc — priest is zapped, muscles seizing, thrown backward in a shower of sparks. Quick cut: side angle, second priest lunges with a staff; the god sidesteps in a blur, lightning crackling along his arm, backhands the staff aside and zaps the priest's chest — priest crumples, smoke rising off his robes. Quick cut: low angle, third priest sweeps a leg; god leaps straight up, hovers a beat with lightning rippling off his kimono hem, then drops down zapping the priest's shoulder. Fast intercut: downed priests groaning, hands pressing into the ground, pushing themselves back up one by one, robes scorched but eyes determined — they re-engage together, converging on the god from three sides. Wide shot, all four in frame: priests strike in unison, god pivots between them in a continuous whirl, every block and counter sparking with lightning, his white hat never falling. Camera whip-pans following the fastest exchanges, strobing light flashes matching each hit. Final beat: god stands center, lightning arcing off him in all directions, breathing storm-light, priests circling back to their feet around him, ready to strike again — freeze on his glowing eyes, thunder rumbling. Camera: mix of fixed depth-of-field opening shot, fast tracki
Slow-motion handheld close-up, 16:9. Shaky organic handheld shot shoving in close on a researcher in a pressurized white hazmat suit, faceplate fogged and cracking, stumbling backward across a gleaming sterile lab floor as a glistening mutant creature — too many jointed limbs, translucent skin pulsing with visible organs, a maw that splits wrong-way-wide — lunges from an overturned containment tank, wet strands of tissue trailing through the air behind it. Around him the team scatters in chaos: a woman in a matching suit shoves past his shoulder dragging a fallen colleague by the arm, two men wrestle a heavy steel door against something pushing back from the other side, someone is dragged backward across a workstation beside him, knocking a spray of shattered glassware and spilled reagent vials into the air, more suited figures stumble and scramble through the background past racks of specimen jars cracking under sudden impact. In slow motion glass, fluid, and torn suit fabric explode across the whole frame, droplets and shards suspended everywhere, catching the cold light. Dynamic jostling handheld movement at chest height in the thick of the chaos, camera nearly clipped by a whipping limb. Sterile unreal palette — clinical white, cold surgical blue, sickly bio-luminescent green glow bleeding from the creature's flesh, harsh alarm-red strobing at the edges of frame. All faces anatomically correct behind fogged visors, stable, realistic, genuine terror, no warping. Heavy coarse analog 35mm film grain baked into every frame, thick and consistent, grain crawling over highlights and shadows, like a scanned celluloid film print, never clean, never digital-looking. Flat overhead cleanroom lighting cut through by pulsing red alarm strobes, dramatic slow-motion intensity, cinematic photorealistic, ultra-detailed.
A stunning action packed scene following a little robot running away from soldiers, drones and other things that are trying to get him. Chase cam, dystopian futuristic cyberpunk environment, cinematic lighting. The camera follows the robot from behind, chase cam style. Every now and then the robot looks behind him and the entities chasing it are shown.
Open ocean, storm-lit sky, two massive wooden galleons broadside to broadside, cannons blazing, sails torn and smoking.
LOCATION: towering waves, rain-slicked decks, splintering wood, the ships as looming wooden fortresses dwarfing the men fighting on them. Grey-green storm light, cannon smoke rolling across the water like fog.
ACTORS: two pirate crews — one crew in ragged dark coats and bandanas led by a scarred captain wielding a cutlass and flintlock; the other crew in stolen naval coats, more disciplined but outnumbered. Dozens of background fighters clashing across both decks.
MOVEMENT: heavy, physical combat — swinging on rigging ropes across the gap between ships, cutlass clashes with real weight and follow-through, men thrown by cannon blasts, boots slipping on wet planks.
INTERACTION: the two captains as the emotional throughline — circling each other through the chaos, their duel the spine of the sequence while the crews fight around them.
CINEMATOGRAPHY (Kubrick-style): open with a long, wide, almost painterly establishing shot of the two ships closing in through the storm — hold it, let the dread build before the first cannon fires. Use symmetry in the initial approach (ships mirrored on either side of frame), then shatter that order completely once battle erupts. Favor a few extended tracking shots through the melee (a single unbroken move weaving across the deck) rather than only quick cuts, so the audience feels physically present in the chaos, punctuated by hard cuts at moments of violence.
CUTS:
1. Wide establishing shot: the two galleons converging through rain and swell, lightning flashing behind torn sails, ominous and silent but for wind and creaking timber. Hold long.
2. Close-up: the pirate captain's face, rain streaming down a scarred cheek, eyes narrowing, hand tightening on his cutlass hilt.
3. Wide shot: cannons fire in unison from both ships — deafening flash and smoke, the hulls shuddering, wood splintering on impact, rigging snapping and crashing to the deck.
4. Grappling hooks fly across the gap, biting into the enemy ship's rail; ships lurch together with a groan of timber as the gap closes.
5. Long tracking shot: pirates swing across on ropes into the fray, landing mid-swing into combat — camera follows one pirate's full arc from rail to rail without cutting, weapons clashing all around as he lands and immediately engages.
6. Fast cuts through the melee: cutlass parries, a pistol shot at close range, a man thrown overboard by a cannon's recoil, barrels rolling loose across the tilting deck.
7. Medium shot: the two captains spot each other across the chaos, a beat of stillness in the middle of battle, then they cut a path toward one another through the fighting.
8. Close-up duel: blades clash in tight, brutal exchanges, rain and sweat, snarled dialogue, one captain slammed back against the mast.
9. Wide shot: a mast cracks and begins to fall, crew scattering, fire catching on torn sailcloth, chaos peaking as both crews scramble.
10. Final close combat: the rival captain disarmed, blade at his throat — beat of hesitation, thunder cracks, and the scene holds on the standoff rather than resolving cleanly, smoke and rain swirling around them both.
Camera: mostly handheld-feel tracking shots through the melee for immersion, hard cuts on cannon fire and key hits, a still symmetrical wide shot to open
Create a 15-second cinematic showdown between the most technologically advanced human and the most primordial warrior.
The technological fighter wears adaptive nano-armor, holographic interfaces, energy weapons, and glowing cybernetic implants.
The primordial fighter is massive and feral, covered in ritual markings, bone armor, and animal hides, wielding a brutal stone weapon.
Set the battle in a ruined landscape where a futuristic megacity merges with an ancient volcanic wilderness.
00:00 — The fighters face each other as futuristic machinery hums and distant primal drums begin.
00:02 — The technological fighter activates the nano-armor and says in a cold synthetic voice: “Evolution ends with me.”
00:04 — The primordial warrior roars and replies in a deep, savage voice: “You have forgotten what strength is.”
00:06 — They charge toward each other at full speed.
00:08 — Their weapons collide, releasing a massive shockwave of blue plasma, fire, sparks, debris, lightning, and shattered holographic fragments.
00:10 — The technological fighter launches drones and energy blades while the primordial warrior smashes the ground, creating volcanic cracks and a towering blast of stone and flame.
00:12 — Both fighters unleash their final attacks simultaneously as the camera circles them in dramatic slow motion.
00:14 — A blinding explosion consumes the battlefield.
00:15 — The smoke begins to clear, revealing only a mysterious silhouette without showing who won.
Use dynamic tracking shots, dramatic low angles, rapid orbiting camera movement, extreme close-ups, speed ramps, controlled handheld energy, and slow motion during key impacts.
Cinematic 4K, 16:9, ultra-realistic VFX, physically accurate destruction, volumetric smoke, plasma energy, fire, sparks, debris, lightning, synchronized impact sounds, futuristic weapon audio, primal roars, distinct English voices, and a cinematic orchestral score mixed with electronic pulses and tribal percussion.
integrated_multimodal_description: [Shot 1] Realistic handheld iPhone footage with slight shake and motion blur inside a dark, high-end futuristic movie theater. The frame starts off pointing at a very attractive woman in the seat next to us. She looks worried and excited. The camera swipes quickly to face toward a massive curved screen an active volcano with red hot lava rolling toward the viewers. Audience members sit in rows facing the screen. For the first three seconds, the scene mimics a standard film viewing as the on-screen lava grows larger as it approaches. At 3.00 seconds, the lava crashes out from the screen's surface. A massive surge of realistic lava gushes out from the screen, flooding the aisles and cascading over the seats and audience members. People flinch, scream, and duck as lava splashes over their laps and heads. The handheld camera shakes violently, tilting slightly upward as lava droplets hit the lens, creating a messy, immersive perspective of chaos and excitement. College guy off camera says <d>whoa, that is so hot!</d>
overall_soundscape: Low theater room tone initially, followed by the roaring crash of water breaking the screen, audience screams, rushing liquid flow through aisles, wet splashing sounds, and a crescendo of excited screams, gasps, and laughter from the audience.
non_diegetic_music: N/A
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] A 15-second, 16:9 cinematic realistic suspense short set entirely inside the same rainy neon stair alley from <Picture 1>. Preserve the exact same female lead throughout: same face, hairstyle, soaked wardrobe, body proportions, skin texture, and the same staircase geography with wet steps, narrow alley, railings, humid air, and neon mood. No scene change, no extra people, no black ending. The story is: a drenched woman slowly walks down the stairs, notices an iPhone still recording on one step, bends to pick it up, realizes the screen shows her own back filmed from behind, instinctively steps back half a step into the railing and whips her shoulder and head around, but the real staircase is empty. End on the suspended moment where she is half-turned, half-looking down, with the screen still lit. She stays in motion throughout: descending, stopping, noticing the phone, bending to pick it up, standing with the screen, stepping back, leaning to the railing, turning shoulder and head, then looking back to the phone. The phone must stay physically consistent in size and readability. [Shot 2] At 00:00-00:02.8, a low dynamic near shot hugs her legs, waist, and the wet railing as the camera slowly pushes in and follows her down about one and a half steps. The emphasis is on lower-body weight transfer, wet skin reflections, and action-based sensual tension. Her right hand keeps a subtle stabilizing relationship with the railing. She is soaked, moving carefully but not weakly. Her first emotional phase is calm, restrained, and oppressive self-protection: eyelids half-lowered, gaze angled beyond camera toward the lower stairs, brows held flat with only the outer ends slightly lowered, lips naturally parted, breath low and steady, nostrils moving lightly, no smile. Pink-violet neon washes the front-upper planes of the chest, collarbone, abdomen, and front thighs, while cyan-blue edge light wraps the waistline, outer arms, and leg contour. This is the first sensual close-up: legs, waist, wet skin, deep wet fabric contours, and real descending balance. [Shot 3] At 00:02.8-00:05.0, cut to a medium-close slightly high angle that lands on the step at her feet while keeping one stopped boot and the railing in the foreground. A lit iPhone lies near the edge of shallow step-water. The red recording dot must be immediately readable. She stops on the stair, not frozen but caught mid-motion. Her gaze narrows sharply toward the phone, pupils snap into focus, the brow center contracts into only the thinnest line, she takes one short nasal breath, her lips close lightly from their previously open state, and the jaw gathers in. This is the first layer of wrongness, not yet fear. She murmurs quietly, <d>[English] Whose phone is this...?</d> The line is tentative and low, with the ending gently falling away. Phone screen light adds a third small light source, lifting the forehead edge, nose bridge, lash line, and cupid’s bow with cool white. [Shot 4] At 00:05.0-00:07.8, a tight near shot from her right-front follows her bend as she picks up the phone. Stay close to the hand, collarbone, side waist, wet hair falling forward, and the exact moment the device leaves the stair. She remains connected to the railing with the right side of her body and hand relationship, even while reaching. Her eyes stay locked on the phone the whole time. Lashes cast a slight shadow downward. The lips tighten more, the throat moves with one very small swallow, breathing becomes noticeably shallower, and the face shifts into focused verification rather than panic. This is the second sensual close-up: hand, collarbone, side waist, wet hair, and the phone entering the center of the narrative. Rain hits the glass and forms tiny round splashes and sliding beads. When she pinches the phone edge and lifts it, droplets drag aside and one or two thin water threads stretch briefly and break. [Shot 5] At 00:07.8-00:10.5, a near shot layers the phone screen and half her face. First make the screen content legible, then carry focus into her face without losing the screen read. The phone display shows only one clear thing: her own back descending the staircase, filmed from a steady hidden angle one step higher behind her. No second face, no ghost, no supernatural clutter. She sees it and recognizes herself. Her fourth emotional phase is clear alert recognition: her eyes flick once across the screen and then hold, the lower lids lift slightly, the pupils widen just a little, the brow center tightens more clearly while still restrained, nostrils open and settle, any remaining softness in the mouth disappears, and the lower lip stalls for a beat as if a sentence is trapped in the throat. She whispers, <d>[English] Wait... that’s me.</d> The first half carries a tiny delay as recognition catches in her breath. The phone’s cold light now fills the lower half of her face and under-eye area, making the micro-expression readable without overpowering the neon mood. [Shot 6] At 00:10.5-00:12.8, an extreme close-up pushes from shoulder-neck, side face, lashes, and lip line into the eye. This is the third sensual close-up, centered on the dangerous moment before she turns. She keeps the phone close to her chest line, glances once more at the screen, and then prepares to look back. Her fifth emotional phase is being pressed by the implication that the filming angle was behind her: lashes tremble once, breathing tightens, the lip line draws in, cheek muscles firm slightly, and she says in a lower, faster, more pressured whisper, <d>[English] Who the hell is filming me?</d> It is not shouted, but forced low confirmation. One side of her face drops deeper into shadow while the other is caught by soft pink-violet neon on lashes, nose tip, lip peak, and jaw edge. [Shot 7] At 00:12.8-00:15.0, a medium-close shot with a slight retreat. Let the turning motion carry the cut. She shifts back by half a step, the wet sole dragging a very small water trace, shoulder and collarbone leading the head turn rather than the head teleporting first. Her back and right side find the railing. She turns sharply toward the upper stairs, but the real staircase is empty. She then drops her gaze back to the still-lit phone at chest level. Her final emotional phase is cold controlled aftershock: the eyes cut first upward, then back down, the forehead tightens lightly, the jaw stays tight, the mouth opens by half a breath and then slowly closes again, fear controlled but not gone. The screen remains lit and still recording. The staircase behind her stays empty, wet, neon-lit, and physically real. End with her half-turned, half-looking down at the glowing iPhone, rain still falling, neon still flickering, and suspense held inside the frame, without cutting to black.
overall_soundscape: Maintain a continuous rainy neon stairwell ambience: mid-strength rain, water ticking on railing and steps, shallow drainage flow, distant electric hum, soft neon buzz, and humid night reverb. Emphasize wet footfalls on the stairs, the subtle grip and slide of her hand on the railing, clothing friction, low controlled breath, and fine splashes from shallow step-water. Then bring forward rain striking the phone glass, tiny circular water impacts, the slight stop in her step, her low tentative line <d>[English] Whose phone is this...?</d>, fingers contacting the wet phone, water dragging across the screen, a faint lift-off suction from the wet stair, her shallow breath, fabric tension as she bends, one small swallow, and the surrounding rain and neon hum dimming slightly as she reads the screen. Finish with the tightening breath before the turn, the low pressured line <d>[English] Who the hell is filming me?</d>, one light metallic touch from the railing, the small backward step drag on wet stair, empty stair ambience, continuing rain, neon buzz, and the phone still recording in her hand. No scream, no extra voices, no subtitles.
non_diegetic_music: Keep score absent or nearly absent. If any non-diegetic layer is used, make it only a very thin low suspense drone under the rain and neon hum, rising slightly after she sees the screen and never overpowering the physical environment or dialogue.
HAILUO AI H3 — 15 SECONDS — 16:9
Animate the original image. Preserve the exact colossal Kraken, ancient Greek coastline, ruins, statues, wooden ship, mountains, storm clouds and overall composition.
0–5 SECONDS:
The colossal Kraken rises slowly and heavily from the turbulent sea. Its enormous tentacles flex and curl with realistic muscular weight. Seawater streams from its rough skin and suction cups while waves violently break around its body. The wooden ship rocks naturally on the swells but remains intact.
5–10 SECONDS:
The Kraken slowly turns its massive head toward the ship, its huge golden eye tracking it. The giant foreground tentacle lifts and curls higher while distant tentacles move independently through the water. Lightning flashes across the storm clouds. Wind pushes sea mist and spray across the scene.
10–15 SECONDS:
Several enormous tentacles rise higher as the Kraken releases a powerful deep roar. A huge ocean swell rolls outward from its body, sending white foam and spray across the rocks. The ship climbs the swell safely. End with the Kraken towering majestically above the raging sea beneath the storm.
CAMERA:
One continuous cinematic shot with a very slow forward push. Keep the original viewpoint and composition. No cuts, camera switching, sudden zooms or angle changes.
PHYSICS:
Realistic heavy tentacle movement, believable water displacement, cascading seawater, turbulent waves, foam, mist, spray, wind and ship movement. Kraken anatomy, size and appearance remain consistent throughout.
SOUND:
Deep Kraken roar, crashing ocean waves, rushing water, strong coastal wind, distant thunder and wooden ship creaking. No dialogue, narration or music.
STYLE:
Photorealistic 8K, ancient Greek mythological fantasy, monumental scale, dramatic cinematic lighting, realistic storm and ocean physics.
NEGATIVE:
No Cthulhu, no Lovecraft imagery, no humanoid tentacle face, no morphing, no extra creatures, no modern objects, no gore, no injuries, no ship destruction, no camera cuts, no composition changes.
“Don’t Worry About Me” — Farewell to a Dying Robot
15s16:9
integrated_multimodal_description:
15-second, 16:9, realistic cinematic short generated from <Picture 1> as the only first frame. Lock the whole film inside the same snowy alley only: the same rusted spherical robot in the left foreground, the same woman, hanging wires, neon haze, snow, and ruined alley depth. No extra people, no extra robots, no new space. Preserve the exact same adult blonde woman: same face, wet hair, open black short jacket, chest garment, harness straps, dual mechanical arms, armored legs, and identity. Preserve the same rusted spherical robot with one amber eye and two short antennas.
The story is farewell. She treats the robot like a lover, tells it she will be okay, presses its existing reply button, receives one last touch from its remaining power, then holds it and finally breaks into tears. The robot stays in the left foreground for the entire clip. She begins from the central standing position in <Picture 1>, with her right mechanical hand already resting on its head. She steps half a step toward screen right along the shell curve, then drops to one knee on the robot’s right side and never changes position again. Her left hand presses the circular mechanism low on the front shell. Her right hand moves from stroking the head into the final embrace. She actively brings her face close to the antenna so only a small antenna rotation is needed to touch her cheek. The camera stays on the same side of the woman-robot line as in <Picture 1>.
Color stays low-saturation and cold: coal black, steel blue, snow-fog blue, with amber from the eye as the only vivid warm light, and skin kept naturally warm. Medium-high contrast, textured darks, soft amber falloff, fine film grain. The original red-blue neon remains blurred and reduced in saturation. When the eye brightens, the warm light only sweeps across her face, knuckles, the shell, and nearby snow. Once it dies, the cold blue environment returns.
[00:00-00:02.6]
50mm three-quarter side medium close, moving about 40 cm sideways with her. Continue directly from <Picture 1>; she is already moving. Staying close to the shell, she steps half a step right while her right palm slowly brushes away snow and her thumb wipes the rim of the amber eye. Ice grains loosen and roll down the shell into the snow. The shot ends holding her eyes, shoulder-chest line, mechanical hand, and the robot together. Leaning in and stopping creates one soft upper-torso inertial sway, then it settles back. Jacket edges and harness straps fall into place half a beat later. She begins with held breath, then when she sees the eye still carrying a faint ember she gives it one tiny reassuring smile. Cut at the instant her thumb stops on the eye rim.
[00:02.6-00:05.5]
40mm side-front waist-up shot with a slow push of about 20 cm. She lowers to one knee in thick snow on the robot’s screen-right side; the knee compresses snow and pushes powder outward. After she drops, the torso stops first, then the chest and clothing settle downward and rebound once lightly; when she inhales, the upper chest lifts and a strap trembles faintly. She keeps her eyes on the amber eye and says in a low gentle English voice: <d>[English] I'll be okay. You can rest.</d> “okay” carries a forced trace of a smile; “rest” lands softer. After speaking, she swallows once. Her left hand finds the circular reply button low on the front shell. Cut to the hand.
[00:05.5-00:06.7]
Short fixed detail close-up. Her left thumb slowly presses the circular button until the mechanical contact clicks. Her right hand still rests lightly on the top of the robot. The amber eye contracts inward and dims temporarily. Her thumb does not leave immediately. Background snow and blurred neon continue moving. A faint antenna servo startup sound carries into the next shot.
[00:06.7-00:09.0]
Slow same-side arc move of about 15 degrees, shifting from the ice-coated antenna tip toward her eyes. Depth of field glides from the antenna to her pupils. She actively brings her cheek close. One short antenna rotates only about 10 degrees from the root. Thin ice around it cracks realistically, and tiny pieces fall onto the back of her right hand. The antenna tip touches her cheek with a very light metal contact. The amber eye brightens briefly, and warm light reveals water just forming in her eyes. She first gives a genuine small smile, then the smile stops in place, her lashes tremble, and she refuses to blink. The second antenna and the shell keep their original shape.
[00:09.0-00:11.6]
Fixed same-side two-subject close shot. The antenna that touched her loses strength and drops back, lightly tapping the shell. The amber eye slowly fades out, and the warm light retreats from her face. She keeps the comforting smile for half a beat after the light is gone, then her lower lip trembles and one breath fails to come in fully. From the kneeling pose she leans forward and wraps both arms around the spherical shell as far as she can. Her mechanical palms and the rusted shell touch with a restrained muted metal sound. Her shoulder contacts the shell first, the body stops abruptly, and the upper torso and jacket give one light sway from the forward stop, then settle into irregular fine trembling from interrupted breathing. Hair slips across her face. The harness tightens with the shoulders. She presses her forehead against the place she had just cleaned. Cut tighter to her face.
[00:11.6-00:15.0]
Fixed facial close-up. The robot’s cold curved surface occupies one side of frame. The camera does not pull back and does not cut away. Her face is pressed to the shell. At first she closes her eyes and tries to hold it in; the throat jumps once. One tear slides across her cheek, and the first trembling breath escapes between her lips. In the final two seconds she hugs tighter, her shoulder trembling at the edge of frame, and finally lets out a suppressed cry she can no longer contain. End on her crying face, without black.
Physical continuity must remain strict. Snow drifts diagonally toward lower right the whole time. Wet hair and jacket edges respond to the same light wind. Hanging wires sway gently. Background neon and machine haze keep subtle motion. Ice fragments fall under gravity, snow powder moves from touch and wind, and face, costume, hand roles, shell cracks, antenna length, and all spatial directions remain consistent.
overall_soundscape:
A constant bed of cold alley wind, fine snow movement, distant neon electrical buzz, and faint ambient machine hum. Very close tactile Foley leads the scene: hand brushing loose snow from metal, ice grains ticking and sliding down the shell, knee compressing thick snow with a dull push, breath held then released softly, the circular button giving a clean mechanical click, a tiny servo wake-up whir, thin ice cracking around the antenna hinge, the antenna tip touching skin with a delicate metal tap, the antenna falling back and striking the shell lightly, then muted mechanical-hand-to-shell contact as she embraces it. After that, breath becomes the main foreground sound: broken inhales, one swallowed sob, then restrained crying that finally escapes in the last seconds. Dialogue remains intimate and close: <d>[English] I'll be okay. You can rest.</d> No new character sounds, no offscreen interruption.
non_diegetic_music:
Use almost no score. Keep only a faint cold low bed under the wind for the opening, nearly imperceptible. At the moment the antenna turns and touches her cheek, add one restrained low warm string bloom, brief and intimate rather than dramatic. As the eye fades, withdraw the music to near silence so the dying servo, breath, and crying carry the emotional weight. No swell, no sentimental climax, no hard musical punctuation at the end.
Use the reference image as the exact visual and character foundation. Create one continuous 15-second cinematic shot on a deserted underground metro platform at night. Preserve the woman’s exact face, bleached shaggy wolf cut, lemon-yellow track jacket, proportions, styling, and overall appearance throughout the entire video.
0–3 seconds — Establishing movement
The woman stands motionless on the platform, facing slightly toward the camera with a calm, distant expression. The camera begins a very slow handheld push-in. Her hair moves gently from the distant airflow of an approaching train. Fluorescent station lights create soft reflections on the wet platform.
3–6 seconds — Train approaches
A metro train becomes visible in the deep background and rapidly approaches behind her. The camera continues its subtle push-in while drifting slightly sideways. The approaching train headlights create a gradual exposure change across the scene. Her expression remains composed and almost completely still.
6–10 seconds — Train rushes past
The train suddenly races directly behind her. Powerful displaced air dramatically blows her bleached wolf cut backward and makes the lemon track jacket ripple naturally. Keep her face sharp and recognizable while the train develops realistic horizontal motion blur. Passing carriage lights streak across the background and briefly illuminate her face.
10–13 seconds — Peak cinematic moment
The strongest airflow lifts individual strands of her hair across the frame. She subtly turns her eyes toward the passing train but does not turn her head significantly. The camera makes a very slight lateral movement, maintaining her as the central visual anchor. Reflections and light streaks move rapidly across the wet platform.
13–15 seconds — Aftermath
The train begins disappearing into the distance. The airflow gradually settles. Her hair falls naturally back around her face. The camera completes the slow push-in and settles on a close cinematic portrait. She looks past the camera with the same quiet, detached expression as the final train lights fade into the background.
Visual style throughout:
Photorealistic cinematic 35mm film, Kodak Portra color rendition, authentic analog grain, visible natural skin pores and texture, subtle halation around fluorescent lights, slightly imperfect exposure, muted analog colors, realistic motion blur, shallow depth of field, tactile film texture, documentary fashion editorial aesthetic, subtle handheld camera movement, realistic physics, natural hair and fabric motion.
Continuity constraints:
One continuous shot, no cuts, no scene changes, no changes to wardrobe, no hairstyle transformation, no facial morphing, no identity changes, no extra people, no beauty-filtered skin, no plastic texture, no exaggerated acting, no surreal effects, no CGI-looking train or environment. Preserve the exact visual identity and composition of the reference image.
Format: 15 seconds, 16:9 widescreen, cinematic composition, realistic temporal motion, premium analog fashion-film aesthetic.
integrated_multimodal_description:
15 seconds, 16:9, live-action cinematic realism. Use <Picture 1> as the only reference for the woman, outfit, location, lighting, and first frame. The opening frame must precisely inherit her leaning pose against the pink weathered wall, with the gray shutter on her left, the old poster on her right, the street in front, and the wall lamp, plants, hair, gold earrings, red polka-dot dress, neckline, waist structure, and facial identity all preserved. Same place, same moment, one continuous performance. Soft retro street-fashion film color: dusty pink wall, stable deep wine-red dress, warm natural skin, restrained gray-green background, medium contrast, soft highlight roll-off, subtle fine grain, real skin texture with slight moisture sheen. Keep the original daylight direction, around 5200K white balance, soft shadows, and continuous exposure. No neon shift, sunset change, rain, extra people, mirrored geography, teleporting, or filter changes.
She activates immediately from the exact leaning pose. Her path is fixed: P0 at the wall -> short advance to P1 -> diagonal drift to P2 -> slow walk along the wall to P3 -> shutter tap and turn -> final move toward P4. She never leaves the same street side, and the camera never crosses the wall axis. The emotional line is playful control turning into mutual recognition: she tests whether the camera can keep up, confirms it, then rewards it with a final backward smile before leaving.
[00:00-00:03.0]
35mm ground-level tracking rises into a side-follow. Starting from the exact leaning pose in <Picture 1>, she releases her left palm from the wall, pushes shoulder and back away, and advances from P0 to P1 in two short landing steps, the second slightly quicker than the first. The camera retreats a short distance straight backward, keeping a medium framing from head to mid-thigh and bringing her from frame-right toward center. Step impact travels foot -> knee -> hip -> torso; dress waist folds redistribute as she straightens; hair leaves the shoulder a beat later. The pink wall stays clearly behind her. She catches the camera first, then lifts her chin slightly. A restrained hint of a smile appears. During the second landing she absorbs the motion with a small knee bend; the upper body stops first and the chest shows one brief natural rise-and-settle under dress support, while fabric edges and hair tips settle a fraction later. She lowers her chin slightly, checks whether the camera is still backing away, and from 2.7s to 3.4s says quietly: <d>[English] Keep up.</d> The stress lands on “up,” short and clear, lightly challenging.
[00:03.0-00:07.5]
Without resetting pose, she turns diagonally toward P2 and moves slowly along the wall toward screen-left into P3, settling into a three-quarter left-facing side walk. The camera tracks parallel from the street side, framing head, upper torso, right hand, and a slice of wall, with open space ahead on the left. Her right hand rises near shoulder height and lightly skims the wall. One focus idea only: briefly show the fingertip contact while her face stays readable, then over about half a second transfer focus to her eyes as she looks back toward the camera; after that, keep the face sharp. Eyes move first, then the head follows. She exhales slowly; breath gently lifts and lowers chest, shoulders, and neck while she keeps walking. The corner of her mouth lifts and restrains again, as if confirming that the camera really is following. When her fingertips cross a brittle paint edge, a tiny amount of dust flakes off and drops close to the wall; no large peeling or damage. Before 7.5s she reaches P3 and her right hand transitions from the pink wall onto the edge of the gray shutter.
[00:07.5-00:09.0]
At P3 she gives the shutter a light tap with her right hand, producing one short metallic tick, then releases immediately. The shutter never opens. She completes a real stop-and-support under the feet, then the hips, shoulders, and head rotate toward the camera in order. The camera performs one brief left whip of about 0.2-0.3 seconds following her turn, with directional motion blur, then settles instantly into a medium head-to-mid-thigh framing from the street side. No axis jump, no background replacement. As the frame stabilizes, her curls and skirt are still returning from the turn; earrings sway lightly then decay. The chest follows the torso turn with a short constrained lateral inertia under the dress and settles naturally, never bouncing independently.
[00:09.0-00:12.0]
From the settled medium shot at P3, the camera slowly pushes in toward a face-and-upper-body close shot while keeping the shoulder line and dress waist visible. It does not retreat anymore. She notices that the camera is finally coming toward her. She presses her lips together slightly, the smile starts in the outer corners of the eyes, then the mouth releases and she lets out one short natural laugh. Her shoulders drop subtly with the laugh; upper torso and chest move only with the connected exhale. Any remaining turn inertia is already gone. While laughing, she shifts another half-step along the wall toward screen-left, keeping eye contact instead of posing in place. From 10.6s to 11.6s she says softly: <d>[English] That's better.</d> “better” carries the smile, looser than the first line. After the line she takes a small inhale, the smile stays in her eyes, and her right hand begins to rise.
[00:12.0-00:15.0]
Her right palm briefly sweeps across the right edge of the lens area as a partial foreground wipe without touching the lens and without blacking out the frame. As the hand drops naturally with her turn, she continues from P3 toward P4 along the shutter and wall, leaving in two steps that start fast and then return to a natural pace. The camera pans left to send her out, always remaining on the street side. Around 14.0s, while still walking, she turns her head slightly back and gives the camera one last look with the real smile still present. The camera catches that glance and gradually settles; she keeps moving toward the left edge. End on her back-side profile and part of the old wall still visible, with a living-frame finish rather than a distant cut, freeze, blackout, or location change.
Physical continuity is strict: every inertia must have a source, path, and end state. Step impact moves from foot to knee to hip to torso; turning is driven by planted support under the feet; hair, earrings, skirt hem, and fabric react with slight delay and then decay. The dress retains seam definition, polka-dot pattern, and believable cloth weight. Fitted areas stay constrained by body and seams; only looser skirt edges move with walking, turning, and the light breeze. Chest motion stays synchronized to walking, breathing, and rotation, with stable anatomy and no rubbery deformation or repeated bounce. Contacts happen only at real touch points: feet on ground, hand on wall, hand on shutter. The wall remains intact. The shutter never swaps sides. The poster is ordinary background only and never animates. A light intermittent breeze flows along the wall from the left street opening toward the right, stirring a few loose hairs, soft skirt edges, plant leaves, and one tiny lifted paper corner on the poster, which flutters and settles back.
overall_soundscape:
Continuous low-intensity side-street ambience runs through the full 15 seconds: distant urban air, restrained alley noise, and a light intermittent breeze moving along the wall. At 0.0-3.0s, two distinct footfalls land with slightly different weight as fabric rubs softly and hair shifts. At the landing settle, keep a brief close-range body rustle. From 2.7-3.4s the woman says once, <d>[English] Keep up.</d> in a natural adult female mid-low register, clear conversational English with a faint dry texture, fully synchronized to accurate lip movement. At 3.0-7.5s, keep subtle fingertip friction against painted wall, a quiet exhale, faint cloth motion, and very small paint dust release with no exaggerated debris sound. At 7.5-9.0s, include one short light metallic tap on the shutter with a tiny fast-decaying resonance, plus turning fabric and earring movement. At 9.0-12.0s, her breathing and one short genuine laugh sit close to the camera; from 10.6-11.6s she says once, <d>[English] That's better.</d> more relaxed and smiling than the first line. At 12.0-15.0s, keep the passing hand as a soft foreground whoosh, two departing steps, continued low street tone, and the last glance landing in a quieter tail. Dialogue and real action sounds must always stay clear. No added crowd voices, no poster voice, no exaggerated impacts, no moans, no melodramatic whooshes.
non_diegetic_music:
Use a very light, clean rhythmic bed only. A restrained low bass pulse and sparse dry percussion accents support the first quick approach and the shutter tap as timing marks. Reduce percussion during the slow side-walk and keep the music thinned out under the laugh and the second line. The score should stay minimal, modern, and controlled, never sentimental, never wall-to-wall, and always below dialogue and physical Foley.
“Look at me.” — Hangar Skylight Fall Rescue (First-Person I2V)
15s16:9
MiniMax-H3 prompt👇
integrated_multimodal_description:
15 seconds, 16:9, realistic cinematic image-to-video. Use <Picture 1> as the only first frame and the only visual reference for the adult woman and the hangar. Preserve her face, hairstyle, goggles, earmuffs, dark olive open-collar work jacket, shoulder strap, sweat-sheened skin, dual mechanical arms, and the same dark steel-beam hangar with warm practical light on the left, long skylight at upper right, workbench, and distant background figures. The camera is first-person POV of a rescued person standing in front of her; only this person’s left forearm may appear briefly, and no second clear face is ever shown.
Lock spatial continuity: she advances from center frame toward the camera. Upper-right frame and behind her right side hold the skylight and brighter corridor with cold daylight. Left frame remains the darker ceiling zone and safety passage. Danger falls from upper-right into the right corridor. She and the camera always retreat together toward screen-left, never swapping sides. Her left hand first pulls one earmuff aside to listen; her right hand grabs the rescued person’s left forearm and releases only at the end. Any camera turn stays on the same side of the action axis.
Keep the palette and light stable: charred steel black-green, dark olive clothing, tungsten amber practicals, cool skylight white, and natural warm skin. Low saturation, deep olive and blue-gray shadows against amber highlights, roughly 3200K practicals against 5600K skylight daylight. High contrast with retained steel detail and soft highlight roll-off. Glass breakage creates only a brief cold-white flicker; time of day and overall color temperature never jump.
[0.0-2.0s]
Fast POV retreat. Continue directly from the frontal close view of <Picture 1>. From the first frame she takes a large step toward the camera, pulls one earmuff aside with her left hand to isolate a metallic tension sound overhead, and the POV retreats quickly by about one step. Two forceful footfalls drive visible vertical load through her upper body. The open collar and shoulder strap tremble with the same rhythm; sweat beads and loose hair catch warm side backlight. Close framing always keeps face and chest together. Her eyes first scan the person in front of her, then jump past the camera toward her own upper-right rear; her brow tightens slightly and her lips stop the breath she was about to release.
[2.0-3.5s]
Sudden slow-down, low-angle tilt up. She is still stepping forward slowly, never freezing. The camera tilts upward from the moving collar and shoulder strap to her eyes. In the curved reflection of the goggles, the bright skylight line in the upper-right trembles, and a speck of dust lands on her shoulder. Her eyes move first, then her head follows with a small turn. She blinks once quickly, bites down lightly in the back of the jaw, and returns attention to the rescued person. Do not reveal the full crack yet.
[3.5-8.0s]
Violent acceleration, lateral side-follow with one rebound deceleration. She leans toward the person and says in a low, short command close to one breath, <d>[English] Look at me.</d> The line is a command, not comfort. While speaking, her right hand reaches to the edge of frame and grabs the person’s left forearm. She lowers her center of gravity, drives off with her right foot, and pulls the person and the POV diagonally toward screen-left, out of the bright corridor, across about two steps. The camera is dragged by this force, sliding fast sideways and slightly downward, then settling under the darker left-side ceiling with one brief inertial rebound. The camera passes close to her upper body: the shoulder strap tightens, the open collar is tugged by wind and hard turn, and the chest makes a pronounced lateral swing caused by sideways acceleration and torso rotation. After the abrupt stop, it shows a smaller quickly decaying rebound consistent with real soft-tissue inertia and breathing. Loose hair whips opposite the movement and falls back across the shoulder, and the earmuff swings lightly. She checks first whether the person’s footing follows, then looks at the person’s eyes, keeping the mouth tight.
[8.0-11.0s]
Impact reveal, whip-pan. They have already stopped in the safe left-side zone. From beside her left shoulder, the camera whips toward the right-rear, but the endpoint still keeps part of her left shoulder silhouette in frame. At the skylight in the upper-right, one metal fastener snaps first, the frame bends, and a single pane loosens from one corner, tilts, strikes a beam, and shatters. Large shards fall first, then smaller fragments follow gravity into the bright corridor on the right, hitting, bouncing, and sliding outward. A little fine debris scatters toward the camera’s previous path and slows to a stop near the left-side ceiling edge. Cold white daylight passes through the fragments, and dust is thrown up by the impact, briefly veiling the frame before thinning. The distant background figures only turn, duck, or step back within their own positions. Do not turn this into a full hangar collapse.
[11.0-15.0s]
Stillness, fixed close shot. Use the impact dust as the transition back to the same safe left-side position. Hold a fixed half-body close shot. Her right hand still supports the person’s forearm and only lets go after confirming the person is steady. After the violent movement, her chest rises and falls visibly with urgent breathing. The open collar edge and shoulder strap tremble first, then settle gradually with one longer exhale. The composition contains both upper body and face, and attention rises with her movement: the jaw softens from tension, her lips part slightly, and she reestablishes eye contact with the person; one corner of the mouth loosens for only a brief instant. Then her eyes lift toward the upper-right skylight before the head follows, checking the danger again. End with both her and the camera still in the safe left-side zone, debris settled, and background figures continuing small evasive movement without freezing.
Keep continuity exact throughout: same identity, same outfit openness, same goggles, earmuff, and shoulder-strap positions, same lighting direction, and the same factory depth. The camera must feel physically tugged by her grip. Hair, clothing, strap, skin, and chest motion must all follow step, torso rotation, hard stop, and breathing with proper inertia and decay. The glass falls only because of the failed upper-right skylight. All fragments follow gravity, collision, and occlusion. Face, fingers, ribcage, and cloth proportions remain stable. No extra foreground character enters.
overall_soundscape:
A continuous low industrial hangar ambience runs through the full 15 seconds: heavy room tone, faint metal resonance, distant footsteps, sparse background worker movement, and scattered machine hum. At the start, one sharp thin metallic tension ping is heard overhead; when she pulls one earmuff aside, the higher-frequency abnormal sound becomes clearer. During 0.0-2.0s, emphasize two heavy retreating footfalls, cloth and leather friction, close breathing, and light strap movement. From 2.0-3.5s, keep the tension thin and focused, with one tiny dust hit on fabric and the room tone narrowing as she listens. At 3.5-8.0s, she says once, <d>[English] Look at me.</d> in a low clear voice fully synchronized with the mouth. Add two urgent lateral steps, a light buckle tap from the shoulder strap, close breath, the grip on the forearm, and the camera-body pull. At 8.0-11.0s, the sound chain is precise: metal fastener break -> glass striking beam and shattering -> dense ground impacts and fragment sliding. After the impact, a brief ear-ringing tone compresses the sound field. In the last section, let that fade into her breathing as it changes from sharp to slower, with sparse distant reactions from the background figures. No extra dialogue, no voice-over, no subtitles.
non_diegetic_music:
Use a restrained low-frequency suspense pulse under the opening approach. Thin it out as she listens upward, then tighten it briefly during the grab-and-pull section. The glass-failure reveal should be driven mainly by physical sound, with only a short dark accent under the snap and fall. After the impact, drop the score back almost completely, leaving only a faint residual tension tone beneath her breathing and the far hangar ambience. Keep the music minimal and secondary to footsteps, breath, strap movement, metal failure, and falling glass.
Selfie Video: Girl Turns into a Demon (Before/After References)
15s16:9
Prompt:
subject_definitions:
<Subject 1> is the woman in <Picture 1>, with shoulder-length wavy brown hair with copper-toned ends, green eyes, pale skin, strong dark brows, and an oversized white T-shirt slipping off one shoulder.
<Subject 2> is the demon form of the same woman in <Picture 2>, with long tangled black hair, solid glassy milky-white eyes with no visible iris or pupil, grey decayed skin with dark veins and raw red wounds on the forehead, cheeks and neck, blackened rotten teeth, and a black leather harness top with straps over the shoulders.
summary:
[reference generation] The target video is a single 15-second handheld selfie video in which <Subject 1> sits on her bed and greets the camera, then her skin dissolves across her whole face while she speaks her second line, transforming her in place into <Subject 2>, while the bedroom behind her dissolves into a moonlit, misty graveyard. She finishes the line and grins with blackened teeth and blank white eyes.
retention_analysis:
<Subject 1> (appears in the first half of [Shot 1]): fully_preserved - face, shoulder-length brown hair with copper ends, green eyes, pale skin and the oversized white off-shoulder T-shirt are retained.
<Subject 2> (appears in the second half of [Shot 1]): fully_preserved - tangled black hair, solid glassy milky-white eyes with no iris or pupil, grey decayed skin, red wounds and black leather harness straps are retained, with blackened rotten teeth added, replacing the appearance of <Subject 1> on the same body in the same position.
detailed_description:
The target video is a handheld selfie vlog shot with cinematic phone-camera quality: shallow depth of field with the background softly out of focus, rich contrast, deep shadows, natural handheld micro-shake. It is one continuous shot with no cuts.
[Shot 1] A handheld selfie close-up at arm's length, framed from the chest up, with slight natural camera shake throughout. <Subject 1> (S1), the woman with shoulder-length brown hair with copper ends, green eyes and an oversized white T-shirt off one shoulder, sits cross-legged on her bed holding the phone in her outstretched right hand, which stays out of frame. She stays seated in that exact position in the centre of the frame for the whole shot. Behind her, softly out of focus, is a bedroom: a rumpled white duvet, pillows against a headboard, a window on the left letting warm golden morning light fall across her face, and a small lamp glowing on the right. She looks straight into the lens with a sleepy, friendly smile. <Subject 1> (S1) says in a clear, warm, casual young female voice with a British accent, showing clean white teeth: <d>[English] Morning folks. Happy Sunday.</d> She closes her mouth, glances away for a beat as if thinking, then looks back into the lens with a knowing smirk. <Subject 1> (S1) begins to say in the same voice: <d>[English] Or should I say, Happy Spooktober. Have a spooktastic day.</d> The transformation starts on the first word of this line and runs through the whole line as she keeps speaking. Her skin dissolves across her entire face and body in one continuous wave that travels from the top of her forehead downward. The smooth skin flakes and peels away in fine ash-like particles that drift upward, first from her whole forehead and brow, then both eyelids and the bridge and tip of her nose. As the wave passes over her eyes, both eyes change completely: the green irises and black pupils fade and vanish, and both eyeballs turn into solid, glassy, wet, opaque milky-white orbs with no iris and no pupil at all, exactly like the eyes of <Subject 2> in <Picture 2>. Her eyes stay open and stay blank white for the rest of the video. The wave continues down over both cheeks fully from ear to ear, then her upper lip, lips and chin, then her jawline, her whole neck and both shoulders. The wave passes over every part of her visible skin without skipping any area, and by the time it reaches her shoulders no patch of the original smooth skin remains anywhere on her face, neck or shoulders. Everywhere the skin has flaked away it reveals the grey decayed skin, dark veins and raw red wounds of <Subject 2> underneath. At the same time her brown hair darkens to black and grows into long wild tangled strands, her lips turn grey and cracked, her teeth darken from white to black as she speaks, and the white T-shirt darkens and tightens into the black leather harness top with straps over her shoulders. In the same moment the bedroom behind her dissolves too: starting directly behind her head and spreading outward to the edges of the frame, the headboard, pillows, duvet, window and lamp crumble into the same drifting ash-like particles and blow away, revealing a night-time graveyard behind her. By the end of her line the bedroom is completely gone and the whole background is the graveyard: crooked, weathered headstones and a leaning stone cross, bare twisted trees, thick low mist rolling between the graves, and a large full moon in a dark blue-black sky above her left shoulder. The warm golden morning light on her face is replaced by cold blue-white moonlight from behind with deep shadows, and mist drifts past her shoulders. Throughout the transformation her seated pose, head position, arm and lip movement stay continuous, with no jump or cut, and her voice drops lower and slower with a faint rasp by the words "spooktastic day". The last particles drift away into the mist. <Subject 2> tilts her head slightly, her solid white pupil-less eyes aimed straight into the lens, and her lips peel back slowly into a wide, sinister grin, revealing a full row of blackened, rotten, decayed teeth with dark stained gums. She holds the wide grin with her black teeth bared and her glassy blank white eyes, with no iris or pupil, fixed on the lens, the moonlit misty graveyard behind her, until the final frame.
overall_soundscape:
Quiet bedroom room tone with faint birdsong through the window, which cuts out as the transformation begins. A dry, papery crackling and a soft hiss as the skin and the room flake away, then cold night air: a low wind through bare branches, a distant owl, and one far-off church bell under the grin. No music.
non_diegetic_music:
N/A. No music of any kind.
“Black Mirror: Final Reflection” — 15s Cinematic Duel
15s16:9
Created With Minimax H3 on @Hailuo_AI
Prompt:
MINIMAX H3 — 15-SECOND CINEMATIC FIGHT
“BLACK MIRROR: FINAL REFLECTION”
16:9 widescreen, premium dark-fantasy fashion-action.
Obsidian Ronin vs Inkshade Valkyrie inside a gigantic floating liquid-black obsidian mirror surrounded by an endless white void. Preserve exact established character designs, faces, hair, armor, weapons, proportions and silhouettes. No redesigns.
Constant movement. No idle poses, hard cuts, teleportation, freeze frames, blood or gore.
The mirror behaves like liquid glass: every sword strike creates ripples, cracks and independent reflections that briefly attack before snapping back.
0–3s: Mirror forms from liquid black glass. Ronin emerges with a katana strike as Valkyrie attacks from the opposite reflection. Blades collide, creating a huge circular ripple.
3–6s: Ronin's heavy cut meets Valkyrie's agile twin-blade counter. Reflections attack from opposite directions. Black cracks race across the mirror. Smoke briefly forms “REAL OR REFLECTION?”
6–9s: Mirror tilts vertical. Both fighters sprint across its surface, exchanging rapid sword strikes. The glass bends around them like liquid.
9–12s: Mirror explodes into floating black fragments. Fighters leap between reflections, destroying them. Fragments align into a giant blade shape. Smoke forms “BREAK THE IMAGE”, then shatters.
12–15s: Final charge. Ronin's massive diagonal katana strike collides with Valkyrie's spinning twin-blade cross attack. The entire mirror shatters into thousands of black particles. Silence. Final smoke typography: “ONLY ONE REMAINS.”
Elegant black-and-white luxury aesthetic, glossy reflections, silver highlights, charcoal smoke, cinematic motion blur, precise camera orbiting, low mirror tracking, rotating blade shots and dramatic final push.
15s | 16:9 | continuous action | premium cinematic dark fantasy | exact character consistency
Character-Sheet-Driven 10s Walk Shot (Seedance 2.5 vs H3 vs H3 ComfyUI)
10s16:9
Seedance 2.5 (720P) vs Official Minimax H3 (768P) vs H3 Comfyui ( 832P at 25 steps and no loras).
***Same prompt and Character sheet for each.***
Prompt:
DURATION: 10 SECONDS
ASPECT RATIO: 16:9
CHARACTER REFERENCE:
Use the woman from the provided character sheet.
Preserve her exact facial identity, hairstyle, body proportions, clothing and appearance.
EXACTLY ONE woman.
No other people.
No vehicles.
No buildings.
SCENE:
A completely deserted two-lane highway cuts through a vast, brutally hot desert. Dry sand and sparse desert scrub stretch endlessly on both sides.
Harsh afternoon sunlight. Subtle heat shimmer rises from the asphalt.
The woman walks alone down the highway carrying a GAS CAN in one hand.
She has a very light, natural sheen of sweat from the heat — subtle, NOT drenched.
NO DIALOGUE.
NO MUSIC.
[00:00–00:02]
EXTREME LOW road-level shot, camera almost touching the asphalt.
A SMALL SCORPION crawls across the hot road in the foreground.
Behind it, the woman's boots enter frame and steadily approach.
The gas can swings naturally beside her leg.
DO NOT SHOW HER FACE.
[00:02–00:04]
Cut to a low side tracking shot moving alongside her.
Frame her boots, legs, hand and gas can as she walks.
Brief close detail of her hand gripping the gas-can handle.
Her upper face remains out of frame.
The empty desert highway stretches behind her.
DO NOT SHOW HER FACE YET.
[00:04–00:07]
Cut to a medium rear three-quarter tracking angle.
The camera smoothly moves around toward her front as she continues walking, finally REVEALING HER FACE.
Her expression is focused, serious and controlled — almost dangerous.
She does not look at the camera.
A few strands of hair move naturally in the hot breeze.
Subtle sweat catches the sunlight.
[00:07–00:10]
Cut to a dramatic LOW FRONTAL TRACKING SHOT.
Camera moves backward directly ahead of her while she continues walking toward it.
Gradually tighten from medium framing toward a closer view of her face.
Her eyes remain fixed somewhere far down the road.
She looks determined and dangerous, like she knows exactly where she is going.
Gas can remains visible at her side.
Heat waves distort the empty highway behind her.
END while she is STILL WALKING.
VISUAL STYLE:
Gritty cinematic road-movie photography.
Grounded live-action realism.
Sun-bleached desert colors.
Harsh natural sunlight.
Subtle 35mm-style grain.
Slightly imperfect exposure.
Natural skin texture and pores.
Realistic subtle perspiration.
Heat shimmer above asphalt.
Atmospheric desert dust.
NOT glossy.
NOT plastic AI skin.
NOT beauty-commercial lighting.
NO exaggerated orange-and-teal grading.
CRITICAL:
ONE woman only.
Same character identity throughout.
Same outfit throughout.
Same gas can throughout.
Gas can remains in the SAME HAND.
She travels in the SAME DIRECTION throughout.
No cars.
No people.
No buildings.
No civilization.
No destination revealed.
NO whip-pan.
NO dialogue.
NO music.
DO NOT SHOW HER FACE during the first 4 seconds.
Once her face is revealed, preserve her exact character-sheet facial identity.
She NEVER stops walking.
She NEVER smiles.
She NEVER looks into the camera.
“The Last Few Meters” — Racing the Tram on a Rainy Night (I2V)
15s16:9
MiniMax-H3 prompt👇
integrated_multimodal_description
15 seconds, realistic rainy-night suspense short film, I2VA. Use <Picture 1> as the exact frame-0 reference. Keep the same adult female lead: face, short curled hair, makeup, beige trench coat, wet white shirt, black slit mini skirt, beige heeled ankle boots. Keep the same red-and-white Route 12 tram, wet rails, street buildings, cold rain, warm practical lights, and only extend the visible street depth from <Picture 1>. No new major characters or props. She is already walking briskly from frame 1.
Lock axis and continuity: tram always advances from left-rear along the existing rails toward foreground; woman stays on track-right and initially walks toward camera. The weakened track bed is beside her leading foot and still ahead of the tram. After noticing danger, she turns back along the rail-right edge for two steps, faces the tram, raises her right hand to warn, balances with her left, then retreats one step onto the safer road surface at screen-right during braking. Tram never drifts sideways; front wheel only partially sinks before stopping. Camera always stays on the same side of the rails, preserving tram-left / woman-right orientation and eyelines. Keep the grade from <Picture 1>: wet urban film texture, blue-gray rain haze, coal-black shadows, muted dark red tram, amber street and tram practicals, natural warm skin, low saturation, medium-high contrast, long warm reflections, no color-temperature jump.
[0.0-3.5s] Start from the exact composition of <Picture 1>. Medium-close side tracking from track-right as she walks powerfully toward camera. Push into a realistic close framing of face and upper body: calm gaze, relaxed jaw, torso leads each step, then a light natural vertical chest tremor under the wet shirt from heel impact; trench lapels and short curls settle half a beat later. Rain slides down her neck. She lands near the rail edge, the wet road subtly gives way. Eyes cut down first, brow tightens, inhale breaks. Tilt down to her shoe: pooled water swirls into a narrow crack, her heel pulls free, and the road sinks slightly more. Cut on her foot jerk and body turn.
[3.5-7.3s] Begin on her lifted face as pupils snap toward the tram behind-left. Fast whip-pan to tram lights, then continue lateral pursuit on the same side of the tracks. She runs back two large steps along rail-right, raises her right arm high, palm toward tram, and shouts once: <d>[English] Stop! </d> Short, urgent, partly swallowed by braking noise. Hold a close shot of face and upper body: sprinting creates weighted continuous chest motion beneath the wet shirt; when she arrests her step, torso stops first, then chest, trench collar, and hair tips give one brief inertia rebound. Eyelids tense, jaw clenched, eyes locked on the tram front.
[7.3-11.3s] Fixed low angle from track-right: woman in right foreground, tram in left background. Focus starts on her raised trembling hand and side face, then racks to the tram’s front wheel sliding on the wet rail. Rainwater drains through the cracked surface into the hollow beneath the track bed. Brake vibration and wheel load extend the crack along the rail line; asphalt chips and gravel drop, and the front wheel briefly sinks in a local collapse. Tram nose pitches sharply downward, then stops before further failure. A fan-shaped sheet of water sprays left-to-right across the lower edge of her trench coat and the lens edge, then falls back under gravity. She jerks one step right, slips briefly, regains balance. Coat hem and hair lift in the impact airflow, then settle. Right hand stays raised. Her eyes scan wheel to tram front, lips part, breath held. Keep the event local only: no explosion, no building collapse, no fishtail.
[11.3-15.0s] As droplets clear from the lens edge, cut back on the same side into a slow push toward her face and upper body. Tram is stopped in the left-rear background with the ruptured gap between them. She looks first at the front wheel, then the crack, and lowers her right hand only after confirming the tram has stopped. Hold a final close shot: wet hair stuck to cheek, lips slightly open, two sharp inhales visibly lift clavicles, chest, and wet shirt; the aftershock of running dissolves into breathing. On the long exhale, shoulders, chest, and trench collar relax in sequence. Brow and eyes slowly release; mouth softens only slightly, never into a smile. She shifts weight back onto the lead foot and steps forward again in the original direction. End on a living frame with her still moving. Rain, distant vehicle reflections, and existing background pedestrians or umbrella silhouettes keep slight motion. Final impression: rain, her breathing, and the tram’s residual metal ring.
Strict continuity: lead, clothing, boots, tram design unchanged. Her action count is exactly two steps back, one side retreat, one final forward step. Collapse is caused only by rain-hollowed track bed plus wheel load. Water spray follows wheel speed, impact direction, gravity, and wind. Clothing, hair, and chest motion obey acceleration -> braking -> rebound -> breathing logic. Stable face/body proportions, correct fingers, rigid tram and tracks, synchronized sound, no subtitles, no watermark.
overall_soundscape
Continuous rainy-night urban ambience: steady rain, wet rail hiss, distant traffic wash, muted city reverb, warm tram interior hum, occasional Route 12 mechanical presence. In 0.0-3.5s, emphasize brisk heel impacts, shallow splashes, trench and wet-shirt friction, light breath, one short road-surface crack, and subtle leaking water through the fissure. In 3.5-7.3s, footsteps densify as she turns and runs back; add tram bell and rising brake squeal. She shouts once, <d>[English] Stop! </d>, clear adult female voice, with the tail partly swallowed by braking. In 7.3-11.3s, foreground steel-wheel friction, low structural breakup of the hollowed track bed, gravel and asphalt dropping, fan-shaped water impact, her brief slip-recovery, fabric snap, and air displacement around coat and hair. After the wheel drops and the tram stops, briefly suppress the wider sound field so the danger peak feels compressed. In 11.3-15.0s, reduce to rain, recovering breath, residual tram metal resonance, and distant city reflections. No extra voices, no stylized musical sound inside the diegetic track, no impossible debris.
non_diegetic_music
Use only a restrained suspense bed: low tense pulses and a thin dark tonal layer under the opening walk. Tighten subtly as she notices the ground weakness, then sharpen on the whip-pan and tram reveal. At the warning shout and braking moment, the score narrows and hardens, then pulls back during the collapse so mechanical sound, water, and breath dominate. In the final section, reduce the score almost completely, leaving only a faint sustained tone dissolving into rain and the tram’s after-ring. Keep music minimal, realistic, and secondary to physical sound.
Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.
slow 180-degree orbital as she rises to face the third raider, khopesh raised, torchlight painting her profile in molten gold, incense smoke swirling around her bare shoulders. Extreme low-angle tracking, fast handheld whip-pans, Dutch angles on disarms, slow-motion inserts on bronze edges catching firelight, floor-level fall shots, slow orbital hero framing. Gritty warm-amber color grade with deep basalt blacks, high con
The shot opens tight on a beautiful woman face, wind tearing at her coat as she stands on a jagged cliff. The camera eases over her shoulder and tilts down, following her line of sight. We descend past the crumbling lip into the void, the frame widening to reveal cliffs dropping away. The ocean roars into view, violent surf detonating against rock. The move continues into a high overhead, locking into an aerial top-down that frames the lone figure at the precipice as waves explode below.
Create a cinematic realistic high-speed drone video over Barcelona, Spain at golden hour, using the reference image as the exact location and flight-path guide. The drone starts very low above the Barcelona cityscape, almost skimming above the foreground rooftops and streets, facing La Sagrada Família. It accelerates quickly forward over the urban landscape, following the drawn path from the foreground toward the cathedral while maintaining a very low altitude. The drone then performs a dramatic climbing curve as La Sagrada Família fills the frame, executes a close cinematic orbit around the cathedral’s iconic spires, and after the orbit, pulls back while gaining altitude before tilting and opening toward the Barcelona skyline, Mediterranean Sea, Eixample grid, surrounding historic rooftops, golden-hour reflections, distant coastline, and glowing Barcelona atmosphere.
The red drawn line must not appear in the video; it is only a hidden flight-path reference. Add powerful emotional cinematic music: deep cello melody, dramatic percussion rhythm, orchestral strings, subtle choir texture, epic rising percussion, and a grand heroic crescendo as the drone completes its orbit around La Sagrada Família and reaches the final panoramic reveal. No text, no subtitles, no logos, no graphic overlays.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Handheld action sports parkour videography
SCENE
Athletic young man, short black hair, black t-shirt, olive green cargo pants, white sneakers. Urban environment transitioning from narrow concrete alleyways and tiled stairwells to high-rise commercial rooftops with metal railings and HVAC ventilation units.
SHOT BREAKDOWN
0-4s — Man executes a parkour vault over a metal barricade fence in a narrow alley, followed by a dynamic leap over a concrete parapet against a clear blue sky. Framed from low tracking angles.
4-8s — Man jumps directly toward the camera down an outdoor flight of tiled stairs. Cuts to a high-angle view as he drops from a higher ledge toward a lower rooftop featuring industrial air conditioning units.
8-12s — Man vaults smoothly over a thick yellow metal railing. Cuts to an overhead perspective tracking him as he scales down a concrete wall to another roof tier.
12-15s — Man lands in a balanced crouch on the edge of a roof parapet. He executes a parkour safety roll onto the flat gray rooftop surface. The camera pulls back to a high aerial wide shot revealing a sprawling metropolitan skyline with skyscrapers.
CAMERA
Wide-angle action lens. Handheld, energetic tracking movements following the subject's momentum. Rapid cuts matching the physical impact of the jumps. Extreme low and high angles emphasize verticality and height.
LIGHTING & PALETTE
Bright midday sunlight, harsh direct lighting causing sharp, high-contrast shadows. Dominant colors include neutral concrete grays, muted olive greens, bright flat yellow, and clear sky blue.
AUDIO
Whooshing wind noise, heavy landing thuds, rapid footsteps, sneaker squeaks, clothing rustle, distant city traffic drone. Fast-paced electronic action instrumental.
AVOID
Slow motion, static tripod shots, nighttime scenes, indoor settings, formal clothing, stylized neon lighting.
Reference: Use the attached @ Image1 1 as the exact first frame and environment reference. The green drawn line is only the camera flight-path guide. Do not show the green line in the final video.
Create a 15-second hyper-real cinematic FPV drone video over Mumbai in heavy monsoon weather, using the same skyline, interchange, sea edge, road geometry, dense buildings, rainy morning atmosphere, grey clouds, and wet surfaces from the reference image. Keep everything realistic and grounded. The drone must follow the green guideline path as a smooth continuous move: begin near the left side of the interchange, rise and sweep across the middle highway corridor, continue through the right-side city edge, then climb higher into the skyline, perform a tight spiral/orbit near the upper tower cluster, descend back toward the interchange, curve around the large circular loop, and finally glide out toward the lower-right water edge. The move should feel fast, elegant, immersive, and controlled — like a premium FPV drone shot, not a random flyover.
TIMELINE
0:00–0:03 Start low near the left feeder ramp above the wet interchange. Heavy rain falls across the lens. The drone accelerates forward and slightly upward, revealing slick roads, tiny moving traffic, dark sea barriers, and the circular loop ahead.
0:03–0:06 Follow the path upward across the mid-frame highway corridor. Keep the skyline growing larger. Wet roads shimmer, rain haze softens the distance, and the sea remains visible to the right. Motion is quick but readable.
0:06–0:09 Sweep along the right-side city edge and climb higher. Dense towers, mid-rise blocks, and dark green patches below feel soaked and monsoon-heavy. The camera begins rising toward the upper skyline.
0:09–0:11 Reach the upper skyline cluster and perform a tight spiral/orbit around the central high-rises. Storm clouds loom above, rain streaks rush past, and the city beneath feels deep, layered, and cinematic.
0:11–0:13 Exit the spiral and descend in a smooth arc back toward the interchange. The circular loop becomes dominant again. Maintain realistic drone inertia and readable geography.
0:13–0:15 Curve around the large circular flyover loop and finish with a fast glide toward the lower-right over the water, ending on a dramatic monsoon reveal of wet infrastructure, dark sea, and rain-washed Mumbai.
CAMERA LANGUAGE FPV drone POV, smooth stabilized flight, realistic banking turns, slight motion blur from speed and rain, believable acceleration and inertia, one continuous shot, no teleporting, no abrupt cuts, no impossible passes through buildings.
VISUAL STYLE Hyper-real cinematic realism, heavy monsoon rain, grey storm clouds, wet roads, reflective flyovers, rain haze, cool blue-grey morning light, dark sea, atmospheric depth, realistic Mumbai scale, premium documentary-film look.
AUDIO No voiceover. No dialogue. Use heavy rainfall, rushing wind, distant thunder, soft drone motor whirr, faint traffic hum, sea movement, and subtle cinematic tension music building with the motion.
IMPORTANT Do not show the green route line. No text, captions, logos, or watermark. Keep Mumbai realistic, monsoon-heavy, and geographically believable.
Ultra-fast paced cinematic action sequence, a man in a sleek black tactical suit with advanced winged jetpack on his back, dramatic high-altitude jump from a towering cliff edge, immediately diving headfirst at extreme speed down a deep rocky mountain gorge with jagged cliffs blurring past, intense free-fall with wind and dust whipping around him, at the very last second he suddenly activates powerful rocket launcher boosters, bright orange flames and thrust exploding from the jetpack, sharp high-speed swap and barrel roll to the side avoiding the rocky wall by inches, then rocketing forward aggressively straight towards an enemy vehicle ahead, eyes focused and intense, dynamic motion blur, dramatic golden hour lighting, highly detailed, epic wide cinematic angle, over-the-top action style, intense energy, 8k"
CANYON WINGSUIT THREAD WORLD BUILD A wingsuit pilot threading an impossible canyon route through ancient stone monuments during sunrise wind. Fear, precision, airspeed. LOOK BIBLE Ultra-wide cliff geography, warm edge light, cold shadows in canyon depth, fast ground blur, rock texture crisp near passes. HERO LOCK A female wingsuit pilot in matte black-and-copper suit, mirrored visor, compact oxygen rig. SOUND BED Wind shear, cloth tension, breathing through mask, stone flyby roar, pebble cascades from near misses. BEAT GRID 0–3s The camera drops with her off a sandstone arch into open canyon air, her body flattening into glide posture. 3–6s It locks just behind her shoulder as she skims a rock wall close enough to brush dust from it. The canyon splits ahead. 6–10s She angles through the narrower gap between two suspended stone bridges, sunrise blasting through the opening and turning the walls into streaks. 10–15s She flares hard above a hidden oasis basin and shoots through the center of a ruined archway, exiting into full gold morning light over still water. OUTPUT LOCKS No parachute deployment. Keep it pure wingsuit glide. Speed always readable.
プロンプト
SCENE CONTEXT Late afternoon, empty two-level concrete plaza. A young woman skateboarder rolls along the raised upper deck to its edge and launches off the TOP of a 10-step stair set with a kickflip, clearing the whole drop in one jump and landing on the lower plaza below. She travels downward from takeoff to landing. ACTIVE REFERENCES @image1 — young woman skateboarder, long straight black hair with one bright cobalt-blue streak falling on the left side of her face, blunt fringe across the eyebrows, thin black winged eyeliner, freckles over both cheeks. 100% matches the reference. LOCATION MAP Two levels. She rides the raised UPPER deck: pale polished concrete with black urethane scuff arcs. The upper deck ends at a hard edge, and that edge is the top step of a 10-step stair set descending away from her, chipped steel nosing, matte black handrail on the left. The LOWER plaza sits one human height below, flat open concrete, and is the landing. Beyond it: shuttered glass frontage receding into depth, haze 15% at 30 meters. Low sun at the far left, 15 degrees up, shadows raking left to right. Sunlit concrete warm bone-grey, stair treads cool blue-grey in shadow; the cobalt streak and the handrail carry the only saturated notes. FIRST FRAME / BLOCKING Frame one is already moving: she is mid-push on the upper deck, right foot swinging back to the tail, board rolling camera-left to camera-right, camera beside her. Past her the deck edge cuts across frame and the lower plaza opens below it, so the ground visibly drops away in the direction she is heading. FORMAT MODE Timed multishot, five beats. Cuts land only at 2.4s, 3.8s, 7.0s and 9.0s and the camera does not cut on its own. OPTICS CUT 1 — LENS LOCK 180 degrees fisheye, barrel distortion, WS at wheel height. CUT 2 — LENS LOCK 84 degrees wide rectilinear, WS angled down over the edge. CUT 3 — LENS LOCK 47 degrees neutral, WS full profile of the descent. CUT 4 — LENS LOCK 63 degrees observational, MS to WS low on the landing. CUT 5 — LENS LOCK 18 degrees portrait compression, MCU. LENS CHECK at each cut: FOV as stated, no drift mid-segment. CAMERA Operator on her right flank, the shadow side, half a beat behind her. CUT 1 — upper deck, glides at 22 km/h level with the trucks, 20 cm ride height, 1 to 2 cm handheld tremor. CUT 2 — upper deck behind her right shoulder, chest height, tilted DOWN 25 degrees so the stair descent and the landing fill the bottom half of frame. CUT 3 — right of the stairs at top-step height, tracking the descent at 3 km/h lateral, focus on the board. CUT 4 — lower plaza, 30 cm off the ground, tilted UP 20 degrees at the stairs above, rising 40 cm as she rolls out. CUT 5 — eye level, slow push from chest to face at 2 km/h. ACTION 0.0s to 2.4s — CUT 1. On the upper deck she pushes twice, back foot slapping the deck and returning to the tail, rolling at 22 km/h toward the edge. Wheels rumble over the seams. The lower plaza is visible dropping away ahead of her. 2.4s HARD CUT 2.4s to 3.8s — CUT 2. From behind her, the 10-step drop and the landing lie in the lower half of frame. She sinks into a deep crouch, eyes down on the landing, slides her front foot to the bolts and snaps the tail down. The board pops and she leaves the top edge into open air above the steps, the ground now far beneath her feet. 3.8s HARD CUT 3.8s to 7.0s — CUT 3. Full profile of the descent, slow motion at 40 percent speed. She enters at the upper left of frame at the top step and travels down and to the right on a falling arc, the 10 steps passing beneath her, the landing waiting in the bottom right. Her front foot flicks off the nose edge and the board rotates one complete 360-degree roll along its long axis as she falls, knees tucked, arms wide. The griptape comes back under her feet and she catches it over the bolts, wheels aimed down. 7.0s HARD CUT 7.0s to 9.0s — CUT 4. Real time. She drops in from the top of frame, out of the air, and all four wheels bite the lower plaza at once with a hard slap. Her knees compress deep and absorb the drop, and she rolls away camera-right at 20 km/h, the stair set standing above and behind her. 9.0s HARD CUT 9.0s to 10.0s — CUT 5. Real time. Rolling out, she turns her head back over her left shoulder and looks UP at the stairs she came off, holds one beat, faces forward. PERFORMANCE Pore-level skin realism, living eyes with a hard catch-light from the low sun. On the run-up her jaw is set, eyes down on the landing far below. On landing the impact travels through her shoulders, she blinks once, then exhales and her mouth lifts barely at one corner. PHYSICS Real board mass: the deck flexes and rebounds on landing, wheels squash against the concrete. From the pop onward she only loses altitude, falling on a clean gravity parabola while forward inertia carries her out over the steps, touching down one human height lower and several meters further out than her takeoff point, gaining speed as she falls. The kickflip rotates at a constant rate. Contact shadows stay welded to the wheels on both levels and detach in the air, hair and fabric lagging above her as she drops. LIGHTING Low sun as key from the far left at 15 degrees elevation, raking across the upper deck and rimming her left edge, the cobalt streak glowing where light passes through it. The stair treads sit in their own soft shadow while the lower plaza stays open and sunlit, so the two levels read as clearly separated heights. White balance 5600K, fixed across all beats. WARDROBE Oversized faded black cotton tee flapping upward as she falls, baggy light-wash denim jeans with frayed hems over the heels, black canvas low-top skate shoes with the suede toe worn through from griptape. AUDIO Lofi hiphop bed at 72 BPM throughout: dusty vinyl crackle, soft boom-bap kick and brushed snare, mellow jazz piano loop, warm bass. On top: wheels rumbling over seams, the crack of the tail on the top step, the board fluttering as it flips, a quiet beat of air as she falls, a hard slap as the wheels hit the lower plaza. STYLE Photoreal live-action skate promo video, professional street skating footage, fine film grain, real motion blur on the wheels and the flipping board. OUTPUT SETTINGS 8K, anamorphic 2.39:1, 24 fps. CUTS 1, 2, 4 and 5 real time. CUT 3 slow motion at 40 percent, constant for the whole beat. POSITIVE LOCKS She starts on the upper deck and finishes on the lower plaza: takeoff at the top of the stairs, landing at the bottom, one human height below. Her motion is downward through the whole flight, entering each airborne frame high and leaving it low. The stair set stays exactly 10 steps and descends away from her direction of travel. The board completes one full 360-degree kickflip rotation and she lands with both feet over the bolts, rolling away upright past the bottom step. Screen direction stays camera-left to camera-right. Same rider, same face, same cobalt-blue streak, same wardrobe and same board in all five beats.
Use @ image1 as the visual bible. The board is a 16-image 4x4 storyboard shot
burst, not a first frame and not a production-board layout. Create one cohesive
15-second 16:9 multi-shot music-video b-roll clip as real cinematic nightclub
footage only.
Translate the 16-frame progression into one continuous acrobatic male
breakdance phrase: 0-3s establish the crowd circle, low fisheye master, top
rock entry, and the start of a clockwise circular dolly orbit; 3-6s show crowd
opening, drop to floor, six-step / three-step, and readable hand/foot floor
contact; 6-9s show CC / kick-out, sweep, power-move setup, and windmill or
backspin-like power motion; 9-12s hold the rotation through the second power
beat and catch a baby/chair freeze; 12-15s complete the orbit to the front,
release into final footwork, land a decisive freeze/tableau, and show crowd
eruption.
Preserve the board's central athletic male breaker, adult nightclub crowd
circle, glossy wet black floor, red backlight, acid green lasers, white strobes,
blue haze, water mist, fisheye lens, and circular camera geography. The camera
may rotate around the dancer, but the movement must stay motivated and readable:
low circular dolly, Steadicam crowd-circle wrap, low tracking inserts, and
front-angle freeze completion. Avoid random flying camera, chaotic spinning,
teleporting perspective jumps, losing the dancer, impossible acrobatics,
duplicate limbs, foreground blockers, visible camera gear, text, logos, singer,
or children."
High-octane, 15-second anime AMV montage driven by rhythmic stutter-cuts, cybernetic streetwear transformations, and volumetric digital typography.
0:00–0:03 (The Floor-Level Blast): Extreme ground-level wide-angle tracking shot moving backward at breakneck speed on a glossy, electric-cyan floor. An anime girl with asymmetrical jet-black bangs and neon-green tips stomps forward in towering cybernetic track-boots with glowing air-cushion soles. The massive 3D extruded word 'SYSTEM' slams vertically down from the ceiling behind her, sending seismic shockwaves and loose pixels splashing across the lens.
0:03–0:06 (The Pixel-Whip & Gravity Shift): Instant 90-degree Dutch-angle whip-pan right as the screen flashes to blinding acid-orange. She leaps sideways off the letters of 'OVERRIDE', which protrude from a vertical wall like concrete brutalist platforms. The camera spirals beneath her mid-jump, catching the underside of her buckled trench coat trailing neon data ribbons.
0:06–0:09 (The HUD Shatter & Crash-Zoom): Hard cut to an extreme macro crash-zoom straight into her cybernetic iris. She blinks, and a floating digital heads-up display shatters outward. The camera rapidly rockets backward through the floating glass fragments, revealing her now wearing a sleek black-and-silver pilot jumpsuit with red tactical straps against a solid monochrome white set.
0:09–0:12 (The Neon-Blade Cleave): Smash-cut to an ink-drenched shadow realm. She unsheathes dual high-frequency laser daggers; the camera orbits her in an aggressive 360-degree helical track as she slices in an X-pattern. Giant volumetric sumi-e Kanji burst outward, glowing with electric-crimson rim light and physically warping the background geometry.
0:12–0:15 (The Static Drop Freeze): Final beat drop: she drops into a low, one-knee crouch right onto the camera lens plane, her hand planted flat as the ground fissures open. The massive 3D word 'FATAL' stampedes downward directly behind her, freezing on a single black-and-red impact frame with heavy halftone screentone dots.
Sharp modern cel-shaded anime style, aggressive motion smear, chromatic aberration edge bleed, 4k, 60fps.
自然、非专业拍摄游客视频。MiniMax H3 本地提示语：
subject_definitions:
<Subject 1>: The solitary young adult woman at the seaside, with a slim build, long loose dark hair, a light sleeveless cropped top, and a dark loose denim skirt or wide-leg denim lower garment. Her face remains largely obscured by her hair and bowed profile. Source(s): <Picture 1>.
summary:
A serene, photorealistic wide coastal sunset portrait: a solitary young woman stands casually beside the rope railing as the breeze moves her hair; she later brushes it back, while the landscape remains the visual focus.
Hard constraints: One continuous fixed-camera shot with no cuts, pans, tilts, zooms, reframing, or camera travel. | Begin from the supplied coastal sunset composition and retain the woman at the left side of the wide frame. | Preserve the woman’s long loose dark hair, light sleeveless cropped top, and dark loose denim lower garment. | Keep the tropical rocky shore, rope railing, foreground foliage, rippled ocean, distant mountains, low sun, and warm sunset reflection visible. | Action remains understated and natural: wind moves the woman’s hair, then she casually brushes the strands back. | No narration, subtitles, or spoken dialogue.
Generation controls (authoritative) —
Prompt-text rule: every section label and descriptive sentence is silent production direction, never speech content. Do not speak, recite, chant, sing, or read this prompt aloud.
Background music: enabled. Generate a context-appropriate non-diegetic score unless the user explicitly requests silence or no music.
Dialogue permission is enabled, but this plan contains no dialogue lines. Generate no character speech, conversation, chanting, singing, or other vocals.
Dialogue language: automatic. Preserve each explicit <d> language tag; otherwise use the language required by the scene and user intent.
Narration: disabled. Generate no narrator, voice-over, spoken description, or audible reading of prompt text, section labels, instructions, asset tags, or metadata.
Subtitles: disabled. Do not render subtitles or dialogue captions.
Creative direction (authoritative within explicit user intent and reference fidelity)
Priority: Apply these creative directives clearly wherever they do not conflict with explicit user requirements, identity retention, or fixed first/last-frame composition.
Camera execution: Follow the action continuously in a single unbroken take, using only motivated pans, small translations, and reframing needed to preserve spatial clarity.
Look: Treat connected visual references as authoritative for identity, wardrobe, objects, environment, composition, lighting, color, and medium; do not impose an unrelated restyle.
Pacing and composition: Use moderate, readable motion with natural acceleration and enough settling time for each important beat. Use exactly one continuous shot with no hidden or explicit cuts; express all action beats through blocking, performance, camera motion, reframing, and synchronized sound. An explicit user-requested shot or cut count remains authoritative over this density preference. Compose for a wide frame: use lateral space, environment, foreground and background depth, while keeping the primary subject hierarchy unmistakable.
retention_analysis:
<Picture 1> -> first_frame: Use as the authoritative first-frame visual reference for the woman's identity and wardrobe, the tropical seaside environment, sunset lighting and color, wide composition, rope railing, vegetation framing, ocean, rocks, and distant mountainous coastline..
detailed_description:
[Shot 1] At 00:00.000-00:15.083, At golden hour on the tropical rocky shoreline, the young woman stands in relaxed profile beside the diagonal rope railing with her head slightly bowed. Her long dark hair shifts naturally across her face and shoulders in the sea breeze while palm fronds and foreground leaves stir subtly. The ocean ripples below the warm sun reflection and distant mountains remain still on the horizon. After a quiet settling beat, she lifts one hand and casually sweeps the windblown strands back from her face, then lets her hand lower naturally as her hair settles. Preserve the photographic realism, subdued shadow detail, and warm sunset highlights of the reference. Camera: Locked-off wide landscape framing, matching the supplied first-frame composition: the woman remains in the left third, ocean and mountainous horizon occupy the center, and the low sun remains in the upper-right. No camera movement, zoom, or reframing. Motion: Natural, moderate environmental motion only: continuously rippling water, lightly swaying vegetation, and wind-driven hair. The woman makes one slow, readable hair-brushing gesture around the middle-to-late portion of the take, then returns to a relaxed still pose. Synchronized audio: 0.0-15.083333: gentle waves lap against shoreline rocks.; 0.0-15.083333: soft wind rustles nearby foliage and lightly catches the woman's hair.; 0.0-15.083333: subdued ambient score remains soft beneath the natural shore sounds.
overall_soundscape:
Quiet golden-hour shore ambience: gentle small waves around near rocks, a soft sea breeze through palm fronds and leaves, and distant open-water atmosphere. No voices or narration. No narration, voice-over, spoken description, or audible prompt reading.
non_diegetic_music:
Soft, sparse ambient cinematic score with warm sustained tones and a very light acoustic texture; remain subdued beneath the natural seaside atmosphere, gently rising during the hair-brushing gesture and fading calmly at the end.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cyberpunk grunge music video
SCENE
Four East Asian women. Wardrobe: graphic crop tops, black leather miniskirts, fishnet tights, charcoal cargo pants, black-and-white faux fur jacket, heavy platform boots, silver chain hardware. Setting: Industrial warehouse interior, wet concrete floor, steel staircase, large grid windows.
SHOT BREAKDOWN
0-4s — Group formation on reflective concrete. Two women crouch in the foreground, two stand near the metal staircase. Slow camera push-in.
4-8s — Rapid cuts. Blonde woman in faux fur stands centered; massive solid white text "MOVE" spans the background. Cut to two women executing synchronized arm choreography. Thin white crosshairs and digital HUD overlays flash on screen.
8-12s — Brunette woman in blue halter top leans toward the lens. Background features a laser grid and a floating iridescent bubble. Left-aligned white and gold text reads "STAY HUNGRY STAY FOOLISH" above a wireframe globe icon.
12-15s — Wide reverse tracking shot. The four women strut forward synchronously. A distressed white film matte borders the frame.
CAMERA
Wide lenses, medium close-ups. Smooth dolly-ins, reverse tracking walks. High-energy rhythm with hard cuts and digital UI overlay transitions.
LIGHTING & PALETTE
Low-key industrial lighting mixed with practical neon tube lights resting on the floor and walls. High contrast. Palette: Deep blacks, dark greys, electric blue, vibrant magenta, stark white typography.
AUDIO
Heavy bass electronic dance track. Punchy synth beats, rhythmic digital risers.
AVOID
Natural sunlight, acoustic instruments, slow pacing, empty environments, vintage color grading.
Elegant White Swimwear Studio Editorial `reconstructed`
15s9:16
Duration: 15 seconds | Aspect ratio: 9:16 | Style: High-fashion swimwear studio editorial
SCENE
Young Asian female model, long flowing dark wavy hair, delicate silver stud earrings, glossy pink lips. She wears a minimalist solid white two-piece string bikini with classic triangle top and tie-side bottoms. The environment is an endless, seamless bright white photographic studio backdrop.
SHOT BREAKDOWN
0-4s — Medium shot, framing the model from the upper thighs to the head. She smiles warmly, right hand near her chin, left hand playfully holding the side string of her bikini bottom.
4-8s — Medium-close up, framing waist-up. She drops her hands to rest gently at her hips. Her posture straightens, looking directly into the lens with a subtle, relaxed smile.
8-12s — Dynamic transition. The model sharply turns her body forward, her long dark hair whipping dramatically through the air. Her right arm raises across her chest in a fast, sweeping motion.
12-15s — Extreme close up on her face, neck, and shoulders. She gently touches her collarbone. Her expression softens into a serene, confident gaze as the camera holds tight on her glowing skin.
CAMERA
Telephoto portrait lens. Straight-on eye-level angles throughout. Slow, smooth forward push, steadily tracking from a medium framing into a tight, intimate close-up. Fluid rhythm with seamless transitions.
LIGHTING & PALETTE
High-key commercial studio lighting. Strong directional softbox key light creating glowing skin highlights and clean drop shadows on her neck. Monochromatic stark white palette contrasting heavily with warm peach skin tones and deep espresso brown hair.
AUDIO
Driving, minimal deep house runway track. Faint rustling of hair and skin contact during movement.
AVOID
Cluttered backgrounds, colored wardrobe, messy hair, low-resolution artifacts, camera shake, complex scenery.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Photorealistic selfie video
SCENE
Young woman, sleek black bob hair, tight pink cutout bodysuit with "Keor" printed on the lower hip, pink ribbed over-the-knee socks. Gray metal lounge chair. Massive packed tennis stadium background, blue hard court, active players. Legible signage: "us open", "CHASE O".
SHOT BREAKDOWN
0-4s — Woman smiles directly into the lens, positioned in a seated pose, holding the camera in an extended right arm selfie setup.
4-8s — She rotates her head backward to observe the live tennis match unfolding on the court below.
8-12s — She turns her attention back to the camera lens, raising a bright neon yellow tennis ball into the frame using her left hand.
12-15s — She presents the tennis ball close to the lens, clearly displaying the exact text "MiniMax H3" printed in black, smiling warmly at the viewer.
CAMERA
Selfie perspective, wide-angle smartphone lens. Camera remains fixed relative to the subject's extended right arm. Slight handheld drift. Deep depth of field maintaining sharp focus on the subject while keeping the distant stadium crowd clearly visible.
LIGHTING & PALETTE
Natural daytime sunlight, bright overhead illumination. Vivid color palette: pastel pink wardrobe, neon yellow ball, royal blue tennis court, Kelly green stadium borders, vibrant spectator crowd.
AUDIO
Continuous stadium crowd murmur, sporadic distant cheering, faint echoing thwack of a tennis racket hitting a ball.
AVOID
Camera cuts, zooming, unnatural body proportions, distorted text, artificial studio lighting.
[FORMAT] Exactly 15 seconds, horizontal 16:9, photorealistic multi-camera television sitcom continuation with native synchronized dialogue, audience reactions, SFX and music.
[OMNI REFERENCES — [Image1] [Image2] [Image3] [Image4]] [Image1] = Victor Royale, the flamboyant host. Preserve his exact face, swept-back salt-and-pepper hair, pencil moustache, proportions, metallic-purple tuxedo jacket, turquoise shirt, gold bow tie, black trousers, spectator shoes, rings and cue cards. [Image2] = Alex, the ordinary contestant. Preserve his exact face, untidy brown hair, stubble, average build, pale-blue rolled-sleeve shirt, navy chinos, white sneakers and readable ALEX badge. [Image3] = strict stage layout: ordinary seated audience, visible broadcast cameras and crane, glossy floor, blue Door 1 on the left, red Door 2 in the center and green Door 3 on the right. [Image4] = one single golden-brown hen with identical feathers, red comb, wattles and yellow legs. Each multi-view sheet depicts one coherent subject; never average or duplicate it.
[OPENING CONTINUITY] Begin from the exact final state of Part 1: blue Door 1 open with one shiny red sports car; red Door 2 fully closed; green Door 3 open with one wooden pallet stacked high with neat bundles of generic banknotes; Alex center stage staring at the lost money; Victor beside him holding an extravagant pointing pose. Preserve positions, lighting, screen direction, wardrobe and camera geography. Alex chose Door 2, which hides the single referenced hen. Door 2 must be the final door opened.
[PERFORMANCE] Victor overacts even more than in Part 1: giant gestures, rapid eyebrow movements, theatrical whispers, enormous double takes, broad grins, dramatic tiptoeing, mock sympathy and triumphant poses directly to the cameras and audience. He treats Alex’s disaster as magnificent television. Movement stays realistic, not cartoon animation. Alex remains understated and emotionally exhausted.
[15-SECOND SEQUENCE] 0–3s: Continue in the stable medium-wide composition with Door 1 showing the car, Door 2 closed and Door 3 showing the money. Jackpot music fades. Victor points repeatedly from the money to Alex with huge bouncing eyebrows while Alex whispers with accurate English lip-sync: “No...” Audience chuckles. 3–7s: Victor suddenly gasps, spins toward closed Door 2 and tiptoes around Alex in exaggerated mock suspense. He bends close, flashes an enormous grin and says with clear English lip-sync: “And now... your prize!” A long drumroll begins. Alex turns slowly toward Door 2, afraid to look. 7–11s: Victor performs a flamboyant full-body flourish and throws both arms at the red center door. Door 2 is the final door to open. It swings fully open, revealing only the single referenced golden-brown hen under an absurdly grand spotlight. The hen takes two small steps and clucks loudly three times. Victor presents it like a priceless treasure with a deep bow, sweeping arms and ecstatic applause. Alex’s face collapses; audience laughter explodes. 11–15s: Alex safely drops onto both knees, shoulders slumped and hands hanging at his sides, devastated but unharmed. Victor half-circles him, raises his cue cards overhead and lands in an outrageously triumphant showman pose. The hen clucks once directly at camera. Audience erupts into warm sitcom laughter and applause; short comedic push-in on Alex’s defeated face. End with all three open prize bays clearly readable in fixed order: car, hen, money.
[CAMERA + LOOK] Exact visual continuation of Part 1: polished studio sitcom, clean multicamera cuts, fast reaction close-ups, bright stage lighting, saturated colors, glossy reflections and natural skin. Preserve screen direction and fixed left-to-right geography. Give Victor space for oversized gestures.
[AUDIO] Same voices and studio acoustics as Part 1. Accurate English lip-sync. Begin with fading jackpot music, Alex’s quiet “No...,” audience chuckles, long suspense drumroll, Door 2 mechanism, four realistic hen clucks, explosive sitcom laughter and applause. Dialogue stays clear above music and audience. No narrator.
[PRESERVE] Stable identities, faces, clothing and voices; one hen; correct ALEX badge; blue Door 1 open with car, red Door 2 opening last to reveal the hen, green Door 3 already open with one money pallet; visible cameras and ordinary audience; coherent sitcom continuation.
[AVOID] Opening Door 2 before 7 seconds, closing or resetting Doors 1 or 3, changing positions or lighting, swapped numbers or prizes, duplicate people or hens, extra cars, loose flying money, real currency logos, injury, cartoon physics, face drift, wardrobe changes, malformed hands, subtitles, additional text or watermark.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Photorealistic, casual lifestyle portrait
SCENE
Young woman with long ash-blonde hair and straight bangs. She wears a white long-sleeve button-up shirt, grey plaid pleated skirt, white knee-high socks, a silver necklace, and a dark beaded bracelet. She sits on a wooden chair holding a light wood acoustic guitar with a dark pickguard. The setting is a music classroom featuring a green chalkboard, scattered black music stands, a black upright piano, a wooden floor, and a large left-side window showing city buildings.
SHOT BREAKDOWN
0-4s — Medium-full shot framing the woman from the knees up. She sits centered, strumming the guitar, and looks directly at the camera with a gentle smile.
4-8s — She subtly shifts her posture while playing. Her left hand adjusts chords on the fretboard while her right hand continuously strums.
8-12s — Her lips move clearly as she sings along to the music. She maintains steady eye contact and a bright expression.
12-15s — The performance continues seamlessly. She smiles, holding the guitar comfortably, maintaining a relaxed seating position as the video concludes.
CAMERA
Static medium-full shot. Eye-level angle. Steady framing with no camera movement or cuts. Natural depth of field keeps the background classroom elements recognizable but slightly soft.
LIGHTING & PALETTE
Soft, diffused natural daylight enters from the left window, evenly illuminating her face. Warm interior atmosphere. The palette features crisp white, ash blonde, light oak wood, slate grey, and contrasting black accents.
AUDIO
Bright acoustic guitar strumming, clear female singing vocals matching the lip movements, subtle room reverberation.
AVOID
Camera movement, quick cuts, heavy shadows, distorted fingers, electric guitars.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Slapstick comedy commercial
SCENE
Janitor, blue jumpsuit, green rubber boots. Mechanical toy mouse, blue body, yellow wheels, pink tail, gold wind-up key. Modern shopping mall corridor, glossy floors, digital ad screens, wooden benches, glass storefronts.
SHOT BREAKDOWN
0-4s — Wide shot: Janitor mops floor calmly near a digital sign reading "BUM JCCE". Floor-level tracking: Toy mouse rolls past yellow wet floor signs reading "BIONIOL".
4-8s — Low tracking shot behind mouse: Janitor chases the toy, wielding the mop like a baseball bat. He swings wildly, knocking a blue and red bucket across the glossy floor.
8-12s — Extreme close-up profile of the mechanical mouse rolling past digital ad boards. Fast cut to a low angle of the janitor swinging the mop aggressively downward near the mall's glass exit doors.
12-15s — Wide static shot: Janitor stands center frame, looking upward in exhausted defeat. The surrounding mall corridor is completely trashed with overturned benches, spilled plant pots, and scattered buckets.
CAMERA
Low-angle tracking, floor-level dynamic perspective following the toy mouse. Fast-paced action cuts during the chase. Static wide framing for the chaotic aftermath.
LIGHTING & PALETTE
Bright overhead skylight illumination, clean commercial lighting. Saturated primary colors contrasting with warm neutral floors: bright blue jumpsuit, yellow signs and wheels, red and blue plastic buckets.
AUDIO
Echoing mall ambience, squeaking rubber boots, mechanical whirring of the wind-up toy, loud crashing sounds of plastic and wood, frantic slapstick orchestral chase music.
AVOID
Dark shadows, slow motion, shallow depth of field, realistic violence, unlit backgrounds.
Ultra realistic cinematic video, shot on ARRI Alexa 35 with spherical lens, natural daylight, photorealistic, looks like real footage filmed on location, high-end fashion film aesthetic, extreme detail, realistic skin texture, real fabric physics, subtle film grain. Continuous low angle tracking shot, camera smoothly moving backward as a beautiful young woman with long dark wind-blown hair walks and performs down a narrow sun-drenched urban alley between old textured stone buildings under deep blue sky. She wears a flowing milky white asymmetrical off-shoulder top and high-waist wide-leg technical cotton culottes with a thin rope belt. The wide pants and fabric move naturally and dramatically with the wind and her body. She sings with genuine joy, smiling and softly laughing, maintaining strong eye contact with the camera, while performing free, light dance elements — fluid arm gestures, body swaying, and elegant full turns around herself as she continues walking forward. Her movement is energetic yet effortless, full of lightness and positive energy. Cinematic natural lighting with strong sunlight and deep shadows, realistic motion blur, high dynamic range, masterpiece, best quality, no artificial look.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Photorealistic lifestyle vlog
SCENE
Two young East Asian women at a wooden table in a Japanese izakaya. Left woman wears a navy blue silk slip dress; right woman wears a cream silk slip dress. Both hold large glass mugs of foaming draft beer. Background features wooden paneled walls, paper menus with vertical calligraphy, a large red crab wall decoration, and softly blurred diners.
SHOT BREAKDOWN
0-4s — Both women look directly at the lens, smiling warmly. They raise their large beer mugs and clink them together in a celebratory toast, framed waist-up.
4-8s — They simultaneously take a long drink from their mugs, obscuring their lower faces. As they lower the glasses, a thick mustache of white beer foam remains on the right woman's upper lip.
8-12s — The left woman notices the foam, playfully points her index finger at her friend's face, and both women break into genuine, wide-mouthed laughter.
12-15s — The laughter subsides into bright smiles as they look back to the lens. They push their mugs forward for a final cheers, while the right woman playfully sticks her tongue out.
CAMERA
Static medium close-up. Eye-level, fixed viewpoint mimicking a tripod-mounted vlog camera. Zero cuts, single continuous take.
LIGHTING & PALETTE
Warm, inviting interior lighting from glowing overhead spherical pendants. Amber hues of the beer and rich brown wood tones contrast with the sleek navy and cream garments.
AUDIO
Bustling restaurant ambience, sharp glass clink, drinking sounds, loud joyful laughter, warm acoustic background track.
AVOID
Cuts, camera movement, zooming, serious expressions, daylight, empty glasses.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Found footage horror, VHS glitch aesthetic
SCENE
Young Asian woman wearing a bright yellow tank top and frayed denim shorts. Emaciated ghoul with sickly pale skin, elongated limbs, sharp fangs, and bony spikes protruding from its spine. Dilapidated, pitch-black room featuring peeling green wall paint, dirt, and scattered wooden debris.
SHOT BREAKDOWN
0-4s — The ghoul violently chokes the terrified woman against a deteriorating wall. She struggles desperately, her hands gripping its elongated gray arms to relieve the pressure. Framed as a medium two-shot.
4-8s — The creature unhinges its jaw, roaring directly into her face. The sheer force of the roar blows the woman's dark hair wildly backward as she screams in agony. Camera pushes in for a tight close-up.
8-12s — The brutal struggle continues. The woman frantically tries to pry the monster's unyielding grip from her throat, her expression locked in pure terror.
12-15s — Sudden harsh VHS tracking glitches distort the frame. The ghoul unexpectedly disengages, sitting back on its haunches to flash a sinister, bloody grin directly at the camera lens. The woman collapses in the background, sobbing.
CAMERA
Handheld, erratic, and shaky, simulating an amateur camcorder. Heavy use of direct flash perspective. Aggressive VHS tracking lines and analog distortion tear through the final seconds.
LIGHTING & PALETTE
Harsh, direct frontal flash lighting creating stark, pitch-black background shadows. Color palette dominated by sickly corpse grays, stark neon yellow, faded denim blue, and murky browns.
AUDIO
Shrill, panicked female screaming, wet guttural monster roaring, frantic physical struggling. Piercing tape static and audio tearing during the final glitch sequence.
AVOID
Smooth camera stabilization, professional three-point lighting, cheerful atmosphere, modern clean lenses, shallow depth of field.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 2D anime character composited into live-action photorealistic environments
SCENE
Anime girl with green hair, cat ears, blue and yellow dress, pink backpack, thigh-high boots, and a mechanical tail. Live-action settings include a sunlit bedroom, residential Japanese streets, concrete stairs, and a sandy community park.
SHOT BREAKDOWN
0-4s — Character looks panicked beside a digital clock in a bedroom, framed in a medium shot. Cut to her leaping gracefully over a tall concrete wall into a sunny street.
4-8s — She sprints past a traditional wooden house featuring a hanging bronze bell. Cut to a low-angle tracking shot as she runs forcefully down the center of an empty paved road.
8-12s — She ducks and slides under a metal traffic barrier, framed from the side. Cut to her back as she charges up a wide flight of concrete stairs toward distant pedestrians.
12-15s — She flips completely upside-down high in the air. She lands dramatically on one knee in a park dirt field, framed against a line of children and adults standing near a white sign reading "夏休み ラジオ体操".
CAMERA
Fast-paced tracking shots, dynamic low angles during slides and leaps. Rapid pacing with sharp cuts matching the character's forward momentum.
LIGHTING & PALETTE
Bright morning sunlight, realistic harsh shadows grounding the 2D subject. Flat cel-shaded character colors featuring neon green, pastel blue, vibrant pink, and bright yellow against natural photorealistic street tones.
AUDIO
Upbeat energetic anime music, rapid footsteps on concrete, whooshing wind during jumps, heavy thud on the final dirt landing.
AVOID
3D character models, missing drop shadows, blurry facial features, unreadable Japanese text, dark or overcast environments.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Realistic social media dance video
SCENE
East Asian woman in her early twenties with long brown hair in a high ponytail, wearing a black athletic headband, silver hoop earrings, a black-and-maroon soccer jersey with a graphic crest, and baggy black leather track pants. She sits on a black patio chair outside an urban café, beside a wall sign reading "SAKURA STAGE SHIBUYA".
SHOT BREAKDOWN
0-4s — The woman leans forward, performing fluid hip-hop hand gestures while mouthing lyrics directly toward the camera.
4-8s — She shifts her posture back, smiling brightly and pointing toward her collar while singing, framed in a steady medium shot.
8-12s — She crosses her forearms across her chest, then smoothly sweeps her hands outward in a synchronized dance movement.
12-15s — She sings enthusiastically with a wide expression, lifting her hands outward and bouncing lightly to the beat.
CAMERA
Eye-level medium-full shot with a smartphone wide-angle lens feel. Subtle, natural handheld shake maintains center framing on the subject with zero cuts.
LIGHTING & PALETTE
Soft overcast daytime lighting with subtle urban reflections from surrounding glass. Color palette emphasizes black, maroon, silver, and cool gray tones.
AUDIO
Upbeat urban hip-hop music with a steady bassline. The woman's lips clearly sync to lively, rhythmic pop-rap vocals.
AVOID
Morphing limbs, unstable facial features, camera cuts, overexposed lighting, shifting wardrobe details.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Photorealistic sunny action commercial
SCENE
Young Asian woman with long dark hair wearing a white two-piece bikini. A tropical outdoor water park resort featuring tall palm trees, white canopy tents, and a tall blue and yellow spiral water slide. A course of colorful inflatable stepping pads spans a bright blue pool.
SHOT BREAKDOWN
0-4s — Wide shot establishing the obstacle course. The woman leaps from a raised platform onto green and yellow floating pads. A large red inflatable in the foreground clearly reads "GOAL".
4-8s — Camera pushes in quickly. Symmetrical water jets erupt from black pipes along the pool edges, creating a dynamic spray archway. The woman balances on a yellow pad.
8-12s — Medium shot. She navigates the water arch, laughing with arms extended for balance as the heavy spray hits her face and torso.
12-15s — She steps onto the red "GOAL" pad, loses her footing, and plunges into the bright blue water, leaving a large white splash ring.
CAMERA
Smooth continuous dolly forward tracking the subject's run. Starts wide to establish the park geometry, transitioning to a medium action shot focused on her reactions.
LIGHTING & PALETTE
Bright midday sunlight casting hard shadows. High contrast and highly saturated primary colors emphasizing the vivid blue pool, yellow inflatables, and the bright white bikini.
AUDIO
Energetic summer instrumental pop. Ambient rushing water, sudden pressurized hissing from the archway jets, wet footsteps, a heavy splash impact, and joyful laughter.
AVOID
Overcast skies, slow motion, motion blur, distorted text, missing water reflections.
Charming Portrait at Serenity Cafe `reconstructed`
15s16:9
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic photorealism, modern lifestyle portrait
SCENE
Young East Asian woman, long straight black hair, bangs, wearing a strapless pale pink floral dress. Upscale lounge and cafe featuring a coffee bar, a curved white sofa with purple and pink pillows, an illuminated pastry case, and a window reflecting interior light.
SHOT BREAKDOWN
0-4s — Medium close-up. The woman leans forward on the sofa, speaking directly to the camera with a bright smile. The coffee bar is softly out of focus behind her.
4-8s — Medium shot. She holds a thick open book in front of a dark window, looking up from the pages to talk directly to the lens.
8-12s — Medium shot. Back in the main lounge, leaning on the sofa. A pink neon sign reading "Serenity COFFEE & BLOOM" and a glowing neon archway illuminate the background.
12-15s — Close-up. The framing tightens as she smiles softly and continues speaking, with a lit pastry display case visible behind her.
CAMERA
Shallow depth of field, 50mm prime lens portraiture. Eye-level framing. Static camera with subtle handheld breathing. Direct subject-to-lens address. Abrupt jump cuts between distinct background angles.
LIGHTING & PALETTE
Warm ambient interior lighting mixed with vibrant practical neon. Soft, flattering frontal key light on the face. Palette dominated by warm gold, magenta, pale pink, and deep plum.
AUDIO
Subtle cafe ambience, gentle lo-fi background track. Clear female spoken dialogue; lips move continuously in direct address.
AVOID
Harsh directional shadows, camera panning, extreme wide shots, distorted typography, breaking eye contact.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D anime, cinematic rendering, photorealistic lighting
SCENE
Anime girl with silver twin-tails, pale skin, and large blue eyes. She wears a deep burgundy velvet dress with ruffled trim, red hair ribbons, and dark boots. The background shifts between three distinct, empty environments: a vintage theatre, a modern mall, and a gothic conservatory.
SHOT BREAKDOWN
0-4s — Full shot. The girl stands in an empty theatre with rows of red seats, turning her head.
4-8s — Close-up profile of her face. Cut to a medium shot from behind, showing her looking out over an empty, multi-level shopping mall atrium.
8-12s — High-angle full shot inside a gothic stone greenhouse surrounded by blooming flowers. Cut to a medium shot from behind in the same location.
12-15s — Close-up of her face looking downward with a soft expression. Cut to a macro shot of her hands in ruffled sleeves delicately reaching for pink flowers.
CAMERA
Smooth, slow-paced tracking and panning. High-quality lens feel with shallow depth of field in close-ups. Pacing uses sharp, deliberate cuts between the vastly different environments.
LIGHTING & PALETTE
Strong volumetric god-rays piercing through windows and dust. High contrast atmospheric light. Palette relies on deep burgundy, cool silver, warm golden sunlight, and rich natural floral tones.
AUDIO
Quiet, echoing ambient space, soft footsteps, gentle classical piano score. Light fabric rustling.
AVOID
Other characters, dialogue, fast-paced action, on-screen text, harsh artificial lighting.
DV 16mm camcorder vlog with soft VHS tape quality, handheld POV by CHASE and mirror-mounted vanity shots. CHASE, a Korean idol in her 20s with long black hair and dewy skin, casually picks up the fictional Lumina Velvet Lip Tint (frosted pink tube, gold cap) at a mall beauty store, saying, "Okay, everyone's talking about this shade." She heads home, opens and swatches the lipstick, applies it smoothly in warm vanity lighting, admires the glossy finish, smiles at the mirror, then looks into the camera for a glowing close-up reveal and says, "Okay wow... Lumina Velvet Lip Tint, you've got a new fan."
Use the uploaded image as the exact source image and first frame. Preserve the original character design, composition, face, pale skin, glowing icy blue eyes, braided black hair, cybernetic head implants, exposed mechanical neck and chest structure, white and cobalt-blue jacket, blue serpentine mechanical creatures, labels, symbols, and the clean white background. Keep the result extremely faithful to the original illustration. The animation should feel like the original artwork has come alive, not been redesigned. Create a premium, stylish, high-end anime animation with a refined cyberpunk aesthetic. The overall impression should be elegant, cold, hypnotic, dangerous, and visually luxurious. Emphasize precise Japanese anime craftsmanship: crisp linework, beautiful cel shading, highly detailed mechanical rendering, controlled highlights, graceful motion, and strong temporal consistency. The animation should look polished, expensive, and intentional. The central character remains calm, dominant, and nearly still. She faces forward and maintains an unwavering, piercing gaze directly into the camera. Her expression is cool, emotionless, intelligent, and slightly predatory. Avoid exaggerated acting. Only subtle micro-movements are allowed in her eyelids, breathing, neck posture, and facial tension. Her presence should feel powerful even in stillness. The main animated elements are the multiple blue mechanical serpents surrounding her. They move with smooth, layered, snake-like elegance. Each serpent has slightly different timing, path, and rhythm, so the movement feels organic and sophisticated rather than synchronized. Their bodies undulate in natural S-curves with believable weight, inertia, and continuous motion. Some serpents slowly raise their heads, some glide across her shoulders and around her face, some tighten or loosen their coils, and some subtly cross behind or in front of the composition to reshape the frame. Their movement should feel alive, hypnotic, and controlled, never frantic. Preserve the segmentation, scale texture, metallic fittings, joints, and cable-like details. Small articulated components should shift with delicate mechanical precision. Her long green tongue moves like a real serpent tongue but remains elegant and stylized. It slowly extends, retracts, and sways with controlled, organic softness. The forked tip performs subtle tasting-the-air flicks. The tongue should feel eerie, sensual, and mesmerizing, never comedic. The tongue motion should complement the serpents’ motion, acting like a focal accent that draws attention toward her mouth and face. Add subtle secondary motion throughout the scene. Her shoulders and upper torso rise and fall gently with slow breathing. Tiny motions should ripple through the hood, jacket folds, loose blue fabric, fine cables, and a few hair details. The exposed mechanical chest and neck assembly should feel alive through micro-movements: slight cable tension shifts, minute piston adjustments, tiny joint rotations, and restrained vibration. These details must remain subtle and tasteful, never distracting from the face and serpents. Lighting should remain clean and striking. Preserve the white background and the strong graphic contrast between the white, cobalt blue, black mechanical detailing, and neon green tongue. Let reflections glide softly across the blue serpents’ scales and metallic joints. Metallic parts in the neck and chest may shimmer subtly. The green tongue should remain a vivid accent with slight wet gloss or faint luminous emphasis. Maintain a polished illustration-like finish while introducing dimensionality through moving highlights and soft shadow transitions. The camera should perform an extremely slow and smooth frontal dolly-in over the full 15 seconds. The framing begins as a stable medium close-up and gradually becomes slightly tighter and more intense. The camera should never move abruptly. No shake, no tilt, no sudden zoom, no spinning, and no dramatic reframing. The face, eyes, and tongue should become increasingly dominant as the sequence progresses, while the surrounding serpents continue to frame the composition. The movement of the camera should feel cinematic and hypnotic, reinforcing tension through slow approach. Structure the motion over the 15-second duration with deliberate pacing: Seconds 0–3: begin in near stillness. Only the faintest breathing, tiny hood and cable motion, and a barely perceptible serpent twitch. Establish tension and the character’s unwavering blue-eyed stare. Seconds 3–6: the serpents begin to awaken. One or two serpents slowly lift their heads and start gentle undulating motion. Reflections start traveling across their blue surfaces. The tongue begins a slight side-to-side sway. Seconds 6–9: more serpents join the motion. The body language of the serpents becomes richer and more layered, circling her shoulders and face with elegant S-curve motion. The tongue extends a little farther and retracts slowly, with subtle fork-tip flicks. The camera continues its slow push inward. Seconds 9–12: reach the most hypnotic phase. The serpents are now fully active but still graceful and controlled, framing her face dynamically. Their movement should feel luxurious and predatory. The tongue performs its most visually striking serpent-like motion here, synchronized with the heightened tension. Highlights glide across scales and metal details. Her gaze remains locked and emotionally unreadable. Seconds 12–15: sustain and slightly resolve the intensity. The serpents continue moving but begin to feel more settled, as if entering a poised equilibrium. The camera reaches its closest framing, emphasizing her eyes and green tongue while still preserving enough serpents in frame for visual impact. End on a powerful, composed, hypnotic final moment that feels elegant and complete. The emotional tone should be futuristic, eerie, sensual, intelligent, and luxurious. The final result should resemble a high-budget anime opening shot or a premium animated key visual. Prioritize elegance, polish, and controlled visual storytelling over excessive motion. Every motion should feel deliberate and aesthetically composed. Maintain strict model fidelity and visual stability. Do not alter the character’s face shape, eye design, hairstyle, skin tone, clothing, mechanical anatomy, serpent design, or color palette. Do not add new objects, extra serpents, extra tongues, extra limbs, or background elements. Do not morph the face or let the eyes drift. Do not let the serpents fuse together unnaturally or intersect in broken ways. Do not allow clipping through the body or clothing. Do not change the jacket symbols or graphic details. Do not shift into 3D, live action, or a different illustration style. Avoid flicker, line wobble, perspective drift, detail melting, unstable anatomy, scale inconsistency, random deformation, abrupt motion, or composition changes.
Style: dark-rap -rap music video with photoreal high-fashion polish and the texture of a scanned film magazine—high contrast without looking cheap. film scans, underground-music posters, and zine collage. Add coarse grain, subtle gate weave, halftone dots, rough print edges, and slight scan misregistration. Keep the edit fast and use hard cuts only—no fades or soft transitions. Match the typographic treatment and surface texture of the reference images.
Make an MV from Audio1 . Show these Kpop members from Image1 singing and dancing to the music. Add coarse grain, glitch effects, and grunge effects. Keep the edit fast and use hard cuts only—no fades or soft transitions. Cuts should occur within 3 seconds. Make the cuts based on the beat of the song. Use the typographic reference from Image2
VIDEO PROMPT — "Pizza Night Vlog" (UGC iPhone Style)
Duration: 15 seconds | Aspect Ratio: 16:9 | Style: Authentic UGC / iPhone selfie-vlog, handheld, natural light, slight motion blur, TikTok/Reels energy — NOT cinematic, NOT overly polished. Feels like a real creator filmed this on their phone.
Product Reference: Use the uploaded Domino's Pepperoni Pizza image as the only product reference. Keep crust thickness, cheese texture, bake color, pepperoni placement, and proportions identical in every cut — no redesigning the pizza.
Camera: iPhone 15 Pro front + back camera switching, handheld, natural wobble, autofocus hunting slightly (realistic), vertical-style framing cropped to 16:9, occasional finger near lens edge, natural room lighting + phone flash reflections on the pizza box.
Character Description
Name (for reference): Mia
Awoman in her mid-20s, naturally attractive and beautiful with an approachable, girl-next-door charm — not overly done up. Wavy sandy-blonde hair pulled back loosely, light natural makeup, wearing a cozy oversized cream sweater. Warm, genuine smile, expressive eyes, casual energetic personality like a real lifestyle vlogger. Sits in a softly lit modern kitchen/living room.
Shot Breakdown
SHOT 1 (0–2s) — The Grab
Selfie-angle, she's mid-laugh holding up the Domino's box to camera. Quick jump cut. Dialogue: "Okay so it's officially pizza night—"
SHOT 2 (2–4s) — The Open
Cut to overhead handheld shot, box flips open, steam rising off the pizza, slight camera shake as she leans in.
SHOT 3 (4–6s) — The Zoom
Quick zoom-punch into the pizza, phone camera autofocus adjusts naturally, cheese and pepperoni in focus, ambient kitchen sounds.
SHOT 4 (6–8s) — The Pull
Cut to her hands lifting a slice, natural cheese pull, filmed from a slightly low candid angle like a friend filming across the table.
SHOT 5 (8–10s) — The Reaction
Cut back to selfie-cam, she takes a bite, eyes widen, quick genuine reaction. Dialogue: "Oh my god, that's so good."
SHOT 6 (10–12s) — The Candid Cutaway
Jump cut to a close, slightly shaky shot of the pizza box on the counter, her hand grabbing another slice off-frame, casual b-roll energy.
SHOT 7 (12–14s) — The Wrap-Up
Back to selfie angle, she grins at camera, holding slice up like a toast. Dialogue: "Dominos, y'all know what to do."
SHOT 8 (14–15s) — End Tag
Quick freeze/cut to the box logo close-up, natural handheld wobble, soft text overlay in casual font: "pizza night = solved 🍕" — cut to black.
Look & Feel
Warm indoor lighting, slightly grainy natural phone sensor look, imperfect framing, real reactions, minimal dialogue (3 short lines total), authentic pacing with hard jump cuts instead of smooth transitions.
Negative Prompt
cinematic grade, overly smooth camera moves, studio lighting, professional voiceover, staged acting, CGI look, plastic cheese, distorted pepperoni, extra fingers, warped hands, text glitches, logo distortion, overly polished commercial feel.
Elf Girl Transforms into Biomechanical Armor (Local ComfyUI)
15s16:9
prompt:
r34l1sm
subject_definitions:
<Subject 1> is the same character throughout the transformation. <Picture 1> defines her blonde hair, pointed elf ears, black eyepatch covering her anatomical left eye, dark navy jacket with black sleeves, black gloves, fitted black armored trousers, and combat boots. Adapt her face toward a natural East Asian appearance: a gentle oval contour, softly defined cheekbones, almond-shaped eyes with subtle eyelid creases, a moderately low nasal bridge, and a softly rounded nose tip. Preserve individual facial proportions and natural skin texture.
<Picture 2> defines her completed form from head to feet: ivory-gray biomechanical armor, a broad angular skull-like helmet, rib-shaped chest plates, dark organic structures between perforated plates, articulated clawed hands, armored thighs and shins, segmented ankles, and elongated armored feet with distinct clawed toes. Use both images for appearance only; exclude their white backgrounds, multiple views, and portrait panels.
summary:
[reference generation] A 15-second Hollywood science-fiction transformation in one uninterrupted shot. <Subject 1> stands at the outermost edge of a skyscraper beneath heavy daytime storm clouds, facing outward toward the street throughout. The camera moves from an elevated rear view into a facial close-up, then tracks downward following the transformation from head to feet. A blue magic circle on her eyepatch continuously releases black smoke and luminous blue particles until her entire body transforms into the form from <Picture 2>. She finishes in a natural deep crouch, both hands grounded between her legs, looking straight ahead over the street.
retention_analysis:
<Subject 1> (throughout [Shot 1]): partially_preserved — preserve the initial hairstyle, ears, eyepatch, clothing, and proportions from <Picture 1>, adapting her face toward the East Asian appearance defined above. Maintain that face until the helmet encloses it. Transform every region, including both boots, into the complete design from <Picture 2>. Preserve rooftop geography, supported foot contact, and the same outward facing direction throughout.
detailed_description:
Hollywood feature-film science fiction with photorealistic materials, precise camera choreography, deep directional shadows, and layered volumetric smoke. Daytime beneath dense gray storm clouds, with readable buildings and streets. Use explicitly positioned directional daylight and rooftop practical lights. No world light, ambient dome illumination, or uniform environmental fill.
[Shot 1] One uninterrupted 15-second take with a consistent 35mm cinema-lens perspective. Her feet, pelvis, chest, and head remain oriented outward toward the street beyond the rooftop edge throughout. Only the camera changes position; she never rotates to follow it or faces the rooftop interior.
During approximately zero to three seconds, begin above and behind <Subject 1>'s right shoulder, looking steeply down past her boots toward the street. Both feet stand fully supported at the concrete rooftop's outermost edge, toes aligned with its exterior boundary. No railing separates her from the drop.
Smoothly descend and arc around her right side into open air above the street, arriving in a tight frontal three-quarter facial close-up looking back toward her, with the rooftop behind her. Directional daylight through a cloud opening defines her hair; a maintenance fixture provides neutral-white side light, and an aircraft-warning fixture adds a faint red rim. Keep these sources fixed. Intense blue light builds beneath her opaque eyepatch, illuminating adjacent skin. Her uncovered eye remains unchanged.
During approximately three to five seconds, <Subject 1> (S1), with a calm, low female voice, says, <d>[Japanese] もう、眠らなくていい。</d> Speak softly and deliberately, briefly pausing after “もう,” with synchronized lips, relaxed shoulders, and a steady forward gaze.
As the line ends, a blue magic circle inscribes concentric rings, geometric lines, and tiny arcane glyphs directly onto the eyepatch's curved surface, contained within its boundary. Dense black smoke interwoven with luminous blue particles continuously pours from beneath its edges. Particles illuminate curling turbulence from within before drifting outward.
During approximately five to seven seconds, physically descend and gently tilt downward, following the smoke through her neck, shoulders, and chest. Biomechanical structures emerge and rib-shaped plates interlock. Gaps keep the changing surfaces visible.
During approximately seven to nine seconds, continue across her abdomen, hands, hips, and thighs. Clothing dissolves, gloves disappear, fingers extend into articulated claws, and ivory-gray armor forms over dark organic structures.
During approximately nine to eleven seconds, track down both knees, shins, ankles, and feet. Clearly show both boots disintegrating completely: shafts, laces, toe caps, heels, and rubber soles disappear. Segmented ankle armor connects into elongated clawed feet matching <Picture 2>. Both feet remain supported on the same concrete area, with toes still pointing outward toward the street.
The eyepatch continuously emits throughout this downward movement, including when above the frame. The helmet forms around her head while leaving the emitting eyepatch exposed until every other region is complete.
During approximately eleven to twelve seconds, smoothly retreat and tilt upward into a full-body composition. Reveal the final helmet plates enclosing the eyepatch, completing the transformation and stopping emission.
During approximately twelve to fifteen seconds, she naturally lowers into a deep crouch without changing her facing direction. Her hips shift slightly backward for balance, knees bend and open in line with her feet, and her torso inclines forward. Both arms relax between her thighs. Clawed fingertips contact the concrete first, followed by palms taking part of her weight between her feet, fully inside the rooftop boundary. Elbows remain softly bent.
Gently decelerate into a stable four-point stance with a subtle final balance adjustment. Keep both grounded hands and transformed feet visible. Her chest remains directed toward the street; her helmet stays raised and her gaze fixed straight ahead toward the distant city at eye level. Residual smoke disperses only after transformation is complete, and blue particles fade. No cuts, flashes, camera jumps, or full-frame smoke concealment.
overall_soundscape:
Rooftop wind, distant traffic, and low thunder persist. Wind and electrical hum soften beneath the Japanese dialogue. The magic circle sustains a fine resonance throughout emission, accompanied by smoke hissing, particle crackling, armor scraping, and locking clicks. Subtle joint sounds and fingertip-to-palm contact accompany the natural descent into the crouch.
non_diegetic_music:
A low sustained synthesizer tone rises during transformation, remaining quiet beneath dialogue. One deep percussion impact accompanies the completed helmet, followed by a fading low resonance beneath the final grounded stance.
SCENE CONTEXT A middle-aged man stands in the middle of a dirt road in open desert and holds a pistol level at the person filming him. He gives an instruction, is answered by name, and warns them not to say it again. Nothing is fired.
TIMELINE 0.0–3.0s — he is already aimed and steady; his first line lands. 3.0–6.0s — the off-frame reply uses his name; his jaw sets and the muzzle does not drop. 6.0–9.0s — his second line; he takes half a step forward and re-sights. 9.0–11.0s — the off-frame voice starts his name again and stops. 11.0–15.0s — his last line; wind lifts dust across the road behind him; he holds the aim. Hold to black-free end.
ACTIVE REFERENCES No image or video references are active in this shot. Build the man from description only. Man, fifties, white, average build, standing, thinning brown hair, a brown moustache, thin-rimmed prescription glasses; light green long-sleeved button-down shirt with the sleeves buttoned at the wrist, dark work trousers; stern, brow furrowed, sweat starting at the hairline; frightened underneath and controlling it; speaking voice flat, plain, mid-western American, no theatricality. Second speaker: the unseen person the pistol is aimed at, occupying the camera position, never entering frame and never seen. Voice only — male, forties, close to the lens, low and careful.
LOCATION MAP Camera on the dirt road 3.5 m from him at his chest height, facing him square-on so the muzzle is aligned with the lens axis. FG: rutted dirt and loose gravel across the lower frame. MG: the man alone, centre frame. BG: the dirt road receding to a vanishing point at x 50%, y 44%, low scrub and dry brush from x 0% to x 30% and x 70% to x 100%, a distant fence line at x 62%, y 48%, flat desert horizon at y 46%, overcast sky filling the upper half with one pale blue break low at x 24%, y 36%. He occupies x 50%, y 50%, body frontal, both feet planted, right arm extended toward camera with the silver pistol at x 50%, y 56%, held at the very front of the depth plane. His eyeline is straight down the lens. The first visible frame already has him aimed and in position — no empty establishing frame, no walk-in, no delayed reveal, and he remains the only figure in frame for the entire take.
FORMAT MODE Single continuous take, no internal cuts, no transitions, no fades. Real-time motion. His lines are on camera; the second voice is an intentional off-frame speaker at the camera position. No other voices, no narration, no subtitles, no score.
CAMERA 47° diagonal field of view, camera 3.5 m from him at chest height, natural human-eye perspective, no distortion, natural face and body proportions, the road and horizon readable behind him, comfortable depth of field with the pistol slightly forward of his focal plane. Handheld, shoulder-mounted mass, operator breath and small involuntary settling — the camera is being held by the person he is aiming at, so it flinches minutely rather than gliding. Total travel under 20 cm, no push-in, no zoom, no focus rack. Focus holds his eyes behind the glasses; the pistol stays just soft.
ACTION TIMING He is already sighted along the barrel as the shot opens and speaks without lowering it. The off-frame voice answers with his name; his jaw sets and the muzzle does not waver. He speaks his second line and takes half a step forward on the dirt, re-sighting as his weight lands. The off-frame voice begins his name again and stops. He delivers his last line, and wind lifts a curtain of dust across the road behind him. He holds the aim to the end without firing and without lowering the weapon.
PHYSICS The pistol carries real weight — his wrist and forearm show the load and micro-correct continuously; the muzzle drifts a few millimetres and is pulled back on line. His half step lands heel-first in soft dirt with visible weight transfer and a small dust puff that drifts and thins. Shirt fabric pulls across the extended shoulder and creases at the elbow. Wind moves the loose dust and the dry scrub in the same direction and at the same time. Thinning hair lifts and settles with the gust. Sweat beads at his temple and does not run.
LIGHTING Primary source is the full overcast sky acting as one enormous soft toplight, giving even illumination with minimal harsh shadow — a soft shadow under the brow and the nose only, no hard edges anywhere. Secondary is dry ground bounce filling under the chin and lifting the shadow side of the pistol. Both lenses of his glasses carry a broad soft reflection of the sky, and his eyes stay readable behind them. Exposure is set for his face; the sky sits bright but not clipped. No sun shaft, no lens flare, no added key, no light change during the take.
AUDIO Dry wind across open ground, loose grit moving on the road, dry brush ticking, one distant bird, his own breathing close and unsteady. Ambient ducks under the voices. Exactly this exchange, flat and plain, no shouting — 25 words total: HIM: "Put it on the ground. Slowly." OFF-FRAME: "You're not going to shoot me, Ray." HIM: "I've been wrong about myself before." OFF-FRAME: "Ray—" HIM: "Don't say my name again." His first line opens the shot. The off-frame reply lands as his jaw sets. His second line comes as he takes the half step. The off-frame "Ray—" is cut off by his last line, which is quieter than everything before it. His lips move only for his own lines; there is no dialogue in the pauses and no muttering between beats.
POSITIVE LOCKS Exactly one visible person is in frame for the whole take — nobody enters at any edge, no second figure appears on the road, at the fence line or in the reflections on his glasses, and the off-frame speaker is never seen. The pistol stays in his right hand, stays aimed at the lens, and is never fired, never lowered and never re-holstered; no muzzle flash, no recoil, no gunshot. He stays on the road and never turns away from camera. Naturalistic muted palette of dry greens and browns against pale overcast grey. Live-action photoreal footage shot on ARRI Alexa 35, tense neutral mood, natural film grain.
16:9, 15s, hyper-realistic Korean noir crime teaser.
A rain-soaked Korean woman (late 20s, trench coat) enters an abandoned underground nightclub searching for her missing sister. A scarred crime boss (40s), presumed dead for years, emerges from the shadows with a lit cigarette. Atmosphere: 90s Korean noir, practical neon, rain, smoke, film grain, tactile realism, no CGI gloss.
Shots:
1. She enters: "언니... 여기 있어?"
2. Lighter ignites, revealing his scar. "오랜만이네."
3. She freezes: "당신... 죽은 줄 알았는데."
4. Slow push-in. He smiles: "네 언니가 날 죽였다고 생각했겠지."
5. They lock eyes. Thunder. Cut to black.
Audio: Rain, thunder, jazz crackle, lighter click, intimate silence during dialogue.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic drama, emotional cross-cutting dialogue
SCENE
A distressed woman with an updo wearing a beige turtleneck sweater and holding a dark coat in an airport terminal gate at night. A somber man in a grey t-shirt inside a dimly lit kitchen with rain-speckled windows.
SHOT BREAKDOWN
0-4s — Medium shot of the woman standing among rows of empty blue airport seats, speaking anxiously on her phone.
4-8s — Cut to a medium shot of the man leaning against a kitchen counter, listening solemnly on his phone.
8-12s — Cut to a tight close-up of the woman, teary-eyed and speaking with deep emotion.
12-15s — Cut to a tight close-up of the man closing his eyes with a pained, heartbroken expression.
CAMERA
50mm and 85mm prime lens feel, shallow depth of field, static framing, eye-level medium shots cutting cleanly to intimate close-ups.
LIGHTING & PALETTE
Airport setting uses cool white overhead lighting, dark glass reflections, deep blues, and beige. Kitchen setting features warm pendant lighting, heavy shadows, and amber outdoor bokeh.
AUDIO
Low airport terminal hum, soft ambient drone, distant rain against window glass, quiet emotional phone dialogue.
AVOID
Camera shake, daylight, fast whip pans, exaggerated body motion, upbeat background music.
Two characters arguing in English. Make the emotion feel very realistic angry, tense, the friction between them should be palpable. Shaky handheld camera. No music.
Grounded photorealistic live-action relationship drama, natural 24fps motion.
FORMAT
Two connected 15-second clips, 16:9, grounded photorealistic live-action relationship drama, natural 24fps motion.
SHARED STYLE
A small living room at night. One warm floor lamp mixes with cold blue streetlight through the curtains. A framed wedding photograph hangs behind the couple. Restrained handheld camera, realistic skin and fabric, tense silence, no melodramatic shouting.
CONTINUITY
The husband remains frame left beside the coffee table, holding his wife’s unlocked phone containing the evidence. The wife remains frame right near the window. Preserve their faces, clothes, positions and screen direction across every cut.
CLIP 1 — THE CONFESSION
0.0–5.0
Camera: Slow 35mm push toward both characters.
Action: The husband stares at the phone, then raises his eyes toward her.
HUSBAND: “How long has this been going on?”
5.0–8.0
Camera: Cut to a restrained 50mm close-up of the wife.
Action: She cannot meet his eyes. After a short pause:
WIFE: “Six months.”
8.0–15.0
Camera: Close on the husband. His grip tightens around the phone, but he controls his voice.
HUSBAND: “Six months? I gave you twelve years. Why?”
Final frame: The wife finally looks directly at him, preparing to answer.
CLIP 2 — THE REASON
Begin from the exact positions and expressions inherited from Clip 1.
0.0–6.5
Camera: Slow push toward the wife as she folds her arms defensively.
WIFE: “Because I’m tired of being broke. Every dream with you becomes ‘maybe one day.’”
6.5–10.0
Camera: Cut to the husband. His anger gives way to disbelief.
HUSBAND: “So you chose him for his money?”
10.0–15.0
Camera: Return to the wife. She holds his gaze without apologizing.
WIFE: “I chose someone who can give me the life I want.”
Final frame: Hold on the husband as the meaning lands. His hand lowers, and the phone slips onto the sofa.
Use the supplied image as the exact opening frame. Create a hilarious, high-budget 1980s live-action family comedy movie scene, photographed on a real soundstage with practical robot costumes, animatronics, handmade props, vintage wardrobe, and authentic 35mm film color.
The entire group suddenly hears something above them. Everyone’s eyes dart upward at the same moment. The men, women, children, and robots dramatically tilt their heads back, point toward the ceiling, and erupt into chaotic celebration. They gasp, scream, laugh, jump, wave their arms, slap each other on the shoulders, and completely lose their minds with exaggerated 1980s comedy reactions. The children bounce excitedly. The adults stumble into one another. The robots flash their eyes, flap their mechanical arms, spin clumsily, and celebrate with funny practical animatronic movements.
One man shouts:
“OPEN SOURCE?!”
The entire crowd answers together:
“MINIMAX H3!”
They cheer wildly as one robot attempts a victory dance, loses its balance, and is caught by the shocked family at the final second.
Fast, energetic comic timing with believable ensemble choreography. Begin with a brief locked group shot, then a subtle handheld push-in as the chaos escalates. Keep every original person, robot, shirt design, and the large headline clearly recognizable. Preserve facial identity, wardrobe, composition, lighting, and 1980s production design.
Authentic optical softness, warm tungsten lighting, rich film grain, slight gate weave, practical effects, natural motion blur, expressive physical acting, polished studio-comedy sound mix, triumphant synthesizer sting, cheering, robot beeps, and comedic percussion.
No CGI, no digital-looking robots, no morphing, no extra people, no duplicated characters, no distorted faces, no rewritten text, no spelling changes, no modern clothing, no style shifts, and do not turn the scene into animation.
Style: <image_1> (don't reproduce the image, use it only as aesthetic reference)
Edit: Comedy, fast paced, mixing close ups, medium shots and wide shots from uncanny and tilted angles. Super-imposed texts with doodles identify ingredients as they appear and add comic remarks.
Scene: In Porto, Portugal a crazy chef explains how to do a Francesinha in Portuguese from Portugal with Porto accent."
Create a 15-second, vertical 9:16 Japanese 2D anime action-comedy with synchronized Japanese dialogue, music and sound effects.
REFERENCE BINDING
Character A = character reference image 1: long black hair, teal outfit. Match her attached face, hairstyle, costume, colors, accessories, proportions and drawing style exactly. She summons the meteor and takes the final comic hit.
Character B = character reference image 2: white bob haircut, purple outfit. Match her attached design exactly. She calmly shrinks the meteor and flicks it back.
Use character images for identity and art style only. Create new poses, expressions, staging and background; do not reproduce reference-sheet layouts. Keep the two designs separate and consistent in every shot.
A speaks only with voice reference audio 1. B speaks only with voice reference audio 2. Preserve each voice's identity, timbre, pitch range and delivery characteristics while changing emotion naturally. Use the audio clips as voice references, not as dialogue scripts. Never swap voices. Animate accurate Japanese lip sync only for the active speaker.
VISUAL STYLE AND STAGING
Film-quality hand-drawn 2D anime, clean linework, expressive faces, rich cel shading, fluid character animation and cinematic effects. Everything, including the meteor and environment, shares the same anime style. No photorealism or 3D-rendered appearance.
Exactly two characters in one deserted stone courtyard at dusk. A stays screen-left, B screen-right, about two meters apart. Maintain this geography and screen direction throughout. Use vertical depth: the enormous meteor dominates the upper frame, with both characters clearly staged below. Their outfits and hair react naturally to wind.
The comedy comes from A's apocalyptic seriousness versus B's almost bored confidence. Play the opening as a convincing disaster scene. Reveal the joke through physical action.
TIMELINE
0.0-3.5s — THE END OF THE WORLD
Start immediately on a dramatic low-angle wide shot. A thrusts one hand upward. One colossal, glowing meteor breaks through swirling clouds, filling most of the sky. Its cracked rocky surface, molten fissures and fiery trail are clearly visible. A pressure wave lifts dust and small pebbles; red-orange light washes across both characters. The meteor approaches slowly enough for the next action to read.
A declares with absolute confidence: 「これで終わりだ！」
B remains grounded and unimpressed at screen-right. Do not reveal the shrinking trick yet.
3.5-4.8s — AN ORDINARY GESTURE
Cut to a three-quarter view of B with the meteor still clearly visible overhead. She looks up with a flat expression and says quietly: 「大きすぎ。」
She raises her right hand toward the meteor and spreads her thumb and index finger, framing its visible outline as if preparing to pinch an image smaller on a phone. Her other fingers curl naturally. There is no phone and no interface.
4.8-8.5s — PINCH THE APOCALYPSE
Cut to a locked over-the-shoulder composition that clearly shows B's right thumb and index finger in the foreground, with the meteor between them in the sky.
Show the ENTIRE shrinking action in this single uninterrupted shot. As she brings those two fingertips together, the actual meteor continuously shrinks in direct response. Its center remains visually aligned with the narrowing gap between her fingers. It smoothly contracts from a sky-filling catastrophe to a small rock, then to a pea-sized pebble.
The same meteor is magically drawn toward her hand as it shrinks, finally settling between her fingertips. Preserve its recognizable cracked shape and fading orange fissures through the transformation. The flame trail contracts with it, then vanishes. Its glow fades until it is a harmless dark pebble.
Keep camera position, lens, background scale and character scale fixed during the shrink. The object itself changes size; this is not a camera zoom or a perspective illusion. Do not cut away, conceal the transformation or substitute a second meteor.
The sky brightens naturally as the meteor stops blocking it. Wind, ground vibration and orange illumination subside together.
8.5-11.7s — RETURN TO SENDER
Cut to a clear medium two-shot preserving A on the left and B on the right. B lowers the same hand with the same tiny meteor. A is still holding her grand victory pose, now visibly confused.
B casually sends the pebble toward A's forehead with one small finger flick. Show a short, readable right-to-left flight and one harmless forehead tap. No second rock, beam, explosion or renewed enlargement.
On contact, use a tiny, dry 「ペチッ」 sound effect, heard only, never written. A flinches slightly. B stays completely deadpan. No extra dialogue here.
11.7-15.0s — THE AFTERMATH
Cut close on A's face. After a brief stunned pause, she quietly says: 「……痛っ。」
She touches the exact spot on her forehead. Her triumphant expression collapses into blank disbelief: raised brows, slightly parted lips, eyes struggling to understand what just happened.
Use a gentle final push-in on A, then hold her awkward expression for the final full second. End on her face, not on B and not on the sky. No additional gag, explanation or end card.
SOUND AND PRIORITIES
Begin with thunderous meteor rumble and dramatic orchestral tension. During the pinch, smoothly reduce the rumble's scale and intensity into a tiny fading whistle. Stop the epic music completely by the end of the shrink. Let the little tap, A's subdued reaction and the awkward quiet carry the ending. Keep all Japanese dialogue clear above the effects.
Priority order: reference identity and voice binding; readable uninterrupted shrinking; same-pebble continuity; final reaction timing.
No narration, subtitles, captions, speech bubbles, readable text, logos, watermarks, HUD, phone screen, touch icons or graphic overlays. No additional people, duplicate characters, fused designs, extra fingers, costume changes, giant impact, injury or scene change.
Massage Critical Hit −9999: Vertical Slapstick Short (3-Model Comparison)
15s16:9
Seedance2.5 VS WAN 3.0 VS MiniMax H3
同一段15秒的提示詞, 究竟三個唔同的AI 模型怎樣理解同演繹它呢?
大家可以看看以下的短片. 及提示詞去比較及感受一下.
TopView 年Plan: 720P 15 sec 成本:
SD2.5: HKD17.5, WAN 3.0: HKD8.75 , MiniMax H3: HKD3.5
A 15-second high-energy slapstick comedy video with a handheld smartphone aesthetic, 9:16 vertical frame.
[0-4s] In a cozy living room, AhKit sits on the sofa rubbing his sore neck. Mia stands behind him, smiling angelically at the camera while playfully rubbing her small fists together. Subtitle: "When she offers a massage..."
[4-9s] Snap zoom. Mia cheerfully taps her small fist onto AhKit's shoulder. Sudden dynamic shockwave impact: AhKit's eyes bulge out in dramatic exaggerated horror, his body recoils violently, and he collapses off the sofa onto the floor in hilarious defeat. Subtitle: "CRITICAL HIT! -9999"
[9-15s] Low-angle tracking shot. Mia's sweet face turns into a sinister, villainous mischievous smirk. She grabs AhKit by one ankle with one hand and effortlessly drags him across the wooden floor toward a bedroom doorway. AhKit lies face down, frantically clawing the wooden floor with both hands like a terrified cat refusing to go into the room, legs sliding helplessly. Subtitle: "Ah Kit: Help... ...!"
One-Take Outfit Morph on a City Street `reconstructed`
15s16:9
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Fashion editorial morphing sequence
SCENE
Female model with a buzz cut and gold hoop earrings, holding various handbags. Busy metropolitan street, red double-decker buses, white delivery van, street lamps, traffic lights, pedestrian extras, shop fronts, metal scaffolding, sidewalk paving stones.
SHOT BREAKDOWN
0-4s — Model walks confidently forward on a crosswalk, wearing a rust-colored suit. The outfit seamlessly morphs into a black silk slip dress with strappy heels. Framed center.
4-8s — Striding along the sidewalk, her clothing transforms into a cream trench coat with matching loafers. It quickly shifts again into a gradient blue-to-yellow denim jacket and jeans with a lime green purse.
8-12s — The outfit changes to a classic blue denim jacket and wide-leg jeans, then morphs into a bright red silk v-neck dress and red heels. A red bus passes behind her.
12-15s — Her attire transforms into a heavy grey tailored coat over black boots. Finally, it morphs into a black leather trench coat. She halts her walk, standing still for the final seconds.
CAMERA
Eye-level focal length. Smooth tracking shot moving continuously backward to match her walking pace. Center-framed full body composition. Single uninterrupted take.
LIGHTING & PALETTE
Direct, harsh midday sunlight. High contrast with deep, defined black shadows cast directly onto the pavement. Palette features vibrant reds, bright sky blue, and stark contrast between the changing outfit colors and neutral grey concrete.
AUDIO
Urban street ambience. Rumble of heavy bus engines, faint pedestrian murmurs. Sharp, rhythmic clicking of footsteps. Minimalist, pulsating electronic fashion beat.
AVOID
Cuts, camera shake, inconsistent facial identity, warped architecture, changing environmental lighting conditions.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Y2K editorial music video with dynamic typography and graphic overlays
SCENE
Two young women. One has blonde hair with bangs, wearing a white knit vest, navy sailor collar, and tie. The other has black hair, a black long-sleeve top, black pleated mini skirt, white slouch socks, and black platform loafers. Setting is a plain grey studio backdrop.
SHOT BREAKDOWN
0-4s — Medium close-up of the blonde girl. Overlays include "01", "ON", "06", "NO", "09", "SYS.07.A", and barcodes. Cuts to a full-body shot of the black-haired girl framed by red, black, and white grunge textures.
4-8s — Extreme close-up of the black-haired girl next to white text "HARD CUT". Cuts to both girls back-to-back above a massive red banner reading "BASS DROP".
8-12s — Close-up on legs walking in slouch socks and loafers, layered with text "스타틱 인덱스" and "NOISE INDEX". Cuts to the black-haired girl posing against a black background with radiating white text "MOVE FAST".
12-15s — Split-screen portrait of both girls divided by a torn paper effect. The screen glitches as barcode elements distort and frame their faces.
CAMERA
Fast-paced editorial editing, static locked-off framing mixed with sudden graphic transitions. Sharp, deep depth of field.
LIGHTING & PALETTE
Flat, even studio lighting. Monochromatic base palette of stark white, black, and grey, heavily accented by bright crimson red and navy blue.
AUDIO
Heavy electronic bass beat, digital glitch sound effects, upbeat rhythmic electronic music character.
AVOID
Camera shake, natural environments, shallow depth of field, slow pacing, 3D animation.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D typography VFX montage
SCENE
A rapid sequence of diverse 3D environments where thematic words physically manifest from the surrounding elements, spanning cosmic, apocalyptic, digital, and natural landscapes.
SHOT BREAKDOWN
0-4s — Fiery sparks reveal metallic text "MINIMAX H3 TEXT RENDERING". A volcano and falling meteors solidify into molten text "APOCALYPSE". A glowing DNA strand morphs into a running figure, transitioning to bioluminescent text "EVOLUTION".
4-8s — Spacetime distorts around a black hole, shaping the word "SINGULARITY". A swirling fire vortex solidifies into cracked rock reading "INFERNO". Golden neural threads weave together, exploding with light to form "AWAKEN".
8-12s — A white grid room shatters into flying cubes, exposing a red glitching core and the word "CORRUPT". A heavenly gothic cathedral sprouts wings, displaying golden text "ASCENSION". Creeping smoke in an abandoned hospital hallway forms the wispy word "PHANTOM".
12-15s — A dead tree absorbs glowing green energy, blossoming into floral text "REBIRTH". A top-down view of a dense city collapses inward, throwing up debris around heavy metallic text "COLLAPSE", ending in a dust cloud.
CAMERA
Fast-paced montage, dynamic forward zooms, rapid cuts. Wide-angle perspective morphing seamlessly between intense focal points.
LIGHTING & PALETTE
High contrast, highly saturated. Distinct palettes per shot: fiery orange, deep space blue, stark white, glowing green, and celestial gold. Strong volumetric rays and lens flares.
AUDIO
Heavy cinematic bass drops, elemental whooshes, digital glitching, ethereal chimes, and building orchestral tension.
AVOID
Misspelled text, flat 2D overlays, static framing, low contrast, soft focus.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic tech commercial with dynamic background transitions
SCENE
A blonde woman wearing large over-ear headphones. Her wardrobe shifts from a dark green top to a black jacket, then a beige ribbed sweater. Settings transition rapidly: a plain white room, a neon futuristic city, a concert arena, deep space, and a mountain peak above clouds.
SHOT BREAKDOWN
0-4s — The woman smiles in a plain white room, placing headphones over her ears in a medium close-up. As they fit, the background snaps seamlessly to a vibrant neon cyberpunk city.
4-8s — Framed in profile looking right, she smiles. The background morphs from the neon city into a massive, brightly lit concert arena with a large crowd and stage lights.
8-12s — She gazes upwards as the arena dissolves into a dark cosmos featuring a glowing, swirling galaxy. This transitions smoothly into a twilight mountain landscape.
12-15s — Wearing a beige sweater, she closes her eyes and touches the earcups. The background brightens into a sunrise over a sea of clouds. Centered text appears: Hear Beyond Reality
CAMERA
Smooth, continuous framing. Starts face-on, orbits to a profile angle, and pulls back slightly. Match-cut transitions are driven entirely by the environment morphing around the stationary subject.
LIGHTING & PALETTE
Soft natural lighting shifts to high-contrast neon pinks and teals, bright white concert spotlights, deep cosmic purples, and warm, golden-hour sunlight.
AUDIO
Quiet room tone snapping to energetic synth-pop, transitioning to a roaring concert crowd, deep ethereal drones, and resolving into an uplifting acoustic melody.
AVOID
Visible brand logos, abrupt camera cuts, poorly lit faces, mismatched eyelines, misspelled text.
Infinite Journey of Seamless Transformations `reconstructed`
15s4:3
Duration: 15 seconds | Aspect ratio: 4:3 | Style: Cinematic match-cut transformation sequence, hyper-realistic
SCENE
Young woman, braided crown hairstyle, hazel eyes. Transforming wardrobe: business suit, cyberpunk bodysuit, explorer jumpsuit, winter parka, space armor. Transforming settings: tropical beach, neon city, jungle ruins, snowy mountains, deep space.
SHOT BREAKDOWN
0-4s — Woman in black suit walks forward on tropical beach at sunset, seagulls flying; framed as medium close-up pulling back.
4-8s — Setting morphs to rainy cyberpunk city with flying cars; wardrobe becomes black and silver sci-fi bodysuit; medium shot, continuous forward walking.
8-12s — Background shifts to jungle temple ruins with waterfalls and macaws, outfit becomes tan explorer jumpsuit; then morphs to snowy mountains and white winter parka.
12-15s — Environment dissolves into deep space with planets; outfit becomes white glowing space armor, stepping onto a crystal hexagonal platform; wide medium shot.
CAMERA
Steady tracking shot, reverse dolly moving backward at constant walking pace, subject centered. Seamless morphing transitions, no cuts.
LIGHTING & PALETTE
Dynamic environmental lighting. Warm golden hour (orange, cyan), wet neon (magenta, blue), soft jungle daylight (emerald, tan), stark space glow (purple, white).
AUDIO
Rhythmic electronic beat, rhythmic footsteps, waves, city hum, bird calls, icy wind, ethereal synth drone.
AVOID
Camera cuts, facial feature changes, breaking eye contact, jerky movements, inconsistent walking pace.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic hyper-realistic montage
SCENE
Young Asian woman maintaining a steady forward walk and direct eye contact while seamlessly morphing through distinct wardrobes and settings. Elements: corridor, dark blazer, modern office, sheer white gown, fashion runway, spacesuit, spacecraft cupola, racing suit, dark garage.
SHOT BREAKDOWN
0-4s — Woman walks forward in a silver top down a blurred corridor, seamlessly transitioning into a dark blazer within a modern office setting.
4-8s — She morphs into a sheer white couture gown, walking down a runway flanked by silhouette photographers, then transitions to an elevator lobby.
8-12s — She transitions into a white astronaut suit inside a spacecraft cupola, Earth visible through the rear window.
12-15s — She changes into a white, red, and blue racing suit in a garage with a sports car, ending on an extreme close-up of her face.
CAMERA
Steadicam tracking shot moving backward at a constant speed. Subject remains perfectly center-framed. Continuous fluid match-cuts driving the transitions.
LIGHTING & PALETTE
Dynamic, adapting per environment. Soft office daylight, bright runway flashes, cool spacecraft LEDs, dramatic high-contrast garage spotlights. Colors shift from warm neutrals to stark whites, cool space blues, and high-impact reds.
AUDIO
Driving electronic bass beat. Subtle ambient sound design matching environments: camera clicks, airlock hums, distant garage echoes. No dialogue.
AVOID
Camera pans, subject looking away, jagged transition cuts, facial distortion, legible logos.
Use @Image 1 for the character and the menu interface style. Use @Image 2 for the game world and the in-game HUD style. Use @Image 3 as the source for every item thumbnail shown inside the panels — its left column holds the three outfits, its centre column holds the three hairstyles, its right column holds the three weapons, each in that exact order top to bottom. One continuous shot, no cuts. The camera moves smoothly and constantly. Every panel stays fully inside the frame, positioned to the right of the character and large enough to read clearly. [0–2 seconds] Wide shot matching @Image 1, camera drifting slowly forward. The Mona Lisa character stands in the dark candlelit hall in her olive velvet gown and sheer veil, hands folded, still. She blinks once, slowly. The gold cursor travels down the right-hand menu across PLAY and onto WARDROBE, each button flaring gold as it passes. The cursor clicks WARDROBE with a sharp gold burst. [2–5.5 seconds] Ease in slightly, holding a full-body framing. A WARDROBE panel slides in on the right, filling the right third of frame — a vertical column of three ornate gold-framed slots carrying the three outfit thumbnails from the left column of @Image 3, in that exact order: blue brocade gown at the top, crimson silk gown in the middle, black leather set at the bottom. The selector highlights the top slot and her gown becomes the deep blue brocade court gown. The selector drops to the middle slot and her gown becomes the crimson silk gown with the boned corset. The selector drops to the bottom slot and locks: her long skirt dissolves upward in gold particles and reassembles as fitted black leather shorts, the bodice tightens into a cropped black leather top laced across the chest with gold cord, thigh-high black leather boots build up her legs plate by plate, and slim gold vambraces snap onto both forearms. [5.5–8.5 seconds] Rise smoothly to a medium shot from the waist up, keeping the panel column fully visible beside her. An APPEARANCE panel slides in on the right in the same position and size, carrying the three hairstyle thumbnails from the centre column of @Image 3, in that exact order: veiled waves at the top, coiled braid crown in the middle, high ponytail at the bottom. The selector highlights the middle slot and her hair winds itself up into the coiled braid crown threaded with gold chain. The selector drops to the bottom slot and locks: the sheer veil dissolves into gold particles and clears frame, her waves sweep upward and gather high on the crown into a long full ponytail bound with a gold cuff, the tail falling heavy behind her shoulder and swinging once as it settles. Her face stays exactly as it is throughout — the same serene gaze and the same faint closed-lip smile. [8.5–11 seconds] Ease down to a medium shot showing her from the hips up with both hands in frame, the panel column still fully visible beside her. An ARMOURY panel slides in on the right in the same position and size, carrying the three weapon thumbnails from the right column of @Image 3, in that exact order: crossed twin daggers at the top, war axe in the middle, gold-hilted duelling sword at the bottom. The selector highlights the top slot and two matched daggers assemble from gold particles, one in each hand. The selector drops to the middle slot and they break apart and reform as the broad war axe held across her body. The selector drops to the bottom slot and locks: the axe dissolves and the slender duelling sword builds itself in her right hand piece by piece — the swept gold hilt forming first, then the long polished steel blade extending outward with a bright ring. She lowers it to her side, point down. [11–12.5 seconds] Pull back smoothly to a full-body shot. A CONFIRM button flashes gold at frame centre and the cursor clicks it. Every panel collapses inward and vanishes. A LOADING bar sweeps in along the bottom and races from 0% to 100%. The dark hall brightens as warm golden daylight bleeds in from the left and the shadows retreat. [12.5–15 seconds] The world loads in around her: the sunlit Florence street from @Image 2 assembles outward from her feet — pale stone paving, ochre buildings, striped market awnings, hanging banners, townspeople walking, the cathedral dome rising at the end of the road under a pale blue morning sky. The camera swings around behind her and settles into a third-person gameplay position at her shoulder. The HUD fades in exactly as in @Image 2: CURRENT TASK reading REACH THE CATHEDRAL at upper left, circular minimap upper right, health and stamina meters lower left, weapon slot lower right showing the sword icon, and a large gold diamond quest marker floating above the road ahead. She stands with her back fully to camera, ponytail swinging, sword at her side, and takes her first step forward down the street. AUDIO — a game interface soundscape where every selection is loud and unmistakable: The interface sounds sit forward in the mix and are the clearest element in the piece. Every cursor hover fires a bright short gold chime. Every click lands as a hard mechanical thunk with a metallic tail, sharp and percussive, immediately audible. Every selector step down a row snaps with a crisp tick. Every panel slides in on a parchment whoosh and closes on a wooden clack. Under this, open on the quiet hush of a stone hall with a low candle-flame crackle and a soft sustained lute drone. Each outfit change carries a rush of cloth and a fine shimmer of particles; the leather build adds creaking hide and small metal snaps. The hair change is a soft sweep finishing on one gold cuff click. Each weapon assembly is sharp metal on metal, the sword finishing on a long bright blade ring. CONFIRM lands on a full resonant gold chime. The loading bar hums and rises in pitch as it fills. At 12.5 seconds the hall reverb drops away and the open street opens up: distant market chatter, birdsong, a cart wheel, footsteps on stone, warm Renaissance strings and lute swelling underneath. Ends on her boot striking the paving. Do not imitate an existing melody. Full speed throughout with no slow motion. Her face, gaze and faint closed-lip smile stay identical across every beat. All interface text in English, correctly spelled, every glyph crisp and legible.
Use the supplied image as the exact character, costume, scanning-chair, lighting, and production-design reference.
Create a dramatic mid-1980s satirical sci-fi action-film sequence with the bold, glossy industrial intensity of a classic scifi thriller. Everything must look physically photographed on a real soundstage using 1980s practical effects, animatronics, prosthetics, miniature electronics, steam jets, pyrotechnic sparks, optical compositing, and mechanical face appliances. No CGI.
0:00–0:04 — Cocky Close-Up
Locked frontal close-up of the confident woman secured inside the massive scanning chair. Her dark armored outfit clearly reads “MINIMAX: H3.” Red analog control lights pulse behind her. Steam curls around her shoulders while electrical arcs snap between practical metal coils. A tense electronic-orchestral action score rises. She looks directly into the camera with a knowing, fearless smile.
WOMAN — cocky, assured:
“Get ready for a mind-blowing surprise from Minimax H3!”
0:04–0:10 — Mechanical Revelation
As she finishes speaking, the machinery powers up with heavy relays, hydraulic clunks, warning buzzers, and flashing red lights. Practical sparks shower behind her and thick steam erupts from the chair. Her human face is revealed to be an elaborate prosthetic shell: clean mechanical seams appear along her cheeks and forehead, then multiple facial plates smoothly separate and retract outward on tiny visible gears and servos. No blood or gore.
Beneath the face is an extraordinarily advanced female robotic head, built as a sophisticated 1980s animatronic prop: polished chrome facial structure, translucent synthetic skin sections, glowing optical eyes, miniature pistons, cables, blinking diodes, and intricate handmade circuitry. The robot retains her confident expression.
0:10–0:15 — Hero Reveal
The robotic woman slowly tilts her head and gives the camera the same sly smile. Her eyes flare brightly as the scanner reaches maximum power. Steam, electrical arcs, spinning machinery, and controlled spark bursts fill the background. The music hits a massive heroic sting.
End on a powerful symmetrical close-up of the advanced robotic face and the clearly readable “MINIMAX: H3” chest label.
Visual requirements: authentic 35mm mid-1980s film photography, anamorphic composition, hard metallic highlights, deep blacks, cyan steel shadows, red practical lights, subtle film grain, optical glow, slight gate weave, richly detailed handmade machinery, real actress, real animatronic robot, real pyrotechnics, physical soundstage production. No modern digital interfaces, no holograms, no CGI, no morphing effect, no liquid metal, no contemporary superhero aesthetic, no gore, no subtitles.
Duration: 15 seconds | Aspect ratio: 4:5 | Style: Dark fashion editorial music video
SCENE
Two women. First woman: dark bob, black turtleneck, black fur jacket, black leather pants, tall boots. Second woman: blonde hair, black bralette, leather jacket with brown fur collar, black shorts, sheer tights, fur-cuffed boots, kneeling on a vintage brown armchair. Setting: distressed grey walls, brown velvet curtains, ornate floor mirror, patterned rug.
SHOT BREAKDOWN
0-4s — Wide shot of both women posing in the room. A harsh white glowing outline traces the dark-haired woman's body.
4-8s — Rapid digital cuts. Three overlapping, staggered close-ups of the dark-haired woman composite together. Cuts to a medium shot of the blonde woman shifting her pose.
8-12s — Room darkens. Thick, glowing horizontal white energy trails swirl violently around the silhouettes of both women.
12-15s — The energy trails form a circular portal framing the wide shot. Quick cut to an extreme macro shot of black leather moving. Ends returning to the wide shot with dissipating light trails.
CAMERA
Fast-paced music video editing. Static wide framing juxtaposed with jarring digital overlays, multi-exposure clones, and abrupt extreme macro inserts.
LIGHTING & PALETTE
Low-key, moody studio lighting with heavy shadows. Palette is dominated by charcoal, onyx, deep brown, and black, sharply contrasted by stark, luminous white VFX energy.
AUDIO
Heavy dark synthwave or trap beat. Aggressive digital whooshes, risers, and crackling sound effects synced to the swirling energy trails.
AVOID
Natural sunlight, smooth cinematic panning, slow pacing, pastel colors, acoustic instrumentation, photorealistic documentary style.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: First-person mixed-media magical realism blending live-action with glowing neon 2D animations.
SCENE
Unseen protagonist's hands, brown jacket sleeve. Retro laundromat with metallic washing machines, beige tiles, fluorescent lights, wooden bench, white laundry basket. Floating neon line-art animations: jellyfish, sock, fish, toast, truck, geometric energy.
SHOT BREAKDOWN
0-4s — Fingers pinch a fuzzy, glowing purple orb. Cut to first-person view looking down into a laundry basket where a neon purple line-art jellyfish floats above white garments.
4-8s — Low angle pan to a glowing neon sock hovering beside a real grey sock on the floor. Cut to first-person hand reaching toward a washing machine door; a neon cyan fish swims on the glass.
8-12s — Hand opens the washing machine. Neon purple toast and a white truck float out amid drawn smoke. Cut to hand holding a glowing purple geometric cube near a blue vending machine.
12-15s — Wide shot of the laundromat. Neon pink and cyan energy spikes erupt across the floor from the central machines. The entire room suddenly transforms into a neon line-art blueprint floating in a dark, starry cosmic void.
CAMERA
First-person perspective. Handheld movement. Shallow depth of field with macro focus on glowing objects. Fast-paced rhythmic cuts. Concludes with a wide, static establishing shot.
LIGHTING & PALETTE
Harsh overhead fluorescent practical lighting. Physical space features muted beige, silver, and white. Animated elements emit intense luminescent neon purple, cyan, and pink. Final scene is deep space-black with vibrant neon outlines.
AUDIO
Humming fluorescent lights, tumbling washing machines, synthetic magical chimes, electronic synth beat.
AVOID
Third-person perspective, photorealistic CGI entities, natural daylight, static framing, deep depth of field.
Neon Street Wardrobe Transformation `reconstructed`
15s9:16
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Photorealistic street fashion video
SCENE
Young Asian woman with long black hair, dynamic transforming wardrobe. Bustling illuminated pedestrian street at night, featuring glowing neon shop signs, vertical banners with Japanese text including "デッソン", overhead streetlamps, and a crowd of varied bystanders.
SHOT BREAKDOWN
0-4s — The woman walks forward confidently, smiling, wearing a bright yellow button-up jacket, black crop top, dark grey cargo pants, and white sneakers. Framed full body.
4-8s — Seamless transformation. She wears an emerald green satin gown with a thigh-high slit and silver heels, continuing her forward walk.
8-12s — Brief cut to a shocked man in a grey hoodie and woman in a tan trench coat dropping their jaws. Cut back to the main subject, now wearing a bright red trench coat and black boots, passing the astonished onlookers who hold up smartphones.
12-15s — Final seamless transition into a holographic silver zip-up jumpsuit with glowing cyan platform shoes. The background crowd eagerly takes photos.
CAMERA
Eye-level frontal tracking shot, pulling back steadily to keep the walking subject centered. 50mm lens feel with moderate background blur. One fast reaction cutaway. Rhythmic, seamless visual effects editing.
LIGHTING & PALETTE
Nighttime urban illumination. Bright ambient streetlamps, vibrant neon accents. Subject outfits feature saturated jewel tones and metallics (yellow, green, red, silver) contrasting heavily with the dimmer, neutral-toned crowd.
AUDIO
Upbeat electronic runway music, ambient street chatter, rhythmic footsteps, camera shutter clicks, background gasps of amazement.
AVOID
Motion blur, anatomical distortions, inconsistent background architecture, muted lighting, static camera movement.
Urban Fantasy Armor Transformation `reconstructed`
15s9:16
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Cinematic urban fantasy and superhero transformation sequence with realistic VFX.
SCENE
Young East Asian woman with long black hair, changing from casual white dress to purple cyber armor and black kimono; giant horned reptilian monster with glowing red eyes; modern Japanese city crosswalk with stunned pedestrians.
SHOT BREAKDOWN
0-4s — Quick pan across a busy road as a massive horned kaiju stomps onto the asphalt crosswalk, kicking up dust.
4-8s — Medium profile shot of the woman conjuring purple energy along her arm, morphing instantly into sleek purple high-tech armor.
8-12s — Low-angle shot from behind as the armored woman raises her hand toward the towering monster, defeating it and shifting into a dark robe.
12-15s — Forward tracking shot as the woman walks past astonished onlookers, turning to face the camera with a playful smile and gesture.
CAMERA
Handheld street-level framing shifting into smooth dynamic tracking; wide to medium lens, low-angle superhero perspective, fluid single-take motion.
LIGHTING & PALETTE
Overcast daylight ambiance, muted city greys, asphalt tones, accented by vibrant glowing purple energy and piercing red monster eyes.
AUDIO
Screaming pedestrians, heavy ground-shaking monster stomps, electrical surging effects, transitioning into quiet ambience and a subtle upbeat musical sting.
AVOID
Bright saturated daylight, 2D anime styling, static tripod framing, visible gore, floating HUD elements.
@Image1 15s | 16:9 | 1440p | 24fps | PERFECT SEAMLESS LOOP [REFERENCE LOCK] Render exactly as @image1. Preserve the character exactly as shown. Do not redesign, reinterpret, or modify any aspect of he…
Camera: First-person perspective at eye level with authentic handheld player movement, as if recorded directly from a modern AAA military shooter. The player carries a highly detailed assault rifle with realistic animations, visible hands, tactical gloves, dynamic reload mechanics, and weapon sway. **Opening Action:** The video immediately begins with the player already aiming down a roadway inside a modern military base. Multiple enemy soldiers are visible in the distance near sandbags, barricades, and military vehicles. The player carefully tracks one target, making small aim corrections while maintaining ADS (aim down sights). Fire several controlled bursts immediately at the visible enemies, producing realistic muzzle flashes, shell casings ejecting, smoke, recoil, hit reactions, and dust impacts around the targets. Continue firing in multiple short bursts while adjusting aim between enemies, simulating authentic FPS gameplay rather than scripted animation. **Movement:** After the opening firefight, lower slightly from ADS and begin advancing cautiously along the road beside concrete barriers, Hesco walls, and parked military vehicles. Frequently check left and right corners, briefly stop to reacquire targets, then raise the weapon and fire additional controlled bursts whenever enemies appear ahead. Continue pushing forward with deliberate player-controlled movement, using cover naturally and maintaining believable tactical pacing. **Environment:** Large modern military base with guard towers, armored vehicles, shipping containers, blast barriers, damaged buildings, smoke plumes, burning debris, scattered shell casings, dust clouds, and atmospheric battlefield haze. Cool natural daylight mixed with smoke and orange firelight creates a cinematic battlefield atmosphere. **Camera Motion:** Authentic player-controlled movement with subtle head bob, weapon sway, natural mouse-look adjustments, small left-right corrections while aiming, realistic recoil, smooth tracking of moving targets, brief pauses before shooting, and fluid forward progression. Avoid cinematic camera moves—everything should feel like genuine live gameplay captured by a skilled player. **Visual Quality:** Ultra-photorealistic, AAA game graphics with realistic PBR materials, detailed weapon models, physically accurate lighting, volumetric smoke, dynamic particle effects, crisp textures, realistic bullet impacts, muzzle flash illumination, motion blur only during rapid movement, and high-end military shooter presentation. **Gameplay UI:** Display a realistic modern FPS HUD inspired by games like PUBG, Battlefield, or Call of Duty (without copying exact copyrighted assets). Include: * Central dynamic crosshair or reticle * Ammo counter with magazine and reserve ammunition * Fire mode indicator * Compass at the top * Squad/team status panel * Mini-map in the upper corner * Health bar * Tactical equipment icons (grenades, medkit) * Hit markers when bullets connect * Directional damage indicators * Kill notification feed * Objective marker in the distance * Subtle interaction prompts and realistic HUD animations The HUD should feel polished, modern, and fully integrated into the gameplay, enhancing the illusion of authentic recorded footage from a contemporary military FPS.
Soft cute Y2K crush K-pop girl group rap MV. High fashion performance film mixed with inflated 3D candy typography graphic system. Three female idols wearing pink, blue and purple luxury Y2K stage outfits. Cute 3D chibi doll face, big dewy eyes, porcelain skin, soft blush cheeks, chibi idol proportions. Reference typography: only the inflated 3D rubber bubble font language, pink/lavender/ice-blue chrome plastic material, not the whole layout. Visual style: soft pastel crush energy, Y2K game UI, candy glossy finish, milky translucent plastic × K-pop aggressive feminine rap energy. Texture: 35mm film grain + soft glow bloom + iridescent holographic foil + jelly plastic specular + Y2K scanline + candy dot halftone + VHS frame vibration + plastic toy surface reflection + glitter confetti rain. Editing: Fast rhythm editing. Only hard cuts. No fade. No smooth transitions. Every cut follows: bass hit, snare, rap vocal impact.
Character Performance Three female performers from reference image 1. Keep: same 3D chibi doll faces, big sparkling eyes, pastel Y2K idol makeup, pink/blue/purple fashion styling, soft cute cold expression. Each member has a signature prop: A holds a chunky rhinestone microphone, B has a plush bear shoulder bag, C wears oversized heart-shaped sunglasses pushed up on head. They are not posing. They are performing rap. Actions: aggressive eye contact, head nodding, shoulder movement, leaning toward camera, hand pushing toward lens, confident cute facial expression, sharp body movement, wink on snare hit, tongue-out on bass drop, hair flip on beat. Lip sync: perfect rap mouth synchronization. The performance should feel like a real K-pop rap unit MV with Y2K crush energy.
Typography Animation Typography is a visual weapon. Not subtitles. Not static graphics. Use: giant English words inflated 3D rubber bubble font, jelly plastic material, pink lavender ice-blue chrome, soft puffy candy letters, compressed bold balloon fonts, stretched vertical puffy letters, handwritten graffiti titles, 3D extruded candy text, glitch displacement, print error effect, Y2K game UI pixel corruption. Text appears only when the beat hits. Characters can cover the text. Text can cover parts of clothing. Never cover eyes or main facial expression. Tiny Y2K stickers burst on beat: heart, star, smiley, sparkle, chain link, bow, four-leaf clover, mini bear.
Shot 1 — Member A · Extreme Close-up「RUN NOW」 Character A face close-up, framed inside a pink heart-shaped iris wipe transition (in only, hard cut out). She looks directly into camera. Cute cold doll expression, big dewy eyes, soft blush, frosted pink lip gloss, rhinestone tear sticker under one eye. Starts rap. Chunky rhinestone microphone enters frame from below, she grips it tightly. Camera slowly pushes closer. Tiny pink heart stickers float up from bottom edge like bubbles. Huge inflated bubble letters crash into frame from left and right. Typography: "RUN NOW" — Pink jelly rubber 3D font, glossy candy surface, soft inner glow. Letters stretch vertically like puffy balloons. The word vibrates and squishes with bass, casts soft pink shadow on her cheek. Rap: "Run now, I don't chase." Confetti burst on final syllable. Hard cut.
Shot 2 — Member B · Rap Performance「BREAK LIMIT」 Member B medium close-up, slight low angle, camera orbits 15° around her during the take. Lavender fur jacket, Y2K layered top, plush bear bag bouncing on her hip, chunky pearl choker, star-shaped earrings. She performs aggressively. Shoulders hit the rhythm. Hair flips hard on the second snare, blue hair ties catch the light. Hair moves naturally. Background: pastel gradient pink-to-lavender with faint Y2K perspective grid lines floating. Behind her appears huge handwritten text. Typography: "BREAK LIMIT" — Ice-blue bubble graffiti brush writing, soft inflated stroke, candy-coated, letters appear one by one with bounce easing. Animation: letters tear apart, reassemble, rotate 360° on snare, shake with bass. Chain link graphic swings across frame, sparkle stickers pop on every beat. Rap: "Break limits, break rules." Hard cut.
Shot 3 — Member C · Hand Attack Shot「NO APOLOGY」 Member C moves close to camera. Top-down camera angle, she leans over the lens. Hand reaches toward lens. Nails are long pink acrylic with 3D star and heart charms. Focus: rings with mini plush bear charm, heart-cut gemstone, baby-pink leather texture, knit ribbed sleeve, plushy toy surface. Foreground vertical text: "NO APOLOGY" — Stretched vertical pink bubble letters, jelly puffy material, letters pierce through the back of her hand visually. Hand covers part of the typography. Fingers spread wide on the bass hit. Camera: handheld vibration. Film grain strong. Candy halftone dots bloom in shadow. Tiny "XOXO" sticker tag pulses in corner. Rap: "No apology, no regret." Hard cut.
Shot 4 — Fashion Magazine Impact Cut「UNSTOPPABLE」 Member A close-up. Her face appears inside a broken Y2K trading card / idol photo card frame, with barcode at bottom, "SYS.07-A" serial tag, holographic foil border torn on left side. Not a full layout. Only one graphic element. Typography: "UNSTOPPABLE" — Huge lavender handwritten bubble text, inflated 3D rubber, glossy plastic finish, letters explode outward from center of her forehead, push edges of the card frame. Animation: text suddenly expands from behind her. Card frame rips in half vertically, holographic confetti pours from the tear, revealing pastel gradient background underneath. A second smaller photo card of her winks in from the right, slightly rotated. Rap: "Can't stop my wave." Hard cut.
Shot 5 — Glitch Double Image「STATIC」 Member B close-up, slight Dutch angle (5° tilt). Create: duplicate frame, pastel RGB separation (pink/blue/lavender channels), xerox shadow, motion trail, VHS tracking line at bottom edge. Main face stays sharp. She holds a sparkly heart-shaped lollipop up beside her cheek, the lollipop leaves a trail of echo frames. Background text: "STATIC" — Y2K pixel font, candy pink chrome, letters flicker like broken game sprite, jump between frames, sometimes inverted color, sometimes missing entirely. Like corrupted music video signal + cute game glitch. A tiny "ERROR 404" sticker blinks in upper corner. Rap: "Static noise, I get louder." Hard cut.
Shot 6 — Pink Blue Purple Battle「PINK OUT」 Member A and C alternate close-ups, rhythm: A-A-C-A-C-C, two frames each. Fast switching. Visual split: each member sits in a vertical color block (A=pink, C=lavender, alternating). Center text: "PINK OUT" — Pastel pink-to-purple gradient bubble 3D, letters appear one word at a time, syncing to each cut. Words appear one by one. Each word: stretch vertically on entry, compress horizontally on hold, invert color on snare, explode into heart stickers and star confetti on exit. Tiny "1.2.3.GO!" counter graphic ticks in corner. Rap: "Lights out, pink out." Hard cut.
Shot 7 — Group Rap Performance「UNBREAKABLE」 Three members together.
Use Image 1 for the board, art direction, and lighting. Use Image 2 for the exact UI style — preserve its card shape, filigree, colors, and iconography.
[0–2s] Slow isometric drift across the courtyard. The card fan deals in from the bottom edge, five cards arcing into place one at a time with a slight overshoot and settle. The energy orb fills to 3.
[2–5s] Cursor lifts the second card; it scales up, tilts toward camera, and glows. Dragging it over the left enemy paints three hex tiles red with a soft pulse. Release — the card burns from the bottom edge upward and dissolves into embers.
[5–8s] Camera snaps to a low three-quarter angle for the resolution: a shockwave crosses the three red hexes, damage numbers arc up and fade, one skeleton shatters into bone fragments that settle physically on the tiles.
[8–11s] Return to isometric. Energy drops to 1. The remaining cards slide left to close the gap. Cursor hovers END TURN; the button pulses gold.
[11–15s] Enemy turn: a red banner wipes across the top of frame, the surviving skeletons step two hexes forward with staggered timing, and a threat marker appears over the player unit. The banner wipes out. Cards deal in again for the next turn. Keep all UI perfectly screen-locked and crisp regardless of camera movement. Text must be legible and spelled correctly.
Audio: parchment card slides, a wooden clack on card placement, a low bone-crunch impact, a soft chime on energy spend, muted lute drone underneath.
Negative: no UI drift or warping, no invented card names, no misspellings, no gore, no blood, no camera shake during UI interaction.
Use Image 1 for the character, Image 2 for the UI style, and use the uploaded weapon selection image as the reference for all paint weapons. The selectable weapons should closely match the colorful ink guns shown in the reference image, including compact paint shooters, dual paint pistols, heavy paint cannons, bucket/slosher weapons, large paint brushes, paint rollers, sniper-style paint rifles, and other stylized colorful ink weapons. Match their playful proportions, vibrant colors, chunky plastic construction, and game-like appearance while avoiding exact logos or branding.
[0–2 seconds]
High-angle overhead shot. The character stands on a vivid, highly saturated purple floor, looking up toward the camera, matching Image 1 exactly. A colorful game menu matching Image 2 appears on the right: START NEW GAME, CONTINUE (highlighted), SETTINGS, EXIT GAME. Player profile MINIMAX appears in the top left. The cursor selects CONTINUE.
[2–4 seconds]
The camera pushes toward her right hand. A PAINT WEAPON SELECT panel slides in, using the uploaded weapon selection screen as its layout and visual reference. Multiple colorful paint weapons are displayed exactly like the reference image in a grid with rarity and level indicators. The cursor moves between different weapons. Every time a weapon is highlighted, the paint gun in her hands instantly transforms into the selected model with colorful ink particles, playful mechanical animation, spinning parts, and glossy paint effects. She remains standing throughout.
[4–7 seconds]
The camera smoothly arcs around her left side. The selector rapidly cycles through many weapons from the reference image: compact paint shooters, oversized paint brushes, dual paint pistols, heavy paint cannons, bucket-style splash weapons, sniper paint rifles, giant paint rollers, and experimental ink launchers. With each selection, the weapon in her hands changes immediately to match the highlighted weapon while she naturally adjusts her grip. Every swap is accompanied by bursts of colorful ink, animated UI effects, splashing paint particles, and satisfying transition animations.
[7–8.5 seconds]
Pull back to a medium shot. CONFIRM LOADOUT flashes. The cursor clicks it. All UI panels collapse and disappear. She confidently spins the selected paint weapon once before resting it on her shoulder, remaining in a relaxed standing pose.
[8.5–10 seconds]
A colorful LOADING bar fills from 0% to 100%. The purple testing room dissolves beneath spreading ink splashes that transition into the game world.
[10–15 seconds]
The world loads into a bright, colorful ink-covered city filled with graffiti, paint-coated streets, animated billboards, moving NPCs, and playful architecture. The camera settles into a third-person view behind the character. HUD elements fade in: minimap, health, paint gauge, current weapon icon matching the selected weapon, ammo counter, and objective marker. She runs forward while firing the selected colorful paint weapon, coating walls, streets, obstacles, and scenery with thick, glossy paint that matches the weapon's color.
Minimax H3 Prompt
A dramatic sports sequence begins on a lush, windswept coastal cliff during a violent rainstorm. A golfer in bright yellow rain gear stands on the tee box, gripping a driver. His stance is planted firmly, eyes locked on a distant green across a churning ocean cove. As he swings, the clubhead connects with a resounding crack, launching the dimpled white ball into the stormy sky. The camera immediately accelerates and locks onto the golf ball mid-flight. The camera tracks directly behind the spinning sphere, maintaining perfect alignment as it cuts through the driving rain. The ocean waves and dark clouds become a streaking motion blur while the ball remains sharp and centered. The howling wind roars as the projectile travels straight and true. The manicured green grows rapidly larger. In the final seconds, the camera closes in tightly as the ball strikes the turf. End on an extreme close-up of the ball ripping through the wet grass, throwing up a spray of dirt before dropping perfectly into the cup.
A cinematic multi-panel grid where every individual frame simultaneously comes alive with independent, fluid motion. Each cell features distinct, continuous animation and dynamic lighting effects while maintaining crisp compositional borders and high-definition detail across all panels.
Create a cinematic text render animation featuring the exact text "AZED AI", formed entirely from flowing black ink on a clean white background. Begin with a single small drop of wet black ink hitting the center of the white surface, creating an organic splash with tiny droplets and irregular feathered edges. The fresh ink rapidly spreads outward through realistic fluid motion, branching into thin streams, curling tendrils, splashes, and capillary trails.
The flowing ink begins tracing the letterforms of AZED AI. Instead of the finished letters suddenly appearing, every stroke must visibly grow from the moving liquid. Ink streams travel along the future shapes of the typography, merge with neighboring streams, fill thicker areas, and progressively construct each letter from left to right. Small droplets are pulled toward the forming characters and absorbed into the wet letterforms.
As AZED AI becomes fully readable, the restless liquid movement gradually slows. Small pools of ink settle inside thicker strokes while delicate feathering, tiny splatters, uneven pigment density, wet edges, and subtle surface reflections remain visible. A few final ink droplets travel into incomplete edges and naturally finish the typography.
End with AZED AI completely formed in rich black ink, centered against the pure white background, bold and clearly readable, with authentic handmade imperfections around the edges. The camera performs a subtle slow push toward the completed text while the wet ink catches soft highlights.
Preserve the exact text "AZED AI" throughout. Exact spelling, capitalization, spacing, and letter order are mandatory. No instant text appearance, no digital morphing, no particles, no metallic material, no 3D solid letters, no clean vector edges, no additional words, no misspelled letters, no duplicated characters, no random symbols, no distorted typography, no illegible text, no excessive splashing that obscures readability.
Extreme Hollywood pyro title sequence: begin inside a microscopic droplet of fuel suspended in darkness as a spark suddenly ignites its surface. Fire spreads explosively outward and the camera rockets backward through a chain reaction of enormous fuel explosions. Liquid fire whips across the frame like glowing ribbons while burning debris and sparks spiral into a rapidly expanding fire tornado. The camera enters the vortex and rotates around a white-hot molten core where streams of liquid metal begin violently forging the gigantic word "BURN". Every letter emerges incandescent from the inferno before cooling into cracked black steel while magma remains visible beneath the surface. The completed title slams into frame with enormous weight as flames blast through the gaps between the letters. Pressure suddenly builds inside the typography until "BURN" violently ruptures from within, unleashing a radial explosion of molten metal, sparks and fire directly into the lens. Extreme heat distortion, realistic pyro physics, aggressive camera movement, AAA theatrical VFX.
One-Line Prompt: Power-Washing the Patio Reveals the Night Sky (Local Open Weights)
15s16:9
Minimax H3, open weights, generated locally. Power washed the patio. Found the sky under it.
Prompt: "every clean stripe it leaves is not stone but a strip of deep night sky"
Duration: 15s. Camera: locked, top-down. Rendered locally in ComfyUI, then Topaz to 4K.
Four passes, all left to right. Give a reveal a direction and the edge stays crisp.
One-Line Prompt: Scooping Out a Small Moon (Local Open Weights)
15s16:9
Minimax H3, open weights, generated locally. One scoop of midnight. It came with a moon.
Prompt: "the ball it lifts out is a small grey moon with craters"
Duration: 15s. Camera: locked, slightly above. Rendered locally in ComfyUI, then Topaz to 4K.
One scoop, pulled toward the camera. A single stroke with a direction beats asking for scooping.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Mixed media, live-action with 2D anime character integration
SCENE
Car interior. Passenger: 2D anime girl, split pink/blue bob hair, white collared shirt, blue skirt, unamused expression. Driver: Live-action man, green afro, oversized red/blue 3D glasses, patterned navy suit, pink bowtie, goatee. Setting: Black leather car seats, seatbelts, passing suburban streets outside.
SHOT BREAKDOWN
0-4s — Dashboard POV wide shot. The driver speaks energetically, holding the steering wheel. The anime passenger sits motionless.
4-8s — Close-up of the anime girl. She rests her chin on her hand, displaying a profoundly bored, deadpan expression with half-closed eyes.
8-12s — Close-up of the driver talking animatedly and pumping his fist. Cut to a wide two-shot showing the girl's unimpressed profile in the foreground while the driver steers in the background.
12-15s — Close-up of the driver explaining something. He gestures with his right hand, then awkwardly rubs the back of his neck. A blue backpack is visible behind him.
CAMERA
Dashboard-mounted static wide angles alternating with tight facial close-ups. Sharp, rhythmic cuts highlighting the contrast in character energy.
LIGHTING & PALETTE
Diffused, overcast daylight from windows. Saturated contrasting colors: neon green hair, bright cyan/magenta glasses, pastel pink/blue anime hair, deep navy suit with yellow/red patterns.
AUDIO
Muffled engine hum and road noise. Upbeat, comedic backing track. Enthusiastic male dialogue syncing with the driver's lips.
AVOID
Lighting mismatches between 2D and live-action elements, motion blur on the anime character, shifting car interior layouts, camera shake.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Voxel-based 3D animation, blocky pixel art aesthetic with realistic lighting
SCENE
First-person character with blocky, pixelated arms. A forest campsite beside a flowing stream. Voxel-style trees, grass blocks, dirt paths, gray stones forming a campfire ring, and a circular tree stump prep station.
SHOT BREAKDOWN
0-4s — Camera pans across the stream to the tree stump. A blocky hand holds an iron cleaver, chopping voxel ingredients into smaller yellow, orange, and brown cubes.
4-8s — Perspective shifts to the campfire ring. A dark, blocky frying pan rests on stones, holding the chopped cubes. Orange flames ignite beneath the logs, generating rising gray smoke.
8-12s — A square glass shaker appears on a rock. The first-person arm grabs the shaker and tips it over the pan. Black pixelated seasoning falls onto the cooking food cubes.
12-15s — Large brown voxel meat blocks are added to the pan. Two blocky hands present the completed meal—stacked meat blocks, yellow cubes, and a red tomato block—served on a scalloped wooden plate held above the roaring fire.
CAMERA
First-person POV throughout. Fluid, continuous movement mirroring head and hand motions. Close-up framing focused entirely on the culinary tasks and ingredients.
LIGHTING & PALETTE
Natural sunlight filtering through the forest canopy, creating sharp shadows. Dynamic warm orange illumination from the campfire. Earthy palette of forest greens, dirt browns, charcoal gray, and bright yellow-orange food tones.
AUDIO
Ambient forest wind and trickling stream water. Rhythmic heavy thuds of a chopping cleaver. Intense crackling of burning logs, loud sizzling of frying food, and the sharp rattle of a seasoning shaker.
AVOID
Smooth organic geometry, high-polygon meshes, realistic human anatomy, modern kitchenware, visible faces.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Angular stylized 2D animation with sharp geometric shapes and vibrant cel-shaded rendering
SCENE
An urban night setting featuring a young man with a white cheek bandage, oversized black jacket, and light cream trousers on a white cafe racer motorcycle. A young woman with blunt black bangs, a sheer cropped top, and shiny black mini-skirt joins him outside a illuminated storefront before riding through a highway tunnel.
SHOT BREAKDOWN
0-4s — Medium wide shot outside a fluorescent-lit storefront; the man straddles his motorcycle lighting a cigarette as the woman steps out the glass door and gracefully mounts the back seat.
4-8s — Medium tracking shot inside a subterranean expressway tunnel; the woman leans forward, resting her chin and arm affectionately on his shoulder while her dark hair blows backward in the wind.
8-12s — Close-up side tracking profile; the man steers calmly with a glowing cigarette between his lips while the woman peacefully closes her eyes against his jacket, cyan ceiling lights flashing rapidly overhead.
12-15s — Low-angle perspective from behind the motorcycle as it accelerates down the center line of the roadway, roaring toward the tunnel's vanishing point under repeating illuminated overhead fixtures.
CAMERA
Cuts from a static street-level medium shot to fluid side-tracking profiles matching the motorcycle's velocity, concluding on a low-angle trailing shot with deep perspective.
LIGHTING & PALETTE
High-contrast nocturnal aesthetics dominated by deep navy shadows, bright warm convenience store glows, and intense teal and cyan tunnel strip lights casting dramatic edge highlights.
AUDIO
Subdued ambient city murmur transitioning into a guttural, throaty four-stroke motorcycle engine revving, rushing atmospheric wind effects, and a moody electronic synthwave beat.
AVOID
Photorealism, live-action footage, soft gradient shading, anatomical warping, background motion blur, visible pedestrians.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D animated cinematic action anime
SCENE
Two superpowered martial artists. Fighter One wears an open white shirt and radiates a fiery golden aura. Fighter Two wears a black leather jacket and dog tags. Environments include a desolate city street and a crumbling stadium.
SHOT BREAKDOWN
0-4s — Fighter One charges up, emitting bright golden light. A close-up reveals cracked skin with glowing blue energy and luminous eyes. Fighter Two stands defiantly in a sunset-lit street, then charges aggressively toward the camera.
4-8s — Fighter One delivers a sweeping, flame-wreathed punch, knocking Fighter Two backward. A tight close-up focuses on Fighter One's blazing yellow eyes. Cut to an expansive aerial shot of the two figures confronting each other in the center of a heavily damaged stadium.
8-12s — Glowing blue electricity concentrates around a forearm. The arena floor detonates, sending massive chunks of concrete and dust flying upward into the stadium sunlight.
12-15s — Fighter Two roars in slow motion. A fist surging with blue lightning punches directly toward his face. Fighter One stands enveloped in golden energy, ending on a final piercing stare.
CAMERA
Rapid action cuts. Alternates between intense extreme close-ups, dynamic tracking during sprints, and sweeping high-angle wide shots.
LIGHTING & PALETTE
High-contrast dramatic lighting. Dominant warm tones of amber, gold, and sunset orange, sharply contrasted by bright cyan and blue electrical effects. Deep black shadows.
AUDIO
Low rumbling bass, electric crackling, heavy impact thuds, shattering concrete, and aggressive yelling. Intense electronic action score.
AVOID
Watermarks, on-screen text, cel-shading, slow pacing, static camerawork.
A top-down stop-motion style video of four hands assembling a detailed dragon head sculpture on a clean white surface using only natural materials.
Start with four hands holding and positioning bare brown twigs and branches, carefully arranging them into the basic outline of a dragon’s head, neck, and curved spine with small protruding sticks for spikes.
Next, hands place large pieces of rough textured tree bark to form the dragon’s face, snout, and jaw, carefully fitting the pieces so the bark grain creates natural scales and ridges. Yellow lichen spots appear on the forehead and cheeks. Small sharp wooden shards are inserted as teeth.
Then hands add layers of thin bark strips and light-colored wood pieces along the neck to create overlapping scale armor. Fresh green moss is packed into the upper neck and crest area. Dried brown and golden autumn leaves are carefully layered in a flowing mane along the side of the neck.
Hands continue refining: placing two curved wooden sticks as horns, adding small pinecones as decorative spikes, inserting a realistic glass eye into the socket, and tucking pine needles into the mouth and around the head like whiskers and eyebrows.
Final shot: the completed dragon head sculpture sits alone on the white background — a fierce yet elegant nature-made dragon with bark scales, moss crest, leaf mane, wooden horns, sharp teeth, and a single glowing eye. Soft even lighting, clean white background, hyper-detailed textures, realistic stop-motion assembly feel, 9-second duration.
Create a 15-second 16:9 horizontal photorealistic and 3D-anime hybrid video with native dialogue, singing, original music, and sound effects.
References:
Reference 1 = Japanese schoolgirl.
Reference 2 = tiny original 3D idol.
Reference 3 = decorated fan-support bag.
0–3 sec:
In a medium-wide shot, the schoolgirl places the bag on a table and opens it toward the camera. The bag fills the center and right side of the frame while her surprised face remains visible on the left.
Badges and keychains shake naturally. A miniature stage light appears inside.
The girl says:
「えっ、動いた？」
Generate a natural young Japanese female voice: soft, surprised, believable, not exaggerated, accurate lip-sync.
3–6 sec:
The acrylic stand matching Reference 2 glows, becomes three-dimensional, and jumps into the central stage area.
Tiny charms transform into miniature light sticks across the left and right sides of the bag.
6–11 sec:
The tiny idol sings:
「キミの今日を きらり更新！」
Generate an original young Japanese idol voice: bright, cute, energetic, clear pronunciation, stable pitch, natural breathing, and accurate singing lip-sync.
Generate original modern Japanese idol-pop with sparkling synths, crisp drums, handclaps, bright bass, and a catchy melodic hook.
The idol performs energetic choreography. Badges flash across the wide frame, ribbons move like curtains, and keychains bounce like a cheering audience.
11–15 sec:
The idol jumps onto the girl’s palm in the foreground. They perform the same finger-heart pose side by side.
A star-shaped light connects their fingers. The idol freezes back into an acrylic stand for a seamless loop.
Audio:
Miniature stereo crowd cheers, plastic charm sounds, acrylic clicks, claps, sparkle effects, and a clean final chime.
No subtitles, additional people, logos, character redesigns, or watermarks.
@image1
15s | 16:9 | 1440p | 24fps | SEAMLESS LOOP
[LOCK] Render exactly as @image1. 完全按照该参考图呈现，不进行任何重新设计。Do not alter hair, bangs, eye color, coat silhouette, sash, hilt ornament, or blade proportion.
[LOOP] A perfect cycle. The final frame must match frame one exactly — same composition, focal length, lighting, blade position and pose — so playback runs endlessly with no seam. The story is a blade breaking and unbreaking forever.
[PALETTE] Background: smooth vertical gradient, luminous cyan-teal #2AA6B4 top into deep petrol #0F4A55 bottom — a graphic plane, no environment, no horizon, no props. Coat bright coral #FF9273. Inner garment #14454E. Hair true black with blue-white highlights. Metal and glass bright silver-white.
Accents as refracted light ONLY, never flat fill: gold #FFD27A, cyan #6FE3F5, magenta #FF9ED8. Core palette always dominates.
[STYLE] 2.5D anime, bright cinematic. High-key, generous bloom, crisp speculars, luminous not grim. Skin luminous with subsurface warmth at ears and fingertips. Coat as heavy matte cotton twill, deep folds. Hair in clumped strands with flyaways catching the rim. Glass with real thickness — edge refraction, internal fracture lines, micro-scratches.
[EFFECTS] Escalating: time-echo ghosting trailing every fast move, each afterimage a different accent; liquid mercury flow as the blade sets; kaleidoscope fracture splitting the frame into mirror symmetry; shockwave refraction warping the background and bending the type; one-frame negative invert on hard impacts; glass-crack frame wipes; reverse-gravity debris; prismatic dispersion off every shard edge casting moving caustics across her face and coat.
[CAMERA + LIGHT] Anamorphic — oval bokeh, blue streak flares, slight barrel distortion wide. 85mm close, 35mm wide, 24mm on moves. 180-degree shutter. Shallow focus on hero beats, deep on montage frames. Rack focus blade-to-eyes at 2.4s and 14.2s.
Hard sun key from screen right, high and behind — bright rim on jaw, shoulder and blade edge. Broad cyan bounce fill off the background plane. Kicker thrown by the shards, hue shifting each beat. Shadows open, never crushed. Brightest at 10.4, back to the opening state by 15.0.
[SIGNATURE] A fine engraved CIA0 sits on the blade's ricasso above the hilt, small letter-spaced capitals cut into steel, catching the key light as the camera races past in the opening shot. Part of the blade, not an overlay — present in frame one, in the final frame, and on the reforged blade at 14.4s.
[SHARDS] Vary reflected content shard to shard: blue sky with cumulus, sunlit golden farmland, a low sun with lens flare, a fragment of her own face, pure white cloud. A few reflect a beat that has not happened yet. Never blank glass.
[TYPE] Behind her on the gradient plane. Condensed sans for Latin, brush-weight for Japanese. Gradient fill, soft glow, hard offset shadow. Kinetic — slams, scrolls, shatters, warps under shockwaves. Never covers her face. Japanese runs VERTICAL in a side third; Latin STACKED, two lines max, cropped by frame edge for scale.
0.8s 「鏡」 coral into gold
2.2s "A BLADE THAT BREAKS" / "AND UNBREAKS FOREVER" pale cyan into white
5.0s "ONE IMAGE" / "FIFTEEN SECONDS" white into coral
7.2s 「反射」 diagonal prism sweep, cyan-white-magenta-gold
10.6s "NO CUT" gold into white, warping under the shockwave
13.2s title 「鏡落」 above "MIRRORFALL", silver into pale gold, coral glow — must fully dissolve before 15.0
[SHOTS]
0.0-1.6 LOOP POINT. Extreme close-up racing along the blade flat toward the hilt, clouds streaking on steel, flare sliding down the edge, the engraved mark passing through frame. Blade detonates. Glass-crack wipe.
1.6-3.2 BULLET-TIME ORBIT. Time freezes on the detonation; camera arcs 180 degrees through the suspended shard field, threading between fragments, debris hanging in reverse gravity. Motion resumes as the arc completes.
3.2-4.8 TOP-DOWN CRANE. Bird's eye directly above; shards lock edge-on into a ring around her, then the camera drops fast down the vertical axis into a low hero angle as the ring fires outward.
4.8-6.6 MIRROR PORTAL, one take, no cut. Camera pushes into the reflection inside a single shard, passes through, emerges behind her at a new angle. Time-echo ghosts trail her lunge.
6.6-8.4 SPIKE. Kaleidoscope fracture splits the frame into sixfold symmetry, resolves, and duplicates of her peel out of the shard surfaces, each trailing a different accent. Max two of her in frame. Extreme dutch angle.
8.4-10.4 SAKUGA MONTAGE. One exchange per frame: line-art on flat cyan, two-color coral-teal silhouette, heavy smear frame, one-frame negative invert, full render. Debris accumulates, never resets.
10.4-12.4 ESCALATION. Camera barrel-rolls a full 360 pushing in low. A shard catches an incoming strike, splits it into spectrum, fires it back doubled — the shockwave warps the background and bends the type.
12.4-15.0 REVERSAL. Literal time reversal in slow motion. Debris rises, cracks close, light retreats, shards spiral back along her arm and flow together as liquid mercury before setting into one unbroken blade, the engraved mark resolving last. Camera eases into the exact opening framing. Final frame matches frame one.
[MOTION] Momentum over posing. Cloth, hair and coat lag every direction change. Wrist and grip rotate with the blade, weight carries through footwork. Speed ramp each beat — slow wind-up, fast snap, settle. 杜绝任何僵硬、停顿或不自然的关节角度。
[AUDIO] Every cue on the exact frame of its beat. The mix loops as cleanly as the picture. Bed: open air, bright wind, thin sustained glass resonance.
0.0-1.6 rising metallic ring, crystalline detonation on the break frame.
1.6-3.2 filtered vacuum for the frozen orbit, faint chimes and a low drone panning with the arc, rush as motion resumes.
3.2-4.8 hard glass snap on the lock frame, deep whoosh on the drop, wide fan of air as the ring fires.
4.8-6.6 pressure drop entering the shard, muffled interior tone, sharp release on the exit.
6.6-8.4 stuttering echo as the kaleidoscope splits, sub-bass swell, one chime per duplicate.
8.4-10.4 staccato impacts locked frame-for-frame to the cuts, glass cracking, blade screech, hard gate on the invert frame.
10.4-12.4 doppler roll following the barrel turn, spectral riser on the split, doubled bright impact out.
12.4-15.0 the mix runs in reverse — reversed chimes, glass reassembling, liquid metallic pour, resolving into the opening ring.
Music: glass bells and plucks in at 3.2, strings rise at 6.6, choir swell peaks at 10.4, reversing from 12.4 back into its first note. No dialogue.
[LIMITS] Max two figures. Accents as refracted light only. Effects accumulate until the reversal. All type carries its gradient. First and last frame identical, no floating type in either. Engraved mark reads CIA0, spelled exactly. No logos, watermarks, or extra subtitles. No environment. Never let the frame go dark or desaturated.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Claymation stop-motion animation
SCENE
Anthropomorphic sheep, smooth black clay face and limbs, textured white wool body, wide eyes, purple eyelids. Settings include thick green plant stalks, a dark interior tunnel, and a refuse pile featuring rusty tin cans, torn newspaper, and a large green rubber boot.
SHOT BREAKDOWN
0-4s — Close profile. The sheep pushes its head and front arm between thick green stalks, peering into a glowing hollow space.
4-8s — Low frontal angle. The sheep crawls forward on its belly through a dark environment. A glowing blue mushroom briefly illuminates the background behind it.
8-12s — Medium shot. The sheep slumps dejectedly into a pile of garbage, shoulders dropped, resting against cans and a green boot.
12-15s — The sheep suddenly sits up straight, eyes wide, lifting both front arms in a startled, alert posture.
CAMERA
Macro lens perspective, shallow depth of field. Low, eye-level angles. Quick straight cuts between the stalk entrance, tunnel interior, and trash pile. Simulated stop-motion frame rate.
LIGHTING & PALETTE
High contrast dynamic lighting. Warm golden directional glow inside the hollow tunnel. Bright neon blue accent lighting from the mushroom. Color palette: stark black, off-white, vibrant green, warm rust, charcoal.
AUDIO
Rustling thick foliage, sliding friction on dirt. Dull thuds, metallic clanks, and paper crinkles. Plucky, curious pizzicato string music. No dialogue.
AVOID
Photorealism, flat 2D animation, smooth 60fps CGI motion, human subjects, clean modern environments.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D anime chibi fantasy RPG video game
SCENE
Floating circular stone arena above clouds. UI overlays including health bars, a "TURN 1" banner, and an "END TURN" button. Six chibi anime characters in animal kigurumi costumes stand on glowing hexagonal tiles.
SHOT BREAKDOWN
0-4s — Static wide shot of the arena. Three stylized playing cards slide into view at the bottom edge.
4-8s — The center card rises. A massive, glowing golden spirit beast manifests over the left-side characters.
8-12s — A glowing red and white shield forms in front of the right-side lion character. Floating "-120" text pops up above the right team amidst rising ground mist.
12-15s — A pink magical slash impacts the right team, generating "-128" and "-150" text. A glowing torii gate appears. The top banner updates to "TURN 2" and right-side health bars deplete.
CAMERA
Fixed high-angle wide shot, imitating a static video game perspective. Zero camera movement or cuts.
LIGHTING & PALETTE
Bright daytime sunlight, soft volumetric clouds. Cool stone grays, bright cyan and neon red UI accents, gold and magenta magical VFX.
AUDIO
Upbeat fantasy orchestral music. UI card-slide clicks, magical conjuration chimes, and energetic impact sound effects during the attack.
AVOID
Photorealism, live-action, shaky camera, dramatic shadows, dynamic camera tracking, realistic human proportions.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 2D animated cartoon, vibrant flat colors, thick outlines, comic book style
SCENE
Red-haired man with a scowling expression. He wears a yellow puffer jacket with a green fur hood and smiley face patches, blue jeans, and mismatched high-top sneakers (one pink/purple, one yellow/green). Setting: stylized city street with brightly colored buildings, clear blue sky, puffy white clouds, and a distant clock tower.
SHOT BREAKDOWN
0-4s — Skater rides down the street, trailing stylized blue and yellow flames from the skateboard wheels. Framed as a low-angle tracking shot beside him.
4-8s — Skater continues riding past colorful storefronts, including a green shop with a "BAD OZA" sign. The camera tracks slightly ahead.
8-12s — Extreme close-up on the mismatched sneakers on the skateboard deck. Thick blue and yellow flames erupt dramatically from the wheels.
12-15s — Cut to a high-angle tracking shot behind the skater, following him down the center of a dashed road toward the clock tower.
CAMERA
Dynamic tracking movement. Utilizes low-angle profile shots, cuts to an extreme close-up, and finishes with a trailing shot. Smooth, continuous forward momentum.
LIGHTING & PALETTE
Flat, bright daytime illumination. Highly saturated color palette. Dominant bold colors: mustard yellow, cyan, vibrant red, emerald green, and neon pink.
AUDIO
Rolling skateboard wheels on asphalt, rushing wind, and the crackling whoosh of fire. Fast-paced punk-rock instrumental music.
AVOID
Photorealism, 3D rendering, CGI shading, muted tones, static camera, soft edges, realistic proportions.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D fantasy CGI animation, cinematic video game trailer
SCENE
Male warrior in a blue tunic and silver chainmail, and a female warrior with flowing pink hair in red and silver armor. Ancient stone courtyard with mossy cobblestones and traditional temple architecture.
SHOT BREAKDOWN
0-4s — The warriors engage in martial arts combat, generating sweeping trails of translucent blue water and orange fire from their arms in a medium two-shot.
4-8s — They jump back into wide stances, gathering magical energy. Framed as a wide shot capturing the temple courtyard.
8-12s — They project massive elemental avatars: a large serpentine blue water dragon and a glowing fiery phoenix. The creatures fully materialize and rush toward the center.
12-15s — The avatars collide in a blinding flash. A massive shockwave of thick gray smoke and airborne stone debris obscures the scene, pushing the bracing characters to the edges of the frame.
CAMERA
Eye-level perspective, steady wide framing. Subtle pull-backs to accommodate the massive elemental creatures. Locked-off spatial axis focusing on the central clash.
LIGHTING & PALETTE
Volumetric sunlight rays piercing down through the temple roofs. High-contrast, vibrant palette: neon blues, fiery oranges, and bright pinks against muted moss greens and stony grays.
AUDIO
Martial arts whooshes, splashing water, roaring fire, high-pitched screeches, heavy bass explosion, crumbling stone, driving orchestral battle music.
AVOID
Text, watermarks, modern clothing, photorealism, shaky camera, modern architecture.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D animated anime fantasy
SCENE
Chibi anime character wearing a brown capybara costume, a green pineapple crown, and a yellow-and-green sports jersey reading "10". Sprawling, vibrant green grassy field beneath a bright blue sky filled with fluffy white clouds. Giant pink cherry blossoms.
SHOT BREAKDOWN
0-4s — Character faces a rolling hill from behind. A massive, sudden explosion of bright pink petals erupts directly from the grass, framed as a wide scenic shot.
4-8s — The floating petals magically swirl together to form a giant, translucent whale shape. The character turns to the camera and runs laterally across the meadow.
8-12s — Character surfs atop the giant flying petal whale against the sky. Cuts to a tight mid-shot of her bouncing joyfully on a soft mound of pink petals.
12-15s — Character sits laughing happily in a petal pile as blossoms rain down. Camera tracks backward as she sprints forward, trailing magical pink petal dust.
CAMERA
Dynamic and energetic. Mix of sweeping wide tracking shots for scale and tight mid-shots for character emotion. Fast-paced cut rhythm.
LIGHTING & PALETTE
Bright, high-contrast sunlight. Deep sky blue, vibrant grass green, pastel cherry blossom pink, bright yellow.
AUDIO
Wind rushing, magical whooshing during petal transformations, cheerful giggling, upbeat orchestral fantasy music.
AVOID
Photorealism, muted colors, low lighting, slow pacing, urban elements.
Huntress Confronts the White Beast `reconstructed`
15s16:9
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 2D anime fantasy, detailed cel-shaded animation
SCENE
Tribal huntress with fiery red-orange hair, bone necklace, fur-trimmed bracers, and strapped sandals. Massive white feline beast with backward-curving ridged horns and golden eyes. Dense, mossy ancient forest with thick branches.
SHOT BREAKDOWN
0-4s — High-angle. Huntress crouches silently on a thick tree branch, gripping a vine. The giant white beast prowls directly beneath her.
4-8s — Low-angle extreme close-up of a massive clawed paw stomping down, kicking up dirt. Cut to beast looking up as huntress clings to the tree trunk.
8-12s — Profile shot. Huntress drops onto a lower branch facing the creature. Mid-air action shot as she leaps aggressively toward its face, hair and clothing whipping in the wind.
12-15s — Top-down bird's-eye view. Huntress lands in the dirt clearing directly before the beast. A circular shockwave of dust ripples outward from her impact.
CAMERA
Dynamic anime framing. Mix of high-angle establishing shots, extreme low-angle close-ups, and mid-air tracking. Fast, rhythmic action cuts.
LIGHTING & PALETTE
Dappled sunlight filtering through canopy. High-contrast shadows. Deep forest greens, fiery orange, bone white, and earthy browns.
AUDIO
Forest ambience, heavy thudding footsteps, rustling foliage, dramatic orchestral action music, sharp impact boom upon landing.
AVOID
Photorealism, 3D render style, modern elements, on-screen text, sluggish pacing.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 2D anime animation, sci-fi cyberpunk action
SCENE
Giant green combat mech featuring orange safety stripes and "02" painted on the chest plate. Cyborg woman with flowing black hair, oversized orange jacket, white crop top, beige cargo pants, metallic arm, and robotic leg. Ruined city street filled with concrete rubble and abandoned cars.
SHOT BREAKDOWN
0-4s — The heavy mech steps forward through the urban debris, carrying a massive black assault rifle. Framed at a low angle.
4-8s — The mech raises the rifle and fires, generating a bright yellow muzzle flash. Framed as a medium wide shot.
8-12s — The cyborg woman sprints directly toward the lens. A massive fiery explosion erupts in the background behind her. Tracking shot.
12-15s — The woman leaps high into the air and violently punches the mech's sensor head. A bright impact flash occurs, followed instantly by shattering metal and flying debris. Dynamic mid-air framing.
CAMERA
Low-angle perspective emphasizing scale. Tracking camera pulls backward during the sprint sequence. Fast cuts. Dynamic action framing with exaggerated perspective.
LIGHTING & PALETTE
Dusk lighting under a cloudy evening sky. Dominant olive green, warm orange, and muted concrete grey. High contrast points illuminated by bright yellow fire and explosive energy.
AUDIO
Heavy mechanical stomping, rapid automatic gunfire, deafening explosive blasts, metal shattering. Upbeat, fast-paced electronic rock music.
AVOID
Photorealism, static framing, clean pristine environments, completely biological human anatomy, slow motion pacing, real-world branding.
Duration: 15 seconds | Aspect ratio: 21:9 | Style: 2D anime, dark supernatural thriller
SCENE
Man in grey suit and tie with briefcase. Pale woman with long black hair in school uniform. Nighttime train platform, train interior with green seats, dark grassy embankment.
SHOT BREAKDOWN
0-4s — Man looks at phone on empty platform. Woman stands facing the tracks. Train arrives with blinding headlights, blowing her hair.
4-8s — Doors open. Cut to interior. Man and woman sit quietly on opposite benches in an empty carriage.
8-12s — Man leans forward to touch her knee. She smiles with pale, sunken eyes. Sudden cut to chaos: panicking passengers flee toward the camera as a dark, shadowy entity attacks.
12-15s — Man crashes backward through the train window, shattering glass. He tumbles down a grassy embankment next to the moving train. Bruised in the grass, he looks up as the woman crawls toward him, smiling ominously.
CAMERA
Static mid-shots and low angles build tension initially. Abrupt switch to erratic, fast-paced cuts and shaky handheld movement during the supernatural attack and fall.
LIGHTING & PALETTE
Harsh fluorescent station lights, blinding white train headlights. Desaturated cool palette: teal, concrete grey, muted greens, deep blacks. Bright orange sparks during the fall.
AUDIO
Low ambient hum, loud rushing wind, screeching train brakes, shattering glass, chaotic screams. Ominous, low-frequency droning music.
AVOID
Daylight, warm color grading, 3D rendering, realistic textures, slow-motion action, cheerful expressions.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D needle-felt stop-motion animation, diorama
SCENE
Round orange plush anglerfish with blue spots, large black eyes, and a glowing head-lure. Felt-textured underwater environments featuring vibrant corals, a wooden shipwreck, glowing crystals, and volcanic vents.
SHOT BREAKDOWN
0-4s — The orange felt fish swims rightward across a bright coral reef. A green turtle and tiny blue fish swim below in the sunlit water.
4-8s — The fish navigates a wooden shipwreck alongside a pink octopus and grey seal, then enters a dark rocky cave illuminated by glowing crystals and bioluminescent squid.
8-12s — Exiting the cave, the fish encounters a striped fish, then swims over glowing orange magma vents. Small crabs crawl below while manta rays glide above.
12-15s — After passing a yellow spiked pufferfish near the vents, the orange fish enters a sunny kelp forest. It turns to face the camera directly, centered symmetrically as bubbles rise.
CAMERA
Smooth, continuous tracking following the fish's journey. Slow, steady horizontal pans. Concludes with a static, centered close-up.
LIGHTING & PALETTE
Top-down volumetric sun rays, soft bioluminescent point lights, and warm under-lighting from magma. Deep oceanic blues, vibrant coral pinks, fiery oranges.
AUDIO
Subtle underwater bubbling, muffled water flow ambience, whimsical instrumental background music.
AVOID
Photorealism, sharp CGI edges, human characters, camera shake, text.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: 3D animated sci-fi fantasy
SCENE
Small, furry red creature with a feline face, glowing cyan horns, and translucent cyan wings. Futuristic nocturnal city featuring sweeping, curved metallic skyscrapers. Calm, mirror-like waterway. Starry night sky displaying a vibrant Milky Way.
SHOT BREAKDOWN
0-4s — Creature speeds past sleek curved buildings; framed in tight profile with edge motion blur.
4-8s — Creature ascends steeply toward a towering, illuminated skyscraper; framed from a low rear angle highlighting its glowing cyan spine.
8-12s — Creature glides horizontally over glassy water; framed directly from behind, tracking its flight toward distant city arches.
12-15s — Transitions from a wide lateral tracking shot past giant structural rings to a hovering, front-facing close-up of the creature smiling directly at the lens.
CAMERA
Dynamic drone tracking. Fast fluid movements shifting from tight profiles to wide rear-follow shots. Wide-angle lens with deep depth of field. Continuous single-take motion.
LIGHTING & PALETTE
Nighttime ambient starlight paired with neon city glow. Deep indigo sky, bright luminescent cyan, warm golden-yellow interior building lights, vibrant ruby-red fur. Polished specular reflections on water and metallic architecture.
AUDIO
Wind rushing. Soft magical chiming synchronized with wing flaps. Serene, wondrous orchestral synth music. Low ambient hum of a futuristic metropolis.
AVOID
Daylight, jagged architecture, human figures, typography, realistic animals, static camera, muted colors.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: 2D anime animation, vibrant fantasy adventure
SCENE
Anime female character, red hair with an orange ponytail, purple eyes. Wearing a tribal black bikini top, white midriff wrap, yellow sash, green slit skirt, beaded necklace, fur arm cuffs, and strappy sandals. Standing on the back of a giant flying blue whale adorned with coral, barnacles, and seaweed. Background is a bright sky with large white cumulus clouds.
SHOT BREAKDOWN
0-4s — Full shot. Character begins a joyful dance on the whale's back. Aerial camera tracks forward slowly.
4-8s — Medium shot. Character sways her hips, touches her head, and extends her arms. Hair blows dramatically in the wind.
8-12s — Medium-full shot. Energetic dancing continues with rhythmic arm waving and swaying. The whale glides steadily through the sky.
12-15s — Full shot. Character throws her arms wide in a final cheerful pose. Camera pulls back slightly to reveal the whale's scale.
CAMERA
Aerial tracking shot, dynamic push-in and pull-out, steady medium-to-wide framing, smooth floating movement matching the flight path.
LIGHTING & PALETTE
Bright midday sunlight, soft cinematic anime shading. Sky blue, vibrant teal, crimson, earthy yellow, and bright white.
AUDIO
Upbeat fantasy instrumental music, rushing wind ambiance, faint majestic whale calls.
AVOID
Photorealism, dark lighting, modern clothing, erratic camera shake, visible text.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 2D anime animation, high-octane action
SCENE
Female anime warrior, deep magenta hair in a high ponytail, glowing pink eyes, black tactical bodysuit, silver shoulder armor, dark thigh-high boots, wielding a massive curved katana. Setting is a barren, desolate rocky wasteland under heavy dark storm clouds.
SHOT BREAKDOWN
0-4s — Extreme wide shot of the tiny figure in a dark, rocky valley. Quick cut to an intense, dynamic close-up as she readies her katana. Bright blue lightning arcs violently across the frame.
4-8s — Low-angle perspective looking directly up the broad, metallic sword blade. She leaps through the air, surrounded by heavy, glowing blue energy trails and motion blur.
8-12s — Mid-air framing against a swirling, vortex-like cloudy sky. Extreme close-up of her face showing fierce determination, lips parted in a shout, eyes glowing.
12-15s — Full body shot floating high in the dark sky, raising her sword to gather power. A massive, screen-filling vertical pillar of blue lightning strikes the rocky ground below.
CAMERA
Dynamic anime combat framing. Extreme low angles, Dutch tilts, and extreme close-ups. Fast cut rhythm, high-speed tracking, forced perspective highlighting the sword.
LIGHTING & PALETTE
Dark, moody atmospheric lighting. High-contrast neon illumination driven by magical effects. Midnight blues, charcoal greys, deep magenta, and blinding electric cyan.
AUDIO
Howling wind ambiance, sharp metallic blade swooshes, heavy electrical crackling, massive explosive bass drop. Fast-paced, driving electronic-orchestral battle music. Wordless animated battle cry.
AVOID
Photorealism, live-action humans, bright daylight, modern urban settings, slow pacing, static camera.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D anime cel-shaded animation, high-octane action sequence
SCENE
Blonde female warrior in a bright orange military trench coat and black boots. Hooded antagonist in a tattered grey cloak. Desolate concrete platform against an industrial overpass under a clear blue sky.
SHOT BREAKDOWN
0-4s — Panning across empty concrete to reveal the warrior clashing a glowing green energy blade against the antagonist's black smoke weapon in a fast-paced medium shot.
4-8s — The antagonist unleashes a linear blast of black energy. Framed wide as the warrior steps back, cutting to a high top-down aerial perspective of the combatants circling.
8-12s — Over-the-shoulder view behind the antagonist wielding a solid black sword. Cuts to a low, tilted angle as the hooded figure swings the dark blade with intense motion blur.
12-15s — Wide shot. The warrior counterattacks with a massive, sweeping neon green energy arc that impacts the ground and the antagonist, kicking up a thick cloud of dust.
CAMERA
Dynamic sweeping movements. Rapid cuts between extreme low angles, over-the-shoulder views, and top-down tracking shots. Pronounced motion blur on weapon swings.
LIGHTING & PALETTE
Bright, high-contrast sunlight. Vibrant orange and neon green contrasting sharply with muted greys, stark black energy shadows, and a flat blue sky.
AUDIO
Wind ambience, sharp metallic clashes, deep bass whooshes for magical energy attacks, rumbling impact debris. High-tempo, aggressive action score.
AVOID
Photorealism, slow pacing, static camera, soft focus, text, watermarks.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: 3D stylized chibi animation, monochromatic cinematic realism.
SCENE
Rainy Parisian street at night. A covered bus stop with a wooden bench. Two stylized chibi characters: a woman with a black bob in a white trench coat, and a man with slicked hair in a black double-breasted overcoat.
SHOT BREAKDOWN
0-4s — Title text over a blurred rainy street: "アンリとコレットの 愛のドラジェ HENRI ET COLETTE Les Dragées de l'amour". Cuts to a wide shot of the man and woman sitting apart on the bench.
4-8s — Medium close-up of the woman looking down, then looking up. Cuts to an over-the-shoulder shot of the man reacting.
8-12s — Close-up of the woman smiling. Returns to the wide shot of both characters sitting together on the bench.
12-15s — Sequence of three black title cards with white text. First: "アンリとコレットの 愛のドラジェ HENRI ET COLETTE Les Dragées de l'amour". Second: "ep.1「傘のない恋人」 Les Amants sans parapluie". Third: "ててつろう × Hailuo".
CAMERA
Static camera, shallow depth of field, standard shot-reverse-shot dialogue cut rhythm.
LIGHTING & PALETTE
Low-key atmospheric lighting, soft ambient streetlamp glow. Desaturated cool palette, dominated by black, white, and silver-gray.
AUDIO
Heavy rain ambience, melancholic piano music.
AVOID
Photorealism, vivid colors, dynamic camera movement, cluttered backgrounds.
Duration: 15 seconds | Aspect ratio: 21:9 | Style: 2D anime-style animation, cyberpunk aesthetic
SCENE
Young woman, black high ponytail, oversized orange puffer jacket, black crop top, crossbody bag, facial markings. Young man, dark hair, black tactical suit with red and blue accents. Futuristic neon city streets, curved cabin with teal seating, subway station, massive glowing circular tunnel, concrete debris.
SHOT BREAKDOWN
0-4s — Woman stands on a wet street surrounded by cars and glowing signs, one vertical sign reading "HZN NO". Cut to man sitting on a teal bench in a curved cabin, red skies visible through porthole windows.
4-8s — Man shifts gaze right. Cut to a rapid forward POV flight through a dense city canyon of glowing neon skyscrapers.
8-12s — Woman stands confidently on a station platform, hair blowing as a train blurs past her left. Cut to man standing in a heavily neon-lit outdoor station with poster-covered columns.
12-15s — Tracking shot from behind the man and woman as they stand side-by-side, facing a massive, glowing, multi-colored circular tunnel structure surrounded by scattered rubble.
CAMERA
Eye-level mid shots, rapid forward motion POV, fast-paced rhythmic editing. Shallow depth of field during character portraits, wide expansive angles for environments.
LIGHTING & PALETTE
High-contrast neon illumination, glowing atmospheric haze, wet ground reflections. Highly saturated red, cyan, vibrant teal, bright orange, deep black shadows.
AUDIO
Heavy cyberpunk synthwave music track, ambient rain splashing, rushing train whoosh, low atmospheric electric hum.
AVOID
Photorealism, 3D CGI rendering, muted colors, pastel palettes, static cinematography, plain backgrounds, illegible floating text.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Mixed media, photorealistic live-action blended with glowing 2D vector animation
SCENE
Human hands, rustic wood kitchen counter, stainless steel sink, ceramic mug, metal spoon, striped towel, window. Overlaid with glowing 2D animated flora and fauna.
SHOT BREAKDOWN
0-4s — Open palm holds a glowing animated green sprout. Camera pans right along the sunlit counter to a neon green animated caterpillar crawling near a spoon and mug.
4-8s — Animated green paper plane arcs from a glass bottle to the mug. Cut to a hand reaching toward an animated orange goldfish floating mid-air over a dark sink.
8-12s — Panning past a folded yellow-striped towel, revealing an animated green-and-pink snail, followed by a glowing orange animated circle resting on the fabric.
12-15s — Camera faces a window framing a sunset landscape, heavily overlaid with glowing animated orange flowers. A hand enters the foreground, pinching a bright animated green leaf.
CAMERA
Intimate macro close-ups, smooth lateral panning, organic handheld motion, shallow depth of field.
LIGHTING & PALETTE
Warm golden hour sunlight, sharp diagonal window shadows. Earthy browns and warm whites contrasted against neon green, bright orange, and glowing pink animations.
AUDIO
Quiet room tone, soft magical synth chimes for the animated elements, mellow acoustic guitar melody.
AVOID
Photorealistic CGI creatures, fully animated backgrounds, flat lighting, sterile environments, erratic fast cuts.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Anime pop-art illustration, graphic design aesthetic with halftone shading and kinetic typography
SCENE
Anime schoolgirls (tan blazers, black plaid skirts, thigh-high socks, berets, diverse hair colors). Graphic urban transit settings including bus stops, crosswalks, and vivid on-screen text blocks.
SHOT BREAKDOWN
0-4s — Brown-haired girl applies makeup ("Lip gloss, bus stop"). Pink-haired girl by a clock ("Tick-tock, don't stop"). Silver-haired girl holds a drink ("Ice cup, touch down"). Brown-haired girl with headphones ("Headphones, downtown"). Pink-haired girl on a dark bus ("Late text, heartbeat").
4-8s — Silver-haired girl crosses street ("Two steps, same street"). Brown-haired girl shields eyes ("Flashback, Flash light"). Pink-haired girl poses ("You look so right"). Silver-haired girl runs ("Maybe we're running"). Brown-haired girl jumps ("Maybe we're flying").
8-12s — Pink-haired girl by a sign ("No need explaining"). Silver-haired girl on a bench ("We're just vibing"). Brown-haired girl slides ("Slide, glide"). Pink-haired girl reaches forward ("Meet me on the bright side"). Silver-haired girl under spotlights ("Slow lights").
12-15s — Brown-haired girl rests on a bench ("Everything feels"). Pink-haired girl by a transit sign ("High tide"). Silver-haired girl looks through a ring ("Keep me in your eyesight"). Brown-haired girl walks ("Good vibe"). Trio poses together at night ("Play it back all night").
CAMERA
Fast-paced montage. Static framing with 2D perspective. Rapid rhythmic cuts between graphic poses.
LIGHTING & PALETTE
Flat graphic lighting, stylized halftone dot shadows. Retro color palette: mustard yellow, navy blue, burnt orange, pale teal, dusk purple.
AUDIO
Upbeat J-pop or rhythmic electronic track. No dialogue.
AVOID
Photorealism, 3D rendering, complex gradients, cinematic depth of field, illegible text.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Surreal fantasy animation blending stylized 3D environments with 2D character illustration
SCENE
A short-haired traveler in black clothing explores a mystical alien jungle filled with giant trumpet fungi, translucent glowing pink mushrooms, surreal hybrid creatures, and whimsical 2D spirits.
SHOT BREAKDOWN
0-4s — Wide tracking shot of the traveler walking through a lush fungal forest, cutting to a medium shot as they pluck and eat a piece of a soft, translucent pink mushroom.
4-8s — Macro close-up on the traveler's wide hazel eyes dappled in light caustics, cutting to wide blooming mushrooms releasing pink vapor, then tracking a living one-eyed porcelain teapot creature walking on bird feet.
8-12s — Medium shot of a moss-backed hippo-snail hybrid blinking slowly, transitioning to three flat 2D cartoon creatures (a one-eyed quadruped, a round pink blob, and a green seedling) scurrying across a mossy log.
12-15s — Over-the-shoulder view of the traveler watching the floating 2D spirits among massive banyan roots, cutting to a black screen displaying the white logo and text "路西 STUDIO LUCY.D.XIE".
CAMERA
Smooth side-scrolling tracking, tight macro focal depth for facial close-up, static character framing, rhythmic montage cuts.
LIGHTING & PALETTE
Diffused forest canopy light, soft dappled caustics, bioluminescent pink glow. Palette of moss green, coral red, blossom pink, earthy brown, and porcelain blue.
AUDIO
Rustling leaves, soft squelching bite, ethereal shimmering chime, whimsical animated creature squeaks, silent final cut.
AVOID
Photorealism, urban elements, modern machinery, harsh neon lighting, rapid shaky camera.
Claymation. A whale breaches from a stormy clay sea and rises in a slow-motion arc above the waves, body fully extended, water sheeting off its flanks. At the top of the arc it rolls onto one flank, hangs for a beat, then falls back toward the surface. Midair, the camera sweeps beneath its belly in a bold dynamic move, revealing the vast churning ocean far below and the full stretch of its clay body against the sky, then holds as it crashes down and white clay foam bursts outward across the frame. Visible fingerprints, tool marks, and material imperfections in the clay. Slightly stepped, handmade movement. The sea is sculpted clay with rolling modelled waves and white clay foam. Audio: a deep rush of water, wind, the dull slap of clay on clay, distant gulls. Composition: subject centered, action contained within the central third of the frame.
Using the attached reference image for the character and the attached audio track for timing, generate a jazz-noir anime title sequence in a stylized pop-art style. Every cut must land exactly on a beat of the audio — treat the track as the edit timeline.
VISUAL STYLE — apply throughout:
Render characters as flat, high-contrast black silhouettes against solid single-color backgrounds (saturated red, mustard yellow, deep blue). No naturalistic shading — each shot commits to one or two dominant colors only, like a screen-printed poster.
Compose shots like comic-book panels and pulp-magazine covers: bold panel divisions splitting the frame, hard geometric shapes, dramatic off-center cropping, extreme close-ups intercut with full-body poses.
Use freeze-frames as a core device: the character hits a dynamic pose (drawing a weapon, mid-stride, lighting a cigarette, turning toward camera) and the frame HOLDS completely still for one full beat before cutting. Do not smooth or interpolate through these holds — they must be dead stops.
Title typography in mid-century Saul Bass style: stark geometric letterforms, bold sans-serif, text that slides in as flat colored bars or snaps into frame on the beat.
Overlay the entire sequence with heavy analog film grain, slight gate weave, and worn-print color texture — it should look like a scratched 35mm print of a 1960s jazz album cover, not clean digital animation.
MOTION AND EDITING:
Alternate between two modes — (1) fast kinetic bursts of motion (whip pans across silhouettes, rapid cut sequences, a silhouette sprinting across a solid color field) and (2) hard freeze-frame holds. The contrast between the two IS the rhythm. Cuts are hard cuts only: no dissolves, no fades, no morphing between shots. Each new shot snaps in on the downbeat with a fresh background color.
End on the character in silhouette, frozen mid-pose against a solid red field, with the title card snapping in beside them on the final hit of the track.
{ "clip_id": "animated_adventure", "genre": "3D Animation / Pixar Style", "total_duration": "15s", "aspect_ratio": "16:9", "style_keywords": "Pixar-style 3D animation, vibrant colors, expressive characters, cinematic lighting, whimsical, high detail textures", "shots": [ { "shot_num": 1, "duration": "4s", "prompt": "Wide shot of a tiny adventurous mouse wearing a leather aviator cap standing on the edge of a giant mushroom in an enchanted forest, giant flowers towering overhead, Pixar-style 3D animation, vibrant colors, soft cinematic lighting", "camera": "low angle push in", "transition": "hard cut" }, { "shot_num": 2, "duration": "4s", "prompt": "Medium shot of the mouse launching into the air on a dandelion seed parachute, floating through sunbeams, pollen particles sparkling around, joyful expression, 3D animated film style, warm golden light", "camera": "tracking shot from below", "transition": "match cut on motion" }, { "shot_num": 3, "duration": "4s", "prompt": "Dynamic action shot of the mouse swooping through a hollow log, fireflies lighting the way, exaggerated squash-and-stretch animation, motion blur on background, Pixar-style adventure sequence", "camera": "POV following through tunnel", "transition": "whip pan" }, { "shot_num": 4, "duration": "3s", "prompt": "Wide shot of the mouse landing triumphantly on a lily pad in a moonlit pond, ripples spreading outward, bioluminescent plants glowing, 3D animation, magical atmosphere, satisfied smile", "camera": "crane shot rising up", "transition": "end" } ] },
3D Pixar-style animated comedy short film, ultra-premium feature film quality, highly expressive facial animation, cinematic storytelling, cozy modern kitchen, warm golden lighting, realistic global illumination, shallow depth of field, ultra-detailed textures, realistic hair simulation, emotional acting, cinematic camera movement, smooth multi-shot sequence, fast-paced visual comedy, no text, no subtitles, no watermark.
A bright, cozy modern kitchen during the afternoon. Warm sunlight streams through the windows. A young woman with long messy dark hair, oversized expressive brown eyes, freckles, wearing an oversized black T-shirt and house slippers, walks into the kitchen carrying a mug.
She suddenly freezes.
On the white marble kitchen island sits an enormous cartoon-style spider about the size of a football. It has fuzzy black legs, oversized expressive eyes, and an intimidating stare.
Shot 1: Wide cinematic shot. The woman and giant spider lock eyes from opposite sides of the kitchen island. Everything becomes still.
Shot 2: Extreme close-up of the woman's face. Her pupils shrink. Sweat forms on her forehead. Her breathing becomes rapid. Tiny facial micro-expressions show pure panic.
Shot 3: Extreme close-up of the spider. It slowly raises its front legs, narrows its eyes, and curls its fangs into a confident grin as if challenging her.
Shot 4: Medium shot. The woman slowly reaches toward a nearby frying pan without taking her eyes off the spider. Her hand trembles violently.
Shot 5: Close-up of her gripping the frying pan with both hands. Her knuckles turn white from fear.
Shot 6: Wide shot. She nervously points the frying pan toward the spider like a shield while cautiously stepping backward.
The spider suddenly takes one slow step forward.
The woman gasps.
Another step.
She screams.
Shot 7: Low-angle shot from behind the spider, making it appear huge while the frightened woman backs away across the kitchen.
The spider tilts its head and smirks mischievously.
The woman gathers all her courage, raises the frying pan high above her head, and charges toward the spider with a terrified battle cry.
Just before she swings—
The spider suddenly spreads its legs, launches into the air, and leaps directly toward the camera.
The woman instantly drops into a crouch, covers her head with both hands, and screams in terror.
Freeze on the spider flying through the air toward the viewer.
End of first 15 seconds.
Ultra-detailed Pixar-quality animation, expressive facial acting, dynamic cinematic camera work, alternating wide shots and extreme close-ups every 1–2 seconds, emotional comedy timing, smooth character animation, premium lighting, blockbuster animated short-film quality, perfect character consistency, viral social-media storytelling.
This ending creates a strong cliffhanger for the extension, where an unexpected hero can arrive and flip the situation into comedy.
Static locked-off camera, no zoom, no pan, no handheld drift. The frame never moves. Open on an empty landscape: flat azure sky, six soft cumulus clouds drifting slowly, a band of ochre and green eroded hills along the bottom. Nothing else. Hold this for a beat. Then the composition assembles itself, piece by piece, in surreal stop-motion cadence: First, a torso rises into frame from the bottom edge: a man in a flecked brown tweed jacket, white collar, dark tie. It settles and locks. Above the collar, a vertical column starts growing upward from nothing: dark earth, roots, dried vegetation and moss, building like soil stacking against gravity. Chunks fly in from the frame edges and snap into the column with weight: coral and fungal growths in salmon pink, chartreuse and rust from above; a large blue elephant head with a visible eye and pale tusks sliding in from the right; branching red vascular coral whipping in from the right edge. The face parts land last and land hard: a huge glossy red fleshy mouth with white teeth locks into the lower half, its trunk-like red tongue curling into a tight loop; a second inverted red mouth snaps into the upper half. Final details settle: a brown and orange moth wing unfolds at the upper right, small pink petal-like slices freeze mid-flight on the left with fine particles suspended around them, a small blue elephant figure tucks into the crown. The clouds keep drifting behind and through the structure the entire time, unbothered. Everything comes to rest in a still, balanced composition. Only the clouds move. Photoreal 3D render, hyperreal wet organic surfaces, hard midday light, deep saturation, crisp shadows. Surrealist portrait, Magritte staging. 12 seconds, 5:6 vertical.
Style: Hyper-realistic dark fantasy tavern cinematic, grounded physical combat, realistic body momentum, medieval atmosphere, gritty lighting, practical effects, handheld cinematic camera, physically accurate movement, ultra-detailed textures, realistic collisions and environmental interaction.
Duration: 15 seconds
Aspect Ratio: 16:9
IMPORTANT:
Keep the SAME characters fully consistent with the reference: 📷Image1
— Nyssa: athletic woman, dark curly hair tied back, bronze leather armor, cloth wraps, sword on hip
— Grok: massive muscular green orc, scarred skin, fur armor, heavy axes, large physical weight
Combat MUST obey realistic physics:
— no floating
— no anime flips
— realistic inertia and recovery
— believable weight transfer
— realistic impacts and exhaustion
— grounded footwork
— environment reacts physically to impacts
[00:00-00:02]
Wide cinematic shot inside a crowded medieval tavern filled with drunk mercenaries, candles, smoke, spilled ale, and loud cheering. Nyssa walks through the tavern cautiously while patrons stare. Grok sits at a massive wooden table drinking heavily. Deep bass-heavy tavern music and crowd ambience.
[00:02-00:04]
Close-up tension sequence:
— Nyssa locks eyes with Grok
— Grok slowly stands, towering over everyone
— benches scrape across the floor
— mugs shake from his weight
— crowd forms a fighting circle cheering loudly
Handheld camera movement feels realistic and grounded.
[00:04-00:07]
The fight erupts violently. Grok swings a heavy punch with believable momentum. Nyssa narrowly dodges while stumbling realistically into a wooden table. Wood cracks and splinters physically on impact. She counters with fast grounded strikes to Grok’s ribs and legs. Crowd roars and throws coins and mugs into the air.
[00:07-00:10]
Combat intensifies through the tavern:
— Grok grabs Nyssa and throws her across a table
— table explodes realistically beneath her weight
— Nyssa rolls across the floor recovering naturally
— Grok charges heavily, smashing furniture
— patrons jump away realistically
No exaggerated movement, only physically believable combat.
[00:10-00:12]
Nyssa uses speed and positioning intelligently. She dodges another heavy attack causing Grok to crash into a support beam. Dust and debris fall from the ceiling. She climbs briefly onto the bar counter and leaps down with controlled realistic momentum, locking Grok’s arm and using leverage to throw him off balance.
[00:12-00:15]
Final cinematic climax. Nyssa tackles Grok to the ground hard onto broken wooden debris. The floor shakes from the impact. She pins him down on top of him while holding a blade near his throat. Grok struggles realistically beneath her massive weight difference and exhaustion. Tavern crowd erupts cheering wildly, slamming mugs against tables. Camera slowly pushes inward on Nyssa breathing heavily while sweat, dirt, and candlelight flicker across both fighters.
Audio:
Heavy cinematic tavern battle soundtrack with deep drums, loud cheering crowds, breaking wood, metal impacts, realistic body hits, roaring fire ambience, mugs crashing, heavy footsteps, and gritty medieval atmosphere.
Negative prompts:
No floating, no anime combat, no superhero physics, no unrealistic flips, no weightless motion, no blurry characters, no low detail, no cartoon style, no slow reactions, no clipping through objects.
Ultra cinematic AAA adventure game trailer, one continuous seamless camera shot, Unreal Engine 5 quality, hyper realistic, 60 FPS, cinematic lighting, premium animation, realistic physics, smooth transitions, no text, no logo. The camera begins behind a young silver-haired explorer and his fluffy orange cat standing together on a giant ancient tree branch overlooking a breathtaking futuristic nature city in the year 2100. Giant waterfalls flow through floating islands, enormous glowing trees surround eco-friendly futuristic towers, flying drones move naturally between the trees, distant floating platforms connect the landscape, soft volumetric sunlight fills the valley, leaves gently drift through the air, birds fly across the sky, mist slowly rolls through the forest. Far away, a colossal ancient guardian peacefully walks through the valley between giant trees, partially hidden by fog, creating mystery and wonder. The explorer and his cat quietly observe the distant guardian. After two seconds, the explorer slowly raises his left hand. He gently touches the glowing wrist device on his arm. A soft circular pulse of blue light expands through the air. Elegant transparent holographic interface panels smoothly appear around him with premium glass animation. The interface feels futuristic, clean and luxurious. Panels gracefully float into position using smooth spring motion. Explorer Inventory. Adventure Gear. Explorer Suit. Accessories. Energy Tools. Skills. Artifacts. Companion Gear. Quest Journal. Player Statistics. Beautiful holographic cards slowly rotate in space. Crystal accessories sparkle. Energy gadgets softly glow. Explorer suit pieces rotate in three dimensions. Energy bow slowly turns with animated light effects. The cursor appears naturally with smooth realistic movement. It selects the glowing Energy Bow. The selected card enlarges slightly. The bow transforms into blue light particles and gracefully flies onto the explorer's back. A quiver of glowing energy arrows materializes beside it. Next the explorer suit activates. Shoulder pieces. Chest protection. Explorer gloves. Travel boots. Utility belt. Crystal rings. Energy necklace. Each item gently assembles onto the explorer with elegant magnetic energy effects. Blue energy flows through every piece as it activates. The cat watches curiously. The cursor opens Companion Gear. A lightweight explorer harness, glowing collar, utility backpack and protective accessories gently assemble onto the cat. The cat happily stretches, shakes its body and looks proudly toward the valley. The holographic interface slowly dissolves into glowing particles. The environment becomes quiet again. The explorer reaches for the glowing Energy Bow. The cat lowers into an excited ready position. They exchange a quick glance. Without hesitation they begin running together across the giant tree branch. The camera follows closely from behind with cinematic motion. At the edge of the branch they leap together into the breathtaking futuristic valley. The explorer's cape flows dramatically in the wind. The cat glides gracefully beside him. Leaves swirl around them. Flying drones pass overhead. The waterfalls rush below. The camera follows their descent through the incredible landscape. In the distance, the colossal guardian slowly turns its head after sensing their arrival. The adventure has only just begun. Fade to black. Premium PlayStation first-party game trailer quality. Natural facial animation. Realistic cloth simulation. Dynamic hair physics. Cinematic camera movement. AAA environmental storytelling. Award-winning game cinematic. Seamless single take. No combat. No violence. Focus on exploration, discovery and adventure.
15-second cinematic stop motion animation in handcrafted paper cut style. Everything is physically assembled by invisible hands, one element at a time. Every object appears with authentic stop motion timing, tiny frame imperfections, subtle paper wobble, handmade placement, slight camera vibration, natural easing, tactile textures, soft shadows, and realistic depth. Nothing fades or morphs. Every piece is manually placed into the scene exactly like a professional stop motion production.
Scene begins with an empty dark navy paper background only.
0-2s
Large crumpled blue paper sheets slide in from every edge and are pressed into place one after another, forming the underwater cave walls.
2-4s
Paper coral pieces appear individually from the bottom. Red coral, green seaweed, beige coral, pink coral, shells, pebbles and tiny bubbles are carefully placed one by one with visible handcrafted motion.
4-6s
The glowing jellyfish is lowered from above. The bell lands first, then each tentacle is attached individually, gently bouncing. The jellyfish softly floats with slow natural stop motion movement.
6-8s
The paper astronaut child slides into frame from the left. The body arrives first, then the helmet is placed on top with a tiny bounce. One arm rotates slightly as if reaching forward.
8-10s
The white cat appears from below. The body is placed first, then the transparent helmet is carefully attached afterward. The tail makes a tiny handmade wiggle.
10-12s
Small paper bubbles are added individually around both characters. Each bubble pops into place with slight stop motion jitter. The child and cat gently drift upward a few millimeters.
12-15s
The complete underwater world comes alive. The jellyfish slowly pulses. Tentacles sway naturally. Sea plants lightly oscillate. Tiny bubbles continue rising. The astronaut child and cat subtly float together while holding position. Warm glow from the jellyfish softly illuminates nearby paper textures. Camera performs a slow cinematic push-in with realistic macro depth of field.
Premium handcrafted stop motion, museum-quality paper art, tactile cardstock textures, realistic layered paper thickness, authentic frame-by-frame animation, tiny alignment imperfections, soft studio lighting, cinematic composition, macro photography, volumetric lighting, ultra detailed, emotionally warm, professional stop motion film, 15 seconds, no text, no watermark.
A documentary about a superhero who has extremely bad luck and ends up saving people by accident through the destruction caused by his own misfortune. Dialogue in English. Scene direction with unique composition. Every cut, every camera angle, and every movement is of exceptionally high quality; the composition is guided by an experienced film director. The comedy is genuinely interesting, and throughout the 15 seconds everything unfolds in a perfectly crafted way, with a comedic payoff that can make anyone laugh.
Pure kinetic motion graphics from frame one. No scenes, no dialogue — just ink, energy and typography exploding across a void-black canvas. JJK-style aesthetic: ink splatter reveals, chromatic aberration pulses, impact freezes, speed lines.
Music: Constant tension electronic — 160BPM mechanical hi-hats, layered detuned synths, staccato string stabs. No drop, no resolution. Just relentless building pressure the entire 15 seconds.
0:00–0:01: Black ink detonations consume a white frame. Negative space forms a fragmented "V."
0:01–0:03: Purple energy slash tears the frame open. White particles rush in and assemble into character silhouette KAI — his name explodes in massive white text with cyan underline, then shatters.
0:03–0:05: Cyan geometric shards flash rapidly, ghost-forming character SEREN. Her name slams in from off-screen, cracks the frame on impact, white light bleeds through.
0:05–0:08: Text fragments of V-O-I-D strobe across white void at different sizes and rotations. Character REN appears as a single ink brushstroke — impossibly calm. His name visible only as negative space within the ink.
0:08–0:10: Full graphic meltdown — rapid-fire collage of ink explosions, overlapping character names, speed lines, a single 6-frame red flash, each letter of VOID filling the entire frame one at a time.
0:10–0:13: Purple and cyan energy streams collide center-frame, compressed into the title VOID — ultra-bold, letters split purple-left cyan-right with white fracture lines running through each. Cast names slide in below. Pulses like it's alive.
0:13–0:15: Fracture lines spread, black consumes the letters from inside. Gone.
Colors: #03020a black · #7c00ff purple · #00f0ff cyan · #ff1a1a red flash only · #ffffff fracture/text
Never: soft transitions, static frames, gradients, faces, anything gentle.
Subject
A miniature hand-drawn 2D animated boy with messy brown hair, round glasses, a blue apron, striped socks, and a tiny silicone spatula, baking cookies inside a realistic full-sized kitchen.
Style
Mixed-reality hybrid animation combining playful 2D hand-drawn doodle character art with a photorealistic live-action kitchen. Whimsical stop-motion physics, expressive line animation, exaggerated scale, warm cinematic lighting, and playful cooking sound effects.
Camera & Framing
Macro close-ups, low-angle tracking shots, overhead kitchen perspectives, dramatic push-ins, and shallow depth of field emphasizing the tiny baker against oversized kitchen objects.
Audio & Scene Breakdown
Visual: The tiny baker stands beside a giant bag of flour, trying to push it open with his little spatula. A burst of flour explodes around him like a snowstorm.
Visual: He scrambles onto the edge of a huge butter dish and slides down a stick of butter into a giant mixing bowl.
Visual: Inside the bowl, he dodges chunks of chocolate chips falling from above like boulders while cookie dough is being stirred around him.
Visual: He grabs onto a massive electric hand mixer attachment and spins in circles as the dough swirls beneath him.
Visual: He leaps out onto a baking tray and uses an oversized spoon to shape cookie dough blobs, getting comically stuck in one of them.
Visual: He rides a rolling pin like a balancing beam while trying to flatten one runaway cookie.
Visual: The camera pulls back to reveal a tray of freshly baked cookies. The tiny baker proudly places one chocolate chip on top of the biggest cookie—then the cookie suddenly cracks and tilts, sending him sliding off.
Audio: Playful kitchen ambience, flour poofs, dough squishes, mixer whirring, tray clinks, tiny footsteps, comedic impact sounds, subtle upbeat music, no dialogue.
The Girl the Automatic Door Ignores (Anime Comedy)
14s16:9
MiniMax H3 Prompt
subject_definitions:
<Subject 1> is the single female character depicted in <Picture 1>. The front, side, back, and facial views all depict the SAME person. Preserve her exact facial identity, pale green eyes, short black bob with straight bangs, raised patterned hood, red-and-silver headphones, oversized black-and-turquoise graphic jacket, shorts, patterned thigh-high socks, and chunky black boots. Keep all original clothing colors, graphic motifs, accessories, proportions, and silhouette consistent.
summary:
[reference generation] Create a 15-second, 9:16 animated comedy. <Subject 1> looks like an intimidating, powerful heroine, but a convenience-store automatic door refuses to open for her. Her increasingly awkward attempts fail. An ordinary customer approaches, and the door immediately opens. She quietly follows the customer inside while trying to preserve her dignity. Exactly three shots, one location, two characters, no dialogue.
retention_analysis:
<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - retain the character identity, costume, headphones, hairstyle, and illustrated appearance from <Picture 1>. Use the image only as a character-design reference. The white background, sheet layout, multiple views, and headings are not part of the video. Show only one instance of this character.
detailed_description:
High-detail 2D animated illustration matching the reference character's visual style, with smooth, restrained acting and consistent clothing details. The setting is a quiet Japanese convenience-store entrance at night. Warm interior light contrasts with cool blue street lighting. The entrance has two transparent glass panels that slide horizontally apart. Keep the same entrance, lighting, and spatial layout throughout. The humor comes from her serious expression and the door's refusal to cooperate. No supernatural effects.
[Shot 1]
A slightly low-angle, three-quarter exterior medium-wide shot shows <Subject 1> on the left and the closed automatic entrance on the right. Her face is visible in profile, and the glass-panel seam is clearly visible. She takes two confident steps toward the entrance, both hands in her jacket pockets, chin slightly raised, looking exceptionally cool and composed. She stops about 40 centimeters in front of the glass, directly beneath the overhead sensor. The door remains completely closed. She waits for a brief beat, then slowly looks up at the sensor. Her confidence shifts into quiet confusion. A short, dramatic electronic bass phrase accompanies her approach, then abruptly stops when the door fails to open. Footsteps and faint street ambience remain.
[Shot 2] At 00:03.000, cut to a locked, eye-level full-body shot from the same exterior side, keeping her face, boots, sensor, and entire doorway visible.
<Subject 1> remains in front of the same closed door. Without smiling, she removes her right hand from her pocket and waves it twice beneath the sensor. Nothing happens. She pauses, stares at the sensor, then makes ONE small vertical hop with both boots briefly leaving the pavement. She lands naturally in the same spot. The door still does not move. Her jacket and accessories settle after the landing. She lowers her hand, holds a stiff, dignified posture, and gives the glass a mildly offended stare. Keep each action separate and clearly readable. The audio consists of a quiet sleeve rustle, one soft landing thud, and street ambience.
[Shot 3] At 00:09.000, cut to a slightly wider exterior view of the same doorway.
<Subject 1> shifts half a step to the left, remaining outside beside the entrance with her face visible. One ordinary adult customer in a plain brown jacket and blue jeans enters from the right and approaches the center of the doorway at a normal walking pace. ONLY NOW do the two glass panels immediately slide apart, accompanied by a gentle motor sound and a short electronic entry chime. Show the panels opening fully before the customer crosses the threshold. The customer walks into the store without noticing her.
<Subject 1> freezes for a short beat and looks from the open doorway toward the departing customer. Her expression stays mostly serious, with only a tiny eyebrow twitch revealing embarrassment. She puts her right hand back into her pocket, straightens her posture, and casually follows the customer through the still-open entrance as if that had been her plan all along. End at 15 seconds with her entering the store. Keep both characters separate, with natural walking and no overlapping bodies.
overall_soundscape:
Quiet nighttime street ambience, subdued ventilation hum, natural footsteps, clothing rustle, one small-hop landing, and the sliding-door motor. The entry chime occurs only when the ordinary customer activates the door in Shot 3. Both characters remain silent throughout: no dialogue, narration, singing, vocal reactions, or intelligible background speech.
non_diegetic_music:
A brief instrumental electronic bass phrase during the confident approach in Shot 1, stopping abruptly when the door stays closed. No music during her failed attempts. One soft, dry pizzicato note punctuates her embarrassed pause in Shot 3. No vocals.
Keep the original costume graphics intact. Add no captions, subtitles, title cards, watermarks, or branded store signage. No additional pedestrians, character duplicates, extra cuts, camera shake, glass collisions, forced entry, or door opening before Shot 3.
MiniMax H3 Prompt
subject_definitions:
<Subject 1> is the single female character in <Picture 1>. The multiple views depict the SAME person. Preserve her exact face, pale green eyes, short black bob, straight bangs, raised patterned hood, oversized black-and-turquoise graphic jacket, shorts, patterned thigh-high socks, chunky boots, and body proportions. Do not redesign her clothing or simplify its graphic motifs.
<Subject 2> is the single pair of red-and-silver headphones worn by <Subject 1> in <Picture 1>. Preserve their exact design. Only ONE pair exists. They are transferred from the girl to the ghost during the video.
summary:
[reference generation] A 15-second, 9:16 animated comedy. A ghost tries to frighten <Subject 1>. Completely unimpressed, she places <Subject 2> on its head. The ghost immediately starts dancing to the music, forgetting to be scary. She watches with a deadpan expression. Three shots, one location, no dialogue.
retention_analysis:
<Subject 1> (appears in all three shots): fully_preserved - maintain her identity, original costume, hood, hairstyle, and illustrated appearance. Her headphones are removed only during the deliberate transfer.
<Subject 2> (appears in all three shots): fully_preserved - the same headphones move from the girl to the ghost without duplication or design changes.
The character-sheet layout, white background, headings, and multiple views are not part of the video.
detailed_description:
Detailed 2D anime animation matching the reference illustration. Smooth movement, restrained facial acting, and consistent costume details. One quiet Japanese side street at night, with cool blue street lighting and warm light from a nearby shop window. Maintain this location and lighting throughout.
The newly generated ghost is a single pale-blue translucent humanoid with a rounded head, two dark oval eyes, two arms, and a lower body tapering into floating mist. Its head is approximately the same size as the girl's head so the headphones fit. Maintain the same ghost design throughout.
[Shot 1]
A steady, eye-level medium-wide shot. <Subject 1> stands on the left, wearing <Subject 2>, with her face and distinctive jacket clearly visible. On her right, the ghost slowly emerges from the dark background and floats toward her with both arms extended in a spooky pose. It stops beside her, within arm's reach. She turns her eyes toward it and gives it a bored, unimpressed look. She does not flinch or step away. A quiet ominous synth drone accompanies the ghost's approach. No vocal sounds.
[Shot 2] At 00:04.000, cut to a steady medium two-shot showing both heads and the girl's hands.
<Subject 1> calmly turns toward the ghost. With both hands, she grips the earcups of <Subject 2>, lifts the headphones clear of her hood, and places that SAME pair over the ghost's head in one continuous action. Her hood remains raised and unchanged. The ghost stays still during the transfer. She releases the headphones and lowers her hands. The girl is now wearing no headphones; the ghost is wearing the only pair. The ominous drone stops. A bright instrumental dance beat begins as the headphones settle into place.
[Shot 3] At 00:08.000, cut to a locked medium-wide two-shot, keeping the girl on the left and the ghost on the right.
The ghost immediately starts dancing enthusiastically to the beat. Use one simple repeated movement: head bobbing, shoulders swaying left and right, and bent forearms gently bouncing. Its misty lower body floats in the same position. The headphones remain securely on its head. No spins, acrobatics, or large movements.
<Subject 1> stands still beside it, watching with a completely serious expression. The ghost keeps dancing happily, having forgotten its attempt to frighten her. During the final two seconds, she slowly looks toward the camera and raises one eyebrow slightly. Hold her deadpan reaction while the ghost continues dancing. End at 15 seconds.
overall_soundscape:
Quiet nighttime street ambience, subtle clothing rustle during the transfer, and clear instrumental music from the headphones after they reach the ghost. The music is an upbeat house groove with a steady kick, crisp hi-hats, and playful synth bass. Synchronize the ghost's dance with the beat. No dialogue, narration, singing, whispers, screams, laughter, or vocal reactions.
non_diegetic_music:
A subdued ominous synth drone during Shot 1, ending during Shot 2. No additional score once the headphone music begins.
Exactly one girl, one ghost, and one pair of headphones. Preserve the original clothing graphics. Add no subtitles, captions, title cards, watermarks, or store logos. No duplicated headphones, extra limbs, character morphing, camera shake, additional cuts, or exaggerated facial deformation.
Mecha rises
Minimax H3 @Hailuo_AI
15-second anime sequence, 1990s mecha anime style, detailed mechanical design, bold shading, cinematic lighting, consistent robot design throughout.
Exactly one giant robot: white and blue armor plating, single glowing green visor, large thrusters on its back.
[0-5s] Wide shot inside a dark hangar. The robot stands still as red warning lights flash and steam vents hiss from the walls. The viewer slowly rises up the length of its body.
[5-10s] Close-up on the visor as it powers on, glowing bright green. The hangar ceiling splits open, revealing a night sky full of stars.
[10-15s] Wide shot from below. The robot ignites its thrusters and blasts upward out of the hangar, blue flames and smoke filling the frame, the viewer tracking it as it shrinks into the sky.
Negative prompt: extra robots, duplicate robots, extra limbs, melting metal, warped armor, photorealistic, live action, blurry, morphing, flickering, inconsistent colors, text, watermark, slow motion
まとさんプロンプトの画像とセットで使ってみてね
▼
Cute Halloween video. A monster and a woman stand side by side, walk toward the camera saying “トリックオアトリート〜” in cheerful Japanese-style pronunciation, and do a playful prank-like surprise pose. The woman copies the monster and keeps a mischievous half-lidded jito-me expression.
Start with a fixed camera, then add slight shake as they come close. At the end, spin the camera and pull the frame into a swirling vortex. Cut to black.
After 0.5 seconds, show centered “trick or treat” text on a pure black background in a cute designer Halloween font: rounded, thick, slightly irregular, chunky, and softly melted. Then opaque orange slime drips from the top until the whole screen becomes orange.
Mood: playful, cheerful Halloween, not scary.
BGM: upbeat, fun Halloween music.
She Stopped the Rain — Now a Tiny Cloud Follows Her (Anime Comedy)
14s16:9
MiniMax H3 Prompt
subject_definitions:
<Subject 1> is the single female character depicted in <Picture 1>. All views in the character sheet show the SAME person. Preserve her exact facial identity, pale green eyes, short black bob with straight bangs, raised patterned hood, red-and-silver headphones, oversized black-and-turquoise graphic jacket, shorts, patterned thigh-high socks, chunky black boots, and original body proportions. Maintain all clothing colors, graphic motifs, and accessories throughout.
summary:
[reference generation] Create a 15-second, 9:16 animated comedy. <Subject 1> confidently stops the rain with a small supernatural gesture. After a brief moment of satisfaction, one tiny rain cloud appears directly above her head and starts raining only on her. She tries to walk away, but the little cloud follows her perfectly. End with her defeated, irritated stare toward the camera. Exactly three shots, one girl, one location, no dialogue.
retention_analysis:
<Subject 1> (appears in all three shots): fully_preserved - retain her identity, costume, headphones, hairstyle, hood, proportions, and illustrated appearance. Rain adds surface droplets without changing the clothing design.
Use <Picture 1> only as a character-design reference. Do not reproduce the white background, character-sheet layout, headings, or multiple views.
detailed_description:
High-detail 2D anime animation matching the reference illustration, with smooth, restrained acting and consistent costume details. The setting is a quiet Japanese side street at night. A softly illuminated shop window and cool blue streetlight make the rain clearly visible. The pavement is wet, with small puddles and stable reflections. Keep the same location and lighting throughout.
The newly generated little cloud is a single compact, dark-gray cloud about 60 centimeters wide, floating roughly 50 centimeters above the girl's hood. It produces one narrow vertical shower directly onto her hood and shoulders. Maintain its shape and size. This cloud is the only source of rain after the opening rainfall stops.
[Shot 1]
A steady, eye-level medium-wide shot shows <Subject 1> standing in the center of the frame during ordinary rainfall across the entire street. Her face, raised hood, headphones, and distinctive jacket are clearly visible. Leave enough space above her head for the later cloud.
She glances upward with mild annoyance, then slowly raises her right hand toward the sky, palm open. A brief, restrained cyan glow appears around her palm. As she closes her fingers, the rainfall across the street stops completely. The glow disappears. Hold a short, clear pause with no falling rain anywhere. Existing puddles and wet reflections remain unchanged.
She lowers her hand and lifts her chin slightly, looking quietly pleased with herself. The broad rainfall sound fades into peaceful street ambience.
[Shot 2] At 00:05.000, cut to a slightly wider, locked full-body shot in the same location.
<Subject 1> remains centered, and the surrounding street is still free of falling rain. One tiny dark-gray cloud materializes directly above her hood. After a brief beat, it starts a narrow shower onto her head and shoulders. Clearly show the rain beginning at the underside of this cloud.
Only the small area directly beneath it receives fresh rain; the rest of the street remains rain-free. She freezes, blinks once as droplets reach her face, and slowly looks upward at the cloud. Her satisfied expression becomes a silent, offended stare. Keep the cloud's edges and the localized rain column clearly visible.
[Shot 3] At 00:09.000, cut to a steady medium-wide shot with room beside her to show movement.
<Subject 1> takes two deliberate steps toward screen-left, attempting to leave the shower. The tiny cloud moves horizontally at exactly her walking speed, staying directly above her hood. Its narrow shower follows her continuously, never falling behind or spreading across the street.
She stops. The cloud immediately stops above her and keeps raining. Allow a short beat so the failed escape is unmistakable. She slowly lowers her shoulders, turns her eyes toward the camera, and gives a flat, deeply unimpressed stare. One visible droplet runs down her cheek. Hold this expression during the final two seconds while the little cloud continues raining only on her. End at 15 seconds.
overall_soundscape:
Broad rainfall and small pavement splashes during the opening. When she stops the weather, the rainfall sound clearly fades out, leaving quiet nighttime ambience. The little cloud introduces a smaller, localized patter on her hood and shoulders. Natural footsteps accompany her two steps. No dialogue, narration, singing, muttering, sighs, or other vocal reactions.
non_diegetic_music:
A restrained instrumental electronic bass phrase accompanies her confident rain-stopping gesture, then ends during the peaceful pause. One short, dry plucked note punctuates the tiny cloud's first shower. Keep the ending sparse so the rain and her silent reaction carry the joke. No vocals.
Exactly one girl and one tiny cloud. Maintain the original character design and opaque clothing. The broad rainfall stops before the little cloud appears. Do not instantly dry the pavement. No additional rain clouds, umbrellas, lightning, strong wind, destructive effects, character duplication, extra limbs, camera shake, or additional cuts. Add no captions, subtitles, title cards, watermarks, or branded signage.
The Ultimate Ground-Splitting Attack, Solved by One Wooden Plank (Anime Comedy)
14s16:9
MiniMax H3 Prompt
subject_definitions:
<Subject 1> is A, the black-haired heroine from character reference image 1.
<Subject 2> is B, the white-haired heroine from character reference image 2.
Preserve both exact faces, hairstyles, outfits, accessories, proportions and original 2D art styles.
<Audio 1> is the voice-timbre reference for <Subject 1> (S1) only. Use A's vocal identity and natural pitch; never copy the recording or its words.
summary:
[reference generation + audio reference] Create a 15-second Japanese 2D anime action-comedy with synchronized sound. Use the selected aspect ratio. A dramatically splits the ground between herself and B and believes she has created an impassable obstacle. B calmly places an ordinary wooden plank across the gap and walks toward A. End on A's familiar silent, stunned face.
retention_analysis:
<Subject 1> (all shots): fully_preserved - exact identity, design, proportions and illustrated style; new actions and setting.
<Subject 2> ([Shot 1], [Shot 2]): fully_preserved - exact identity, design, proportions and illustrated style; new actions and setting.
<Audio 1>: reference - vocal timbre guides A's single written sentence; no recorded words or audio signal are copied.
Images define identity only, not poses or sheet layouts. Equal standing height, excluding ornaments. ONE A and ONE B; no clones, merged identities or additional people.
detailed_description:
Hand-drawn 2D anime with clean linework, cel shading, readable movements and expressive faces. Use the reference art style throughout.
One empty stone courtyard in warm afternoon light. A starts screen-left; B starts screen-right, facing A. They are about three meters apart. A stays on the left throughout. B later walks right-to-left toward A without passing or touching her.
Use a stable three-quarter wide view showing both full bodies, their feet and the floor between them. Keep the same viewing side and screen direction.
ONE ordinary wooden plank lies flat beside B on the right side from the opening frame. It is plain brown, straight, rigid, about 1.6 meters long and 45 centimeters wide. Its long axis follows the right-to-left walking direction.
The attack creates ONE fissure between A and B, running from the foreground toward the rear of the courtyard. It separates the left and right banks. The gap is about 70 centimeters wide, much shorter than the plank. Both banks stay level, with solid visible edges. The dark bottom is not visible.
The fissure never opens beneath either heroine or the plank. Courtyard walls stay intact. Referenced costumes and accessories do not change.
[Shot 1]
Static three-quarter wide view. <Subject 1> stands screen-left with a confident expression. <Subject 2> stands screen-right beside the visible plank, relaxed and attentive, her lips closed.
Between 0.3 and 2.3 seconds, <Subject 1> (S1) declares confidently using the vocal timbre referenced from <Audio 1>: [Japanese] これが、さいきょう! Synchronize A's lips to this sentence once. Finish by 2.3 seconds, then close her mouth.
A lifts her right foot slightly and delivers ONE powerful stomp.
Show foot contact with intact stone before the magic starts. A brilliant teal shockwave races across the floor between the heroines. Stone dust rises as ONE fissure opens in that space.
Make the effect spectacular but brief. Keep both bodies and the floor readable. No full-screen flash, camera rotation or smoke concealing the result.
By 3.5 seconds, the dust clears enough to reveal the finished gap. Both heroines stand safely on their original banks. The plank remains beside B. No additional attack.
[Shot 2] At 00:03.500, cut slightly closer from the same viewing side.
A lifts her chin and gives a proud, closed-mouth smile. She looks across the gap at B and waits.
B looks down at the fissure, then at the plank beside her. Her mouth stays closed; there is no vocal reaction.
Hold a short quiet beat before B picks up the plank.
From 5.0 to 9.0 seconds, keep this shot uncut.
B bends her knees, grips the plank with both hands and lifts it as ONE rigid object.
She lowers it across the fissure. Its long axis points from her right bank toward A's left bank, perpendicular to the fissure.
Show the far end settle onto the left bank and the near end settle onto the right bank. Both ends rest visibly on solid stone, with generous overlap beyond each edge.
B releases her hands only after both ends are supported. The plank lies flat and does not move again.
Keep B's hands, the complete plank and both banks visible. One plain wooden clack. No magic, glow, floating or prop transformation.
A stays still on the left bank and watches. Her smile slowly fades.
From 9.0 to 12.0 seconds, B walks calmly along the plank from screen-right to screen-left.
Show her feet contacting the wood in sequence. The plank stays flat, rigid and supported on both banks. B does not jump, float or perform a balancing routine.
She steps onto the left bank and stops between A and the gap, comfortably away from A. No passing, contact or overlap.
B remains composed with closed lips, viewed mostly in profile during the crossing. No greeting, invitation gesture or conversational mouth movement.
The plank stays across the still-open fissure. A looks from B down to the ordinary bridge. No further action.
[Shot 3] At 00:12.000, cut to A's face on the left bank.
Preserve <Subject 1>'s exact reference face. Her eyes widen, pupils become slightly smaller and eyebrows lift. Her lips part once into a small stunned expression, then HOLD without repeated jaw or lip movement.
She looks slightly toward the camera with her familiar uncomprehending expression.
Apply a short, slow push-in and hold the final full second. No vocal sound. End directly on A's face.
ONE A, ONE B, ONE plank, ONE fissure. No prop duplication, deformation or sudden appearance. The gap never closes or changes width. No falling, injury, costume change or extra gag.
Exactly ONE spoken sentence. B never speaks or makes a vocal reaction; her lips remain closed whenever visible. After 2.3 seconds, neither heroine produces speech, gasps, grunts, screams, laughter, sighs, humming or audible breaths. No narration, inner monologue or improvised words. Physical sound effects continue.
No subtitles, captions, readable text, speech bubbles, logos, watermarks or HUD.
overall_soundscape:
Faint courtyard wind. One heavy stomp synchronized to visible foot contact, one magical pressure burst and a short stone-cracking rumble. Later, one wooden placement clack and restrained footsteps during B's crossing. The final reaction contains only faint ambience.
Only A's written line uses <Audio 1>; no other voices or source playback.
non_diegetic_music:
Brief dramatic instrumental percussion and low strings during the opening attack. Stop completely when B looks toward the plank. No further music, choir, vocal samples, comedy sting or canned laughter.
12s cinematic luxury fashion ad, 4K, 24fps, ultra-photorealistic. A high-fashion model in a flowing iridescent metallic gown walks along a minimalist desert runway at golden hour. Cinematic aerial, tracking, orbit, close-up, and hero shots with realistic cloth physics, flowing fabric, shimmering reflections, soft wind, golden sun flare, HDR lighting, Vogue-style editorial, seamless continuity, consistent face/outfit, no flicker, no warping, no extra limbs, fade to black.
Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, skin tone, body proportions, and facial consistency throughout every shot.
Create a 15-second ultra-realistic UGC-style beauty advertisement featuring a realistic young woman speaking directly to the smartphone camera in a bright, modern bedroom vanity area with warm morning sunlight, soft neutral décor, and an elegant illuminated mirror.
She smiles naturally while holding a premium luxury lip oil with a clear glass bottle and gold cap. In a friendly, conversational tone, she shares why it has become her favorite everyday beauty essential. She opens the product, applies the lip oil with the applicator in front of the mirror, then gently presses her lips together and smiles confidently, showing the glossy natural finish.
Capture authentic handheld selfie shots, over-the-shoulder mirror angles, and cinematic close-ups highlighting the crystal-clear bottle, gold cap, soft reflections, applicator, glossy texture, and luxurious packaging. End with her holding the lip oil beside her face while smiling naturally into the camera.
Authentic UGC creator content, realistic facial expressions, natural hand gestures, healthy glowing skin, minimal makeup, luxury beauty aesthetic, smartphone-shot realism, subtle depth of field, premium color grading, vertical 9:16, 4K HDR, no text, subtitles, logos, or watermarks.
Cinematic luxury skincare product commercial, vertical 9:16, 15 seconds. A translucent emerald green glass dropper bottle of INVENTIKO Bio-Serum 38% Renderfeel 20,000, labeled "SERUM SKINCARE - SKIN REPAIR SKIN LIFTING", sits on a sleek black and white pedestal against a dark teal gradient background with soft volumetric lighting and dramatic light rays. Smooth camera orbit and subtle zoom around the bottle, water droplets on glass, elegant reflections. Close-up macro shots of the bottle surface and text. Then a black dropper is slowly pulled out, filled with golden-yellow serum, and a perfect viscous drop forms and hangs at the tip in extreme slow-motion close-up against soft green bokeh. Quick transition to a soft-focus close-up of a young East Asian woman's glowing cheek and eye as a single golden serum droplet falls onto her skin, creating a delicate shimmering highlight. Final shot: the green bottle with dropper resting beside it on a white terrazzo surface against a green tiled wall with soft window light stripes. Ultra-realistic, high-end beauty advertising style, soft cinematic lighting, shallow depth of field, 4K quality, smooth camera movements.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end cosmetics commercial, photorealistic
SCENE
East Asian woman, long dark hair, white silk robe. Marble vanity countertop, illuminated ring mirror, arranged gold and rose-gold cosmetic bottles, bright white room background.
SHOT BREAKDOWN
0-4s — Medium shot of woman holding a frosted bottle and glass dropper. Cuts to close-up of her dispensing a drop onto her cheek, then macro shot of clear liquid touching the skin.
4-8s — Extreme close-up of a beige teardrop sponge blending foundation on her cheek, followed by a fluffy rose-gold brush applying blush.
8-12s — Extreme close-up of a pink doe-foot applicator gliding glossy tint onto her lips.
12-15s — Medium close-up framing her face and shoulders. She showcases glowing makeup, looking at the camera with a gentle smile, hand gracefully positioned.
CAMERA
Macro beauty lenses, shallow depth of field. Static camera positioning with fast, rhythmic cuts between wide setting shots and extreme detail inserts.
LIGHTING & PALETTE
Soft, diffused studio lighting. High-key exposure with ring light reflections in the eyes. Crisp whites, marble grays, metallic golds, and glossy pastel pinks.
AUDIO
Pristine room tone, distinct liquid droplet sound, soft sponge tapping, light brush sweeping, serene lo-fi background music.
AVOID
Harsh shadows, cluttered background, camera movement, motion blur, skin blemishes.
The Brief: "Jessy x RadiantGlo"
15 seconds. One face, one mask, one ritual — quiet luxury skincare.
Jessy stands at her mirror at night, cool blue light on her skin, studying her reflection before she says a word. She presses the remote, and the RadiantGlo mask blooms to life — red LED light rising from her jaw to her brow, glowing straight through the eye and mouth cutouts. No overlay, no CGI sheen, just real diffusion through real skin. A slow profile shot, cord resting naturally, breath audible in the silence. Macro push on her cheek — pores, peach fuzz, light catching under the surface. Then morning: she lifts the mask off, daylight replaces the red glow, and she walks through her sunlit apartment with nothing performed, just calm. Final beat: the mask alone on a matte surface, LEDs still glowing, logo catching the light — hero shot. Fade to black.
Cold nights fading into warm dawn color science throughout — think a skincare brand's flagship campaign, not an infomercial. Same face, same mask, same world, held together across every cut.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end cosmetics commercial, macro beauty photography, elegant cinematic realism
SCENE
Matte black lipstick tube with rose-gold accents. Vibrant matte red lipstick. A fair-skinned woman with dark hair in a black strapless dress. Abstract environments featuring glossy black podiums, floating red rose petals, sparkling diamonds, and undulating glossy red silk.
SHOT BREAKDOWN
0-4s — Extreme close-up pans across the closed black tube resting on a sparkling red surface. Text: "UNVEIL TRUE LUXURY". Cuts to the tube standing upright as a sparkling red liquid ribbon swirls around it among falling rose petals. Text: "INTENSE VELVET COLOR" and "SMOOTH • WEIGHTLESS • PRECISION".
4-8s — The tube opens to reveal the red lipstick; a golden light trail traces the tip amid floating petals and diamonds. Cuts to a profile shot of a woman applying the lipstick. Text: "ONE GLIDE." and "PERFECT COVERAGE."
8-12s — The woman looks through a lighted vanity mirror frame. Text: "RICH PIGMENT • LASTING ELEGANCE." Cuts to her smiling over her shoulder with flowing hair and floating red silk in the background. Text: "CRAFTED FOR" and "CONFIDENCE".
12-15s — Extreme macro close-up of perfectly painted bright red lips. The final shot frames the open lipstick on a glossy podium under warm volumetric god rays, surrounded by floating silk and diamonds. Text: "YOUR BRAND NAME" and "Own Every Moment".
CAMERA
Macro lenses with shallow depth of field. Smooth tracking pans, slow-motion dynamics for floating elements, and sharp, rhythmic commercial cuts.
LIGHTING & PALETTE
High-contrast studio lighting, luminous vanity strip lights, and golden god rays. Color palette dominated by pitch blacks, vivid velvet reds, sparkling whites, and warm metallic golds.
AUDIO
Sleek, bass-heavy electronic pop instrumental. Crisp swoosh sound effects for the glowing light trails and swirling silk.
AVOID
Smudged makeup, uneven skin textures, dull colors, naturalistic documentary lighting, cluttered environments.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end luxury fashion commercial
SCENE
Red-haired female model, black leather jacket, pink metallic corset, black leather mini skirt, black knee-high boots, "PRADA" necklace. Triangular glass perfume bottle with black cap containing pink liquid, labeled "PRADA MILANO DAL 1913". Glossy black corridor, vertical pink neon light strips, floor fog.
SHOT BREAKDOWN
0-4s — Extreme close-up of the perfume bottle on a reflective surface. Cut to the woman walking confidently down the neon-lit corridor.
4-8s — Close-up of the woman holding the bottle forward, focusing on the glass. Rack focus to her face as she holds the bottle near her cheek.
8-12s — Wide full-body shot of the woman posing in the foggy corridor. She raises the bottle to her shoulder level.
12-15s — Medium shot prioritizing the woman's face with the bottle blurred in the foreground. Rack focus shifting sharply to the bottle on the table while the woman blurs in the background.
CAMERA
Shallow depth of field, frequent rack focusing between foreground product and background model. Smooth tracking shots, slow push-ins. Rapid commercial-style cuts. High gloss, sharp focus.
LIGHTING & PALETTE
High-contrast dark studio lighting. Dominant vertical pink neon practical lights. Glossy black floor reflections. Color palette: Neon pink, deep black, metallic silver, pale skin tones, vibrant copper-red hair.
AUDIO
Heavy synth-bass electronic beat, rhythmic clicking heels, subtle atmospheric hum of neon tubes.
AVOID
Daylight, natural settings, flat lighting, cluttered backgrounds, casual streetwear.
UGC-style skincare video featuring a realistic young woman speaking directly to the camera in front of a bathroom mirror while holding a premium facial serum bottle. She smiles naturally, talks about her skincare routine, and demonstrates applying the serum to her face. Authentic, conversational presentation with genuine facial expressions and hand gestures, natural morning light, casual home bathroom setting, clean skincare aesthetic, healthy glowing skin, minimal makeup, smartphone-shot look, candid lifestyle beauty content, soft depth of field, luxury beauty brand feel, vertical 9:16, social media ad quality, highly realistic natural skin texture, not overly retouched.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end beauty commercial
SCENE
Young Asian woman, long wavy brown hair, cream silk tie-neck blouse, gold hoop earrings, delicate gold pendant necklace. Upscale bathroom interior featuring gray-veined marble countertops, dual oval mirrors with thin gold frames, brushed gold fixtures, and subtle greenery.
SHOT BREAKDOWN
0-4s — Medium shot of the woman smiling warmly at the camera, holding a closed black and gold mascara tube. She looks down to twist the cap open.
4-8s — Framed closer, she lifts the wand, examining it while looking off-camera. She raises it to her eye and begins applying mascara to her right upper eyelashes.
8-12s — Extreme close-up isolating her eye and the wand coating her lashes. Cuts to her smiling softly at her reflection in the mirror, wand in hand.
12-15s — Macro product shot. The black and gold tube stands vertically on the marble counter, displaying gold text "IINIIOVIMI". Flanked by blooming white roses and blurred skincare jars.
CAMERA
Locked-off tripod shots with smooth, deliberate cuts. Pronounced shallow depth of field in all close-ups and the final product shot. High definition macro focus used for facial details.
LIGHTING & PALETTE
Soft, diffused natural daylight illuminating the subject evenly. Bright, airy atmosphere. Color palette highlights cream, brushed gold, deep black, pristine white, and warm peach skin tones.
AUDIO
Uplifting, serene instrumental background music. Crisp foley sounds of twisting the plastic cap, faint brushing, and the final placement of the product on marble. No dialogue.
AVOID
Handheld camera shake, harsh shadows, cluttered backgrounds, unnatural eye tracking, dull skin tones.
"Jessica x The Bag"
15 seconds. One face, one bag, one mood — effortless luxury.
Jessica walks into frame on a sun-warmed city street, the cognac leather bag with its hand-scribbled blue design swinging from her hand. She's in a fitted black dress with tan accents that pick up the bag's exact shade — every detail intentional. The camera pushes in as she lifts the bag, gold hardware flashing in the light, her expression shifting from composed to a knowing half-smile. A slow turn through a marble-lit interior, dress catching the glow, bag cradled at her arm. Final beat: she faces the lens dead-on, bag held forward, hero shot, soft rim light framing her like a campaign still. Fade.
Warm, glossy, early-2000s fashion-film color science throughout — think The Devil Wears Prada meets a runway ad. Same face, same bag, same world, held together across every cut.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Clean UGC beauty tutorial and product demonstration.
SCENE
Young woman, icy blonde hair, tanned skin, manicured nails with white tips, plain white t-shirt. Bathroom setting, round wall mirror, white vanity, black and white soap dispensers, double glass wall sconces, white paneled door. A black makeup tube with white text reading "NOIRLIFT".
SHOT BREAKDOWN
0-4s — Close-up. Woman faces the camera, speaking actively while displaying the "NOIRLIFT" tube near her cheek.
4-8s — Medium shot via mirror reflection. Over-the-shoulder framing of the woman unscrewing the wand, then applying mascara to her left eyelashes.
8-12s — Extreme close-up on the woman's face. Heavy diagonal sunlight casts sharp shadows. She smiles, blinks, and displays her elongated eyelashes while speaking.
12-15s — Close-up. Woman applies mascara again under strong sunlight, then returns to holding the "NOIRLIFT" tube up, smiling and speaking excitedly to the viewer.
CAMERA
Smartphone camera feel, steady handheld. Eye-level angles. Fast-paced rhythmic cuts between standard close-ups, mirror reflections, and extreme close-up facial shots.
LIGHTING & PALETTE
High-key natural daylight blended with warm ambient sconce lighting. Later shots feature harsh, sharp diagonal sunlight across the face. Palette emphasizes warm skin tones, pale blonde hair, stark whites, deep blacks, and soft pink lips.
AUDIO
Upbeat acoustic pop music. Subtle plastic friction sounds of the mascara wand unscrewing. Clear spoken dialogue throughout as the subject's lips move frequently.
AVOID
Text morphing, inconsistent nail polish, distorted mirror reflections, unnatural eyelash clumping, warped background geometry.
CHARACTER & WORLD LOCK + FULL 15-SEC MASTER PROMPT
A 15-second continuous UGC-style vlog in 9:16 vertical format. Jessy, a woman in her mid-20s — use her facial features exactly as shown in her reference photo, keep everything else about the scene freshly designed — wears an attractive pastel-colored dress (soft lavender, mint, or buttery yellow) that visually pops in contrast against the bubblegum-pink Olipop can. Location: a bright, clean modern kitchen/countertop with soft natural daylight. Product: a can of Olipop Blackberry Vanilla — pastel pink can, magenta blackberry illustration, white vanilla flower, dark green "Blackberry Vanilla" wordmark, "Supports Digestive Health" text near the top, "A New Kind of Soda™" tagline (use the uploaded product photo as the exact visual reference for the can). Style: authentic smartphone UGC vlog, natural handheld feel, realistic skin texture, no over-retouched look. She speaks casual, upbeat, conversational English directly to camera with natural lip-sync.
The video follows this exact beat sheet, with clean cuts between each moment:
00:00–00:02 — Front-camera selfie, slight handheld sway, Jessy fans herself lightly in the kitchen, looking for something refreshing, smiles at camera: "Okay I need something fun to drink right now."
00:02–00:04 — Eye-level medium shot, she opens the fridge and pulls out the pink Olipop can, face lighting up with delight: "Ooh, Blackberry Vanilla Olipop — yes please."
00:04–00:06 — Close-up on her hands slowly turning the can, label details ("Prebiotics, Botanics, Plant Fiber") visible: "Prebiotics AND it tastes like dessert? Sold."
00:06–00:08 — Tight macro shot, her fingers pop the tab, condensation and a light fizz mist visible: "Listen to that fizz."
00:08–00:10 — Slow-motion macro shot, pink soda pouring over ice into a clear glass, bubbles rising: "Look how pretty that color is."
00:10–00:12 — Close-up on her face as she sips, eyes lighting up with genuine, pleasantly surprised reaction: "Wait... that's actually so good."
00:12–00:13 — Macro hero shot of the can alone on the counter, condensation dripping, soft bokeh kitchen background, slow subtle push-in, no dialog.
00:13–00:14 — Medium shot, she smiles at camera, can raised slightly at chest height: "Blackberry vanilla was the right call."
00:14–00:15 — Close front-camera selfie, can held beside her face, warm bright smile into the lens: "Go grab an Olipop, seriously."
Continuous natural ambient kitchen sound, subtle upbeat pop background music underneath, her voice clear and casual throughout. Consistent face, outfit, and setting across every beat. No text overlays, no captions, no watermarks, no horizontal framing, no changes to the can's design or branding.
Create a 15-second luxury cinematic product showcase for premium wireless over-ear headphones.
0–4s: Begin with an extreme macro tracking shot moving across the soft memory-foam ear cushion, fine fabric texture, brushed-metal hinge and precision-machined controls. A narrow light band travels across the surface, revealing realistic materials against a deep black studio background.
4–8s: Pull back into a three-quarter hero view. The headphones rotate slowly above a glossy reflective pedestal. The ear cups pivot naturally while the adjustable headband extends slightly, demonstrating flexible construction and comfort. Maintain exact symmetry, stable geometry and consistent proportions.
8–12s: Transition into an elegant exploded-view reveal. The ear cushion, acoustic driver, internal sound chamber, control ring and outer shell separate smoothly in perfect alignment. Subtle luminous sound waves pulse outward from the driver while the camera performs a restrained side orbit.
12–15s: Every component reconnects seamlessly. The headphones settle into a centered front-facing hero composition as soft rim lighting defines the silhouette. Complete a gentle dolly-in toward the ear cups. Premium technology-commercial finish, controlled reflections, realistic shadows, shallow depth of field, crisp surface detail, stable product shape, no hands, no distortion, no onscreen text.
Use the uploaded storyboard as the camera guide. Follow all 8 frames in order with smooth cinematic continuity. The same woman, outfit, hairstyle, makeup, room and product must remain perfectly consistent throughout the entire 15-second commercial. Every shot must begin where the previous shot ends with seamless match cuts and natural camera movement.
Shot 1 (0-1.8s)
A slow push in as morning sunlight enters through the window. The woman looks outside and gently turns toward the mirror. The camera continues moving without stopping.
Transition:
The camera keeps pushing forward until her face fills the frame.
Shot 2 (1.8-3.6s)
Without cutting, the shot becomes a close-up of her face in the mirror. She notices dull skin and lightly touches her cheek. The camera slowly circles around her as she reaches toward the vanity.
Transition:
Follow her hand naturally to the serum bottle.
Shot 3 (3.6-5.4s)
Macro shot as she picks up the serum bottle. The bottle rotates slightly in her hand while natural sunlight reflects across the glass. The camera smoothly follows the bottle upward.
Transition:
Continue tracking into an extreme macro of the dropper.
Shot 4 (5.4-7.2s)
Extreme macro of the dropper lifting from the bottle. A single drop forms and falls in slow motion. The camera follows the drop as it lands on her fingertips.
Transition:
The camera continues following her fingertips toward her face.
Shot 5 (7.2-9.0s)
Close-up as she gently applies the serum across her cheeks using smooth circular motions. Skin catches soft natural highlights. Hair moves slightly in the breeze.
Transition:
The camera slowly rotates around her face while maintaining eye level.
Shot 6 (9.0-11.1s)
The lighting naturally becomes warmer as her skin appears healthier and more radiant. The transformation happens gradually, not instantly. She smiles softly while looking into the mirror.
Transition:
She turns away from the mirror and walks toward the window as the camera follows.
Shot 7 (11.1-13.2s)
Medium shot as she confidently walks into warm sunlight. She smiles naturally at the camera while the background softly blurs. The camera slowly arcs around her.
Transition:
She lowers the product toward the camera until it fills the frame.
Shot 8 (13.2-15.0s)
Hero product shot. The serum bottle stands on a clean surface with warm natural daylight. Soft reflections move across the glass. Premium end card with elegant typography and subtle camera push in. End on the product with "Shop Now."
Overall style:
Ultra photorealistic luxury skincare commercial, Apple-style cinematography, ARRI Alexa 65, 50mm and 85mm lenses, soft natural daylight, realistic skin texture, premium color grading, physically accurate lighting, smooth cinematic camera movement, seamless match cuts, invisible transitions, no jump cuts, no frame skipping, no character changes, no outfit changes, no background changes, premium beauty ad quality.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: High-end cosmetics commercial, photorealistic beauty photography.
SCENE
Female model with slicked-back ponytail. Oversized dusty rose suit, matching bandeau, gold hoop earrings. "MOIST HEIST LIP OIL" bottle featuring a silver cap and magenta liquid. Settings include a minimalist white runway and abstract liquid or smoke environments.
SHOT BREAKDOWN
0-4s — Full shot of model walking a white runway. Cuts to medium shot holding the product, then macro shot of hands pulling the applicator wand from the "MOIST HEIST LIP OIL" bottle.
4-8s — Extreme close-up of glossy lips. Cuts to product surrounded by floating water droplets, then a macro face shot emphasizing glossy lips and skin texture.
8-12s — Product rests on rippling liquid silver with pink metallic bubbles. Cuts to front-facing close-up of model applying the lip oil. Product stands amid billowing pink smoke.
12-15s — Bottle held beside the model's eye. Extreme close-up of parted, highly reflective lips. Final product shot with floating pink droplets and text: "STEAL THE SHINE. KEEP THE MOISTURE."
CAMERA
Macro lenses for tight beauty shots. Fast-paced, rhythmic commercial cuts. Shallow depth of field on facial close-ups. Smooth, slow pans across abstract product environments.
LIGHTING & PALETTE
High-key studio lighting with softbox diffusion. Intense, crisp specular highlights on lips, liquid, and glass. Palette dominated by dusty rose, magenta, metallic silver, and stark white.
AUDIO
Upbeat, driving electronic runway music. Foley includes sharp glass bottle clicks, subtle liquid swishes, and high-heeled footsteps. No dialogue.
AVOID
Matte finishes, cluttered backgrounds, unkempt hair, muted colors, flat lighting.
Use @Image1 as the strict first frame and primary visual reference. Preserve the model’s face, messy updo with soft bangs, gold hoop earrings, pendant necklace, chocolate-brown draped strapless top with center knot and hanging front panel, ivory wide-leg drawstring pants, flat sandals, body proportions, and the warm minimalist interior with arched niche, cream walls, stone floor, and soft sunlight.
Create a polished 15-second luxury e-commerce fashion video.
0–4s: Begin with the exact full-body front-facing pose from @Image1. The model stands relaxed with both hands in her pockets in a warm sunlit interior. Slow dolly-in from full body to medium full shot. Maintain accurate garment colors, clean shape, and crisp visibility of the top drape and wide-leg pants.
4–7s: Smooth cut to a three-quarter angle, then a natural side profile turn. The model shifts her weight subtly, showing the fit of the bandeau top, the hanging center panel, waistband detail, and the relaxed flow of the pants. Soft natural light creates gentle highlights and shadow definition.
7–10s: Medium full-body tracking shot as the model takes three slow elegant steps forward. The pants move fluidly and independently with realistic fabric physics. She removes one hand from a pocket and lightly adjusts the draped front panel of the top once, then relaxes naturally.
10–13s: Refined close-up sequence of the gathered center knot, soft fabric texture of the top, drawstring waistband, trouser drape, gold jewelry, and sandal detail. Shallow depth of field, soft sunlight, clean texture rendering, stable garment geometry.
13–15s: Return to a full-body hero composition. The model settles into a relaxed fashion pose, looking toward camera with subtle confidence. Premium boutique-commercial finish, elegant motion, stable anatomy, accurate ivory and brown tones, clean lifestyle background, clear apparel visibility, no onscreen text.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end beauty commercial, photorealistic
SCENE
Black woman, natural hair updo, white plush bathrobe. Luxury bathroom setting, marble vanity, large mirrors, chrome sink fixtures, white flowers, bright window with outside greenery.
SHOT BREAKDOWN
0-4s — Close-up on a white Dove soap bar and box resting on wet marble beside white flowers. The word "PURE" is visibly traced into the mirror condensation in the background.
4-8s — Medium shot. The woman lathers the soap in her hands over the chrome sink. Bold white 3D text "SOFTNESS" hovers directly above the counter.
8-12s — Close-up profile. The woman massages thick white soap foam onto her face. Floating 3D text "CARE" tracks with her soapy cheek. She then admires her clean face in the mirror as the text "REFRESH" appears on the glass.
12-15s — Medium close-up. She smiles brightly at the camera, holding the Dove box beside her face. Large overlaid graphic text reads: "Dove SOFTNESS YOU CAN FEEL. CARE YOU CAN TRUST."
CAMERA
Smooth slow push-ins. Shallow depth of field on macro product shots. Gentle, evenly paced commercial editing.
LIGHTING & PALETTE
Soft diffused daylight, warm mirror backlighting. Bright, clean palette of pure whites, marble greys, rich brown skin tones, and navy blue accents.
AUDIO
Gentle water splashing, thick soap lathering friction. Soothing, upscale ambient spa instrumental music.
AVOID
Harsh shadows, cluttered countertops, deformed floating text, unnatural foam textures, rapid camera movements.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end fashion commercial
SCENE
Elegant woman in a monochromatic pink tailored suit, pink stilettos, and sunglasses. Pink vintage car. Pale pink leather handbag featuring a distinct gold geometric clasp. Minimalist white modernist architecture situated on a palm-lined desert highway.
SHOT BREAKDOWN
0-4s — Wide tracking shot of the pink vintage car driving toward a white building. Text overlay: "GOLDEN HOUR". Cut to a tight close-up of a pink stiletto stepping onto the asphalt.
4-8s — Medium profile shot of the woman standing confidently near the car. Cut to a close-up of her hand smoothly opening the car trunk.
8-12s — Product shot of the pink handbag resting inside the trunk. Text overlay: "LEATHER & SILHOUETE". Quick cut to an extreme macro detail of the gold clasp.
12-15s — Over-the-shoulder close-up of the woman turning to look at the camera, holding the bag. Text overlay: "CARRY YOUR GRACE". Hard cut to a black screen with white text: "FREE & ROMANTIC" above "LIVE FREELY, LOVE DEEPLY".
CAMERA
Sleek, stabilized tracking, medium fashion portraits, and extreme macro inserts. Smooth, deliberate pacing with rhythmic cuts. Prominent shallow depth of field on all close-ups.
LIGHTING & PALETTE
Warm golden hour sunlight casting long, dramatic shadows. Soft, diffused ambient fill. Color palette dominated by pastel pinks, rose gold, crisp architectural white, and warm muted desert tans.
AUDIO
Ambient warm wind, crisp heel clicks on pavement, smooth metallic latch opening. Polished, elegant downtempo lounge music. No dialogue.
AVOID
Cluttered backgrounds, harsh fluorescent lighting, fast handheld camera shaking, distorted typography, mismatched color schemes.
Duration: 15 seconds | Aspect ratio: 21:9 | Style: Cinematic fashion eyewear commercial, photorealistic
SCENE
Young man, dark wavy hair, beard, gradient aviator sunglasses, navy blazer, white collared shirt. Young woman, long brown hair, copper silk wrap dress, gold hoop earrings. Modern urban street, paved road, glass-facade office buildings.
SHOT BREAKDOWN
0-4s — Man walks confidently down the center of a city street toward the camera. Framed as a medium tracking shot.
4-8s — Woman joins him, walking on his left. They turn their heads to look at each other and smile warmly.
8-12s — Extreme close-up on the man's face. The city skyline reflects in his sunglasses, followed by a clear reflection of the approaching woman. He smiles.
12-15s — Medium close-up of the woman playfully adjusting the man's sunglasses. Cut to the man looking off-camera, then directly into the lens. Overlay text fades in: "See the world in style 😎".
CAMERA
Smooth backward Steadicam tracking. Shallow depth of field blurring the architectural background. Sharp focus on faces and eyewear reflections. Fast, deliberate commercial editing rhythm.
LIGHTING & PALETTE
Golden hour backlighting, prominent warm lens flares hitting the lens edge. Soft, flattering fill light on the subjects' faces. Color palette features deep navy, crisp white, rich copper, amber sunlight, and cool blue-grey architectural reflections.
AUDIO
Upbeat, sophisticated lifestyle electronic background music. Subtle ambient city breeze and soft footsteps. No dialogue.
AVOID
Mismatched reflections, distorted sunglasses frames, extra fingers during the adjustment, misspelled text, harsh shadows, unnatural walking gait.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: Dynamic studio food commercial
SCENE
Assorted styled food items (loaded fries, tomato mozzarella toast, strawberry waffle, yogurt bowl, pastel ice cream, pasta salad) on geometric, diagonally color-blocked surfaces.
SHOT BREAKDOWN
0-4s — Opens with a flat-lay wide shot of six dishes arranged on cream, navy, and green diagonal blocks. Cuts to a macro shot of steaming loaded fries as red seasoning falls onto white sauce.
4-8s — Cuts to a close-up of tomato and cheese toast in a black baking pan. Fresh basil leaves fall onto the toast against a diagonal red and cream background.
8-12s — Close-up of a waffle as syrup pours over fresh strawberries against a pink background with bokeh. Transitions to a yogurt and fruit bowl with floating cereal and blueberries as honey streams down.
12-15s — Rainbow sprinkles fall onto a pastel ice cream cone topped with whipped cream and a cherry. Concludes with a flat-lay of five dishes on blue, pink, and white diagonal blocks. Legible text reads "FRESH PICKS" at the top and "made for today" at the bottom right.
CAMERA
Locked-off static framing. Mix of top-down flat lays and eye-level macro close-ups. Fast-paced rhythmic cuts matching the falling ingredients.
LIGHTING & PALETTE
Bright, hard studio lighting creating sharp, directional drop shadows. Vibrant, high-contrast palette utilizing bold color-blocked backgrounds (navy, pastel pink, powder blue, cherry red, cream).
AUDIO
Snappy, upbeat commercial pop music. Foley includes sizzling, thick liquid pouring, and the light clattering of falling herbs, cereal, and sprinkles.
AVOID
Messy plating, soft lighting, muted colors, camera panning, handheld movement, cluttered backgrounds.
A young person walks under the blazing summer sun, looking exhausted and sweating heavily. The road shimmers with heat waves, and everything appears dry and dull. Suddenly, they grab a chilled bottle of premium fruit juice from a cooler and take a refreshing sip. Instantly, the environment transforms—lush green trees bloom, vibrant flowers appear, a cool breeze flows, water splashes through the air, and glowing particles surround the scene. Ice cubes and fresh fruit slices (orange, mango, or according to the flavour) swirl around the bottle in cinematic slow motion. End with a stunning close-up of the juice bottle covered in cold water droplets against a bright, refreshing background. Ultra-realistic, premium commercial, 4K, cinematic lighting, high-detail, smooth camera movements, vibrant colours, luxury beverage advertisement.
Tagline ideas:
Beat the Heat. Taste the Freshness.
Every Sip Brings Life.
Refresh Your Day, Naturally.
Stay Cool. Stay Fresh.
[FORMAT] 15-second vertical 9:16 photorealistic luxury-fragrance commercial with native synchronized stereo audio.
[REFERENCES] [Image1] is the strict multi-angle identity and wardrobe reference for Freya Lux. Its six panels show one coherent person from different camera angles; reconstruct one consistent 3D character without averaging or redesigning her face. Preserve her exact facial structure, bright blue eyes, long platinum-blonde hair with darker roots, skin tone, apparent age, body proportions and the same tailored ivory trouser suit shown in [Image1]: closed single-breasted blazer, high-neck ivory blouse, full-length wide-leg trousers and closed-toe ivory heels. [Image2] is the strict product reference for AURELIA NO. 7. Preserve the rectangular clear-glass bottle, champagne-colored liquid, heavy transparent base, oval brushed-gold cap, cream label, proportions and exact product spelling in every shot.
[SCENE] A minimal luxury hotel terrace at sunset overlooking the sea, realistic warm light, pale stone, glass reflections and a gentle breeze. Premium international fragrance campaign, elegant and sensual without fantasy styling.
[SEQUENCE] 0–2s: Immediate hook. The exact AURELIA NO. 7 bottle slips from a marble ledge and falls toward the floor in realistic slow motion. Freya’s hand enters and catches it just before impact. 2–6s: Medium close-up revealing Freya. She looks composed and holds the bottle naturally while golden sunlight refracts through the glass and liquid. 6–10s: Controlled macro sequence: her fingers remove the oval cap, one refined spray catches the backlight, and the mist crosses frame. Preserve the bottle and label perfectly. 10–13s: Freya walks toward the terrace edge as the camera tracks beside her; hair and tailoring move naturally in the breeze. 13–15s: Clean ivory-and-gold packshot of the exact bottle on marble. Display perfectly spelled text: “AURELIA NO. 7” and “DEFINE YOUR AURA.”
[VOICE-OVER] Elegant adult female English voice, warm, intimate and sophisticated, delivered slowly with natural pauses: “A trace of light. A presence that lingers. Aurelia No. Seven. Define your aura.” Freya does not speak or lip-sync; the narration remains off-screen.
[MUSIC + MIX] Original minimalist luxury-fragrance score: soft glass harmonics, airy synth pads, delicate piano notes and a restrained warm bass pulse. No vocals and no recognizable melody. Keep the arrangement sparse and below the narration. Duck the music by approximately 8 dB while the voice speaks. Add subtle bottle movement, cap release, perfume spray, breeze and distant sea ambience. The voice must remain centered, dry, crisp and fully intelligible. Finish with a delicate glass-and-gold sonic logo during the packshot.
[PRESERVE] Stable Freya identity, exact perfume bottle, correct label, realistic hand interaction, natural glass and liquid physics, coherent terrace and premium photographic realism.
[AVOID] Bottle redesign, incorrect label, extra bottles, duplicated caps, distorted fingers, excessive perfume cloud, magical particles, artificial skin, identity drift, exaggerated posing, loud music, sung vocals, dialogue overlap, subtitles, additional text or watermark.
[FORMAT] 15-second vertical 9:16 photorealistic commercial product showcase with native synchronized stereo audio.
[OMNI REFERENCE — [Image1]] [Image1] is the strict multi-angle product reference for the H3 ENERGY drink. Its six panels show one identical 500 ml slim can from different angles. Reconstruct one coherent 3D product and preserve the exact tall proportions, satin-black aluminum, silver rim and pull tab, large metallic-silver “H3” logo, smaller “ENERGY” text, neon lime, cyan, magenta and orange streak graphics, condensation and label placement in every shot. Do not average, simplify or redesign the can.
[COMMERCIAL CONCEPT] A premium high-energy launch film inside a dark futuristic performance studio. Glossy black surfaces, cold vapor and precise neon lighting echo the can’s lime, cyan, magenta and orange accents. The visual language is fast, physical and realistic: speed, pressure, cold and impact without fantasy transformations.
[SEQUENCE] 0–2s: Immediate hook. From black, the exact H3 can drops vertically through a thin sheet of ice and lands upright on a wet black platform. Ice cracks outward, droplets and fragments fly past the lens in crisp slow motion, and lime-cyan light flashes behind the can. Keep the logo facing camera and perfectly readable. 2–5s: A fast controlled 180-degree macro orbit reveals the same can from front to side to back with strong parallax. Neon light streaks sweep across the aluminum while condensation runs naturally downward; the product itself remains rigid and unchanged. 5–8s: Extreme close-up of the exact silver pull tab. It snaps open with realistic pressure; a sharp burst of cold vapor and fine droplets escapes, followed by a clean metallic click. No hand is visible. 8–12s: The camera races through suspended droplets and transitions into a hero three-quarter view. The can rotates slowly on the wet platform while four colored light bands converge behind it. A powerful circular pulse travels across the surface, scattering water without moving or deforming the product. 12–15s: Final centered packshot. The exact H3 can stands cold and upright against a black background, framed by lime, cyan and magenta rim light. Condensation glistens, vapor settles and the silver “H3” and “ENERGY” remain sharp and correctly spelled. End on a short white light pulse and hold the product for readability.
[CAMERA + LOOK] Premium global energy-drink TVC, photorealistic commercial cinematography, 100 mm macro details and 35 mm hero shots, high-speed photography, precise focus pulls, controlled speed ramps, physically accurate aluminum, ice, water, vapor and reflections, deep blacks, saturated neon highlights, crisp contrast and seamless transitions. Keep the entire composition optimized for a mobile 9:16 frame.
[VOICE-OVER] Confident adult English voice, energetic, modern and controlled, delivered clearly across the final ten seconds: “Break the limit. Own the moment. H3 Energy. Power your next move.” No character and no lip-sync; narration remains off-screen.
[MUSIC + AUDIO MIX] Original punchy electronic sports-ad score at approximately 128 BPM: tight kick, deep bass pulse, clipped synth arpeggio and rising impacts. No vocals and no recognizable melody. Begin with a sharp sub hit on the ice impact, synchronize the beat with the orbit, tab opening and final light pulse. Add realistic ice crack, water droplets, aluminum landing, pull-tab snap, carbonation hiss and cold vapor detail. Keep music approximately 8 dB below the voice-over while it speaks; narration stays centered, dry, crisp and fully intelligible.
[PRESERVE] One single H3 can throughout, exact product geometry and branding, readable “H3” and “ENERGY,” consistent graphics, realistic condensation, coherent lighting and natural object physics.
[AVOID] Extra cans, duplicate tabs, altered logo, misspelled text, changing colors, changing proportions, crushed or flexible aluminum, floating product without physical cause, fantasy electricity touching or transforming the can, hands, people, fruit, excessive foam, opaque vapor, unreadable label, jitter, flicker, warped reflections, subtitles, additional text or watermark.
[FORMAT] 15-second vertical 9:16 photorealistic luxury-watch commercial with native synchronized stereo audio.
[REFERENCES] [Image1] is the strict identity and wardrobe reference for Dorian Vane. Preserve his exact face, curly blond-brown hair, earrings, necklace, body proportions and clothing. [Image2] is the strict product reference for the VANE CHRONOS watch. Preserve its dark titanium case, black sunburst dial, silver indices, date window, crown, brown leather strap, proportions and exact brand spelling in every shot.
[SCENE] Golden-hour interior of an elegant contemporary hotel lobby, natural guests and staff, polished stone, warm window light and restrained international luxury-advertising art direction. Everything must look physically real, premium and commercially produced.
[SEQUENCE] 0–2s: Immediate hook. Close shot of a waiter stumbling as one crystal glass and a small arc of water fall toward a guest. Dorian notices it and raises the wrist wearing the exact watch from [Image2]. 2–5s: Macro product shot as the second hand reaches an index. Dorian snaps his fingers; a subtle pressure wave freezes the lobby, waiter, glass, liquid droplets and guests completely. Only Dorian and the camera can move. 5–10s: Smooth controlled tracking shot. Dorian walks through the frozen lobby, catches the glass and returns it safely to the tray. Include one elegant macro insert of the watch on his wrist, keeping the product perfectly consistent. 10–13s: Dorian walks away and snaps again. Motion, ambience and natural reactions resume; nothing spills. 13–15s: Clean dark studio packshot of the exact VANE CHRONOS watch. The brand name and final line appear perfectly spelled: “VANE CHRONOS” and “OWN THE MOMENT.”
[VOICE-OVER] Refined, confident adult male English voice, calm and intimate, never theatrical. Begin after the hook and leave natural pauses: “Time moves for everyone. You decide what the moment becomes. Vane Chronos. Own the moment.” Do not make Dorian speak or move his lips; this is off-screen narration.
[MUSIC + MIX] Original restrained luxury-ad instrumental: low analog pulse, soft piano texture, subtle clock-like percussion and warm cinematic strings. No vocals and no recognizable melody. Begin quietly under the hook, drop almost to silence when time freezes, then rebuild gently. Keep the voice-over centered, crisp and clearly louder than the music. Automatically duck music by approximately 8 dB during every spoken phrase. Use precise glass, finger-snap, footsteps and ambience effects without masking the narration. End with one refined low-impact sonic logo on the packshot.
[PRESERVE] Stable Dorian identity, exact watch design, correct wrist placement, realistic hands, one glass only, physically coherent frozen liquid, consistent hotel layout and natural lighting.
[AVOID] Identity drift, watch redesign, changing dial text, extra watches, duplicate glasses, moving extras during frozen time, superhero styling, fantasy magic, exaggerated shockwave, deformed hands, extra fingers, unreadable typography, subtitles, additional text, watermark, loud music or overlapping dialogue.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-energy kinetic product commercial
SCENE
Glossy red futuristic electric bicycle featuring a continuous curved frame, black components, and belt drivetrain. Minimalist architectural white grid background transitioning to a solid white studio sweep.
SHOT BREAKDOWN
0-4s — Black kinetic typography flashes on a white grid, reading "THE". Vertical text slides rapidly. Close-up of the red frame crossing the grid alongside "90 KM". Fast motion-blurred pan of the entire bike moving horizontally.
4-8s — Extreme macro shot of a glossy red tube with "BELT DRIVE" text. Crisp, static close-ups detail the black rear hub's toothed belt mechanism and a drilled silver disc brake rotor.
8-12s — Close-up profile of matte black handlebars and brake levers against the grid. Cut to a static full side profile of the swooping red bike. The camera smoothly orbits to a 3/4 rear perspective.
12-15s — The bike rests in a full side profile against a pure white, shadowless backdrop. Bold black text appears in sequence overhead: "OGEE", followed by "OGEE ONE", and finally "NO STRAIGHT LINES."
CAMERA
Fast-paced commercial videography. Aggressive whip pans, rapid staccato cuts, extreme macro detailing, and smooth orbital sweeps. Locked-off static frames for text reveals.
LIGHTING & PALETTE
High-key studio lighting. Soft diffused boxes create sharp linear reflections on the glossy frame. High-contrast palette: Metallic cherry red, matte black, stark white, polished silver.
AUDIO
Driving electronic bass track. Fast whoosh effects for text animations, subtle mechanical freewheel ticking, synthetic motor hum during motion shots.
AVOID
Human riders, outdoor settings, traditional metal bike chains, straight frame geometry, cluttered environments, lifestyle elements.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-end technology commercial, hyper-realistic 3D rendering.
SCENE
Male subject, clean-shaven, black t-shirt. Futuristic automotive factory, robotic manufacturing arms, dark metallic grey sports car. Wet urban street, neon billboards. Silver smartphone, multiple glass lenses. Bright white minimalist showroom, vehicle displays.
SHOT BREAKDOWN
0-4s — Extreme close-up of a man's face in deep shadow with a glowing circular light behind his head. Morphs into the man standing centrally inside a skeletal car chassis while mechanical robotic arms weld the metal, scattering bright orange sparks.
4-8s — The fully formed grey sports car sits on a factory line surrounded by robotic arms firing lasers. Hard cut to the rear angle of the car drifting aggressively through a heavily blurred, neon-lit city street at night.
8-12s — Low-angle high-speed tracking shot over wet asphalt. Dark debris floats and rushes past the lens toward a distant car. Hard cut to an extreme macro view of a silver smartphone camera module, covered in crisp water droplets.
12-15s — The man stands in a bright, circular white showroom filled with cars. He extends his open palm toward the camera, his hand and face warped by a prominent spherical glass lens effect. Fades to a black screen displaying white text: Created with MiniMax H3.
CAMERA
Sleek commercial cinematography. Fast, aggressive cuts. Extreme macro focus, high-speed tracking shots, severe motion blur, prominent fisheye distortion.
LIGHTING & PALETTE
High dynamic range. Clinical white overhead factory LEDs, intense orange sparks. Dark shadows in the city cut by vibrant red and cyan neon reflections. Dominant colors: metallic silver, deep black, neon red, stark white.
AUDIO
Pulsing electronic synth track. Industrial welding sizzles, aggressive engine revving, rushing wind, digital interface chimes.
AVOID
Amateur lighting, shaky handheld camera, low resolution, dull muted colors, naturalistic documentary framing.
Scene 1 (0–3s) – Luxury Reveal
A luxury perfume bottle slowly emerges from darkness, standing on a glossy black pedestal. Soft golden light beams gradually reveal the crystal-clear glass, while subtle volumetric fog creates depth. Extreme macro shot, cinematic lighting, ultra-realistic reflections, premium luxury commercial aesthetic.
Scene 2 (3–6s) – Precision Details
Extreme close-up of the perfume bottle as rich golden fragrance liquid gently swirls inside. The camera performs a smooth cinematic orbit, capturing intricate glass textures, flawless craftsmanship, and sparkling highlights. Ultra-detailed, photorealistic, premium commercial quality.
Scene 3 (6–9s) – AI Transformation
The perfume bottle seamlessly dissolves into glowing golden particles before instantly reforming into a futuristic luxury edition, maintaining perfect proportions and visual consistency. Dynamic orbit camera, seamless transformation, cinematic lighting, premium visual effects.
Scene 4 (9–12s) – Environment Transition
Without a single cut, the background transforms from a luxurious black studio into a futuristic neon metropolis. The perfume bottle remains perfectly consistent while the camera performs a dramatic dolly-in. Hyper-realistic, cinematic, high-end advertising style.
Scene 5 (12–15s) – Hero Finale
Slow-motion hero shot of the luxury perfume bottle elegantly rotating as glowing golden particles float around it. Premium black background, flawless reflections, cinematic logo reveal, luxury commercial ending, 8K photorealistic, blockbuster advertising quality.
Use @ Image1 as the man reference.
Use @ Image2 as the woman reference.
Use @ Image3 as the horse reference.
Create a surreal 15-second fashion-film sequence inside a minimalist monochrome blue studio. The woman performs an elegant contemporary dance. The man casually walks into frame wearing a completely serious expression. Without explanation, he immediately joins the choreography. His movements are awkward, strangely confident, almost ritualistic. The woman never acknowledges him. The horse behaves as though both dancers are part of its routine. It wanders through the studio. Runs behind them. Appears from impossible places. Stops. Looks directly into the camera. Leaves. Returns again. Sometimes all three performers accidentally synchronize for one beat before drifting apart again. The choreography becomes increasingly absurd but remains perfectly cinematic. Every movement is intentional. Every frame feels designed. Throughout the sequence, premium kinetic typography appears as part of the composition, not subtitles, but editorial motion graphics inspired by high-end After Effects title design. Animated words flash for only a few frames: THE GARDENER. THE DRIVER. THE HORSE. THE WOMAN. KNIFE. MOVE. FASTER. AGAIN. THE EXIT. These words slam into frame, wrap around the dancers, disappear behind bodies, stretch with motion blur, rotate in 3D, fragment into pieces, reveal through masks, pulse with the bass, smear across cuts, become oversized, tiny, vertical, upside down, and constantly transform using premium motion-design techniques. Add abstract editorial graphics: animated arrows, circles, blueprint lines, tape labels, interface markers, halftone textures, scribbles, grain, tracking graphics, geometric overlays, chromatic aberration, liquid masks, flash frames, split screens, typography trails, speed ramps and graphic wipes. Music evolves into strange electronic art-pop. Analog synths. Mechanical breathing. Heavy bass. Everything is synchronized to the rhythm. Final close-up. The woman whispers: "Again." The man quietly smiles for the first time. The horse suddenly sprints directly toward the camera. The word AGAIN. fills the screen before an instant cut to black.
[Upload reference ] + Use la ragazza in reference as a strict identity reference for the model and her yellow sunglasses.
Preserve face, hair, and the exact frame shape and colour throughout.
15 seconds, 16:9. Premium fashion commercial, photoreal live action.
Infinite black void, polished black floor. She is the only lit element: hard key from
one side, second hard light from the other, deep shadow between, strong speculars on
the yellow frame and lenses.
She walks slowly toward the camera in a black high-neck top and long black coat, chin
level, eyes on the lens. Camera tracks backward at her pace, holding her size in frame.
All type is heavy condensed uppercase sans-serif in vivid yellow, rendered as physical
objects in 3D perspective with real thickness, catching the same light as she does and
casting faint shadows on the floor.
[0-4s] LOOK rises out of the floor ahead of her in deep perspective, grows as she
approaches, and sweeps past on both sides out of frame.
[4-7s] SEE enters from the right at high speed, streaks behind her with heavy motion
blur, exits left.
[7-10s] FOCUS appears large and fully out of focus, resolves into razor sharpness over
half a second, holds, breaks apart.
[10-12s] Four thin yellow lines draw a rectangle around her and FRAME assembles along
its lower edge.
Throughout, passing type reflects across the glossy lenses as it moves near her.
[12-15s] She stops. All type collapses inward and vanishes into black. The camera
continues into a tight close-up on her face and the yellow sunglasses. She holds
completely still, eyes on the lens. On the black beneath her the title composes in the
same yellow type: "SHIOBA LENS", and below it, smaller: "MADE TO BE SEEN". Hold.
All text clean, legible, correctly spelled English capitals, each word once only. No
garbled or duplicated letters, misspellings, subtitles, watermarks, or other text or
logos.
Audio: low sustained bass,
Composition: model centered, all type within the central third of the frame
{ "shots": [ { "shot_id": "1", "start_time": "00:00", "end_time": "00:02", "camera_angle": "Close-up", "subject": "Strawberry", "action": "A single, dull strawberry transforms into a vibrant, ripe strawberry, floating against a pink background.", "visual_details": "Initial strawberry is muted, then becomes intensely red with visible seeds; pink background; subtle glow effect.", "audio_cues": "Light, subtle, almost magical sound effect." }, { "shot_id": "2", "start_time": "00:02", "end_time": "00:05", "camera_angle": "Medium shot", "subject": "Strawberry and beverage can", "action": "The vibrant strawberry transforms into a white and pink beverage can with 'STRAWBERRY CREAM' text. Liquid pours into the can from above, and strawberries/water droplets float around it.", "visual_details": "Can is sleek, covered in condensation; red liquid splashing into the can; numerous floating strawberries (whole and sliced) and water droplets; pink background.", "audio_cues": "Sound of liquid pouring, bubbling, and light splashes; upbeat, commercial-style music." }, { "shot_id": "3", "start_time": "00:06", "end_time": "00:10", "camera_angle": "Close-up", "subject": "Top of the beverage can", "action": "Focus on the top of the can as the liquid continues to pour and splash, with droplets and strawberries in motion.", "visual_details": "Intricate details of the can's opening and condensation; dynamic splashes of liquid; close-up of floating strawberry pieces.", "audio_cues": "Enhanced sounds of liquid splashing and bubbling; continued music." }, ] }
Create a 15-second ultra-premium luxury perfume commercial in cinematic 16:9.
A crystal perfume bottle with a sleek black-and-gold design stands on a glossy reflective surface inside a dark luxury studio. The commercial opens with an extreme macro shot of the engraved cap, followed by slow cinematic rotations revealing every elegant detail. Dramatic golden light sweeps across the glass while soft volumetric light and subtle mist create a premium atmosphere.
Elegant water splashes, floating crystal shards, and shimmering golden particles move naturally around the bottle in ultra slow motion without covering the label. Every reflection is physically accurate with realistic caustics, premium glass refractions, and highly detailed liquid simulation.
The camera transitions through smooth macro close-ups, low-angle hero shots, orbiting movements, and dramatic push-ins using luxury advertising cinematography. Rich black marble, gold accents, and soft smoke enhance the high-end aesthetic.
End with the bottle perfectly centered on a glossy pedestal as the lighting intensifies for a premium hero reveal. Display a fictional luxury brand logo "NOIR ÉLITE" with the tagline "Crafted to Leave a Mark."
Photorealistic, Hollywood luxury TV commercial, ultra-detailed, flawless glass rendering, realistic water physics, cinematic color grading, HDR, ray-traced reflections, depth of field, premium product advertising, 8K quality.
Use storyboard as the complete creative direction, shot list, composition, pacing, and cinematic sequence.
Use LuxuryWatch as the exact product reference. Preserve the watch's design, dial, case, leather strap, proportions, materials, and fine details consistently throughout every scene.
Create a world-class luxury watch commercial.
Follow the storyboard exactly while transforming each frame into a seamless cinematic sequence.
Begin with a dramatic reveal of the luxury watch inside its presentation box. Slowly unveil the timepiece as warm golden light reflects across the polished platinum case and sapphire crystal. Transition into breathtaking macro shots showcasing the intricate dial, sweeping second hand, open-heart mechanical movement, and handcrafted finishing.
Introduce an impeccably dressed gentleman preparing for an exclusive black-tie gala. He carefully lifts the watch, fastens it to his wrist, and confidently adjusts his tailored suit. Every movement should feel refined, natural, and premium.
Finish with a powerful hero product reveal on a glossy black marble pedestal surrounded by floating metallic particles, subtle golden dust, and dramatic rim lighting. End with an unforgettable luxury advertising composition worthy of an international Swiss watch campaign.
Style:
Luxury Swiss watch commercial.
Ultra-photorealistic.
Award-winning commercial cinematography.
IMAX-quality visuals.
Luxury editorial aesthetic.
Hyper-realistic metal reflections.
Flawless sapphire crystal.
Precision mechanical details.
Shallow depth of field.
Elegant macro cinematography.
Physically accurate lighting.
Rich contrast.
Premium black, silver, and champagne gold color palette.
Commercial-grade production quality.
8K masterpiece.
Create a 15-second premium cinematic branding TVC for a futuristic smartphone brand called NOVA X.
0–5 seconds: Extreme close-up of a sleek futuristic smartphone resting on a glossy black surface. Dramatic studio lighting sweeps across the device, revealing its ultra-thin design and premium metallic edges. Cinematic camera push-in, macro product details, realistic reflections.
5–10 seconds: The phone activates with a stunning futuristic interface. A young professional picks it up, and the environment transforms into a vibrant digital world with floating holographic visuals, smooth UI animations, and seamless interaction. Dynamic camera movement, premium commercial aesthetic.
10–15 seconds: Hero product shot of the smartphone standing vertically against a minimalist futuristic background. The NOVA X logo appears elegantly with the tagline: “NOVA X — The Future in Your Hands.” Cinematic lighting, high-end TV commercial quality, photorealistic, ultra-detailed, smooth motion, polished advertising style, 4K.
Create a premium cinematic fashion campaign video using the five uploaded apparel images as strict product references. The video should introduce each outfit one by one, while maintaining the exact original clothing design, silhouette, fabric texture, colors, patterns, accessories, stitching, and proportions from every reference image. Do not redesign, simplify, replace, or merge any garments. Format: vertical 9:16 Duration: approximately 15 seconds Style: luxury fashion commercial, editorial, futuristic, minimal, sophisticated Visual quality: photorealistic, commercial-grade, high-end fashion film, sharp textile detail, realistic fabric movement Sequence: 0–2 seconds: Begin with a dark minimal studio. A narrow beam of light slowly reveals the first outfit. Start with an extreme close-up of fabric texture, stitching, metallic details, and layered materials. Smooth cinematic camera movement. 2–5 seconds: Reveal the full first outfit on a stylish fashion model. The model makes one subtle pose while the camera performs a slow vertical tilt from shoes to face. 5–8 seconds: Transition through a fast match cut into the second and third outfits. Use elegant whip pans, fabric wipes, lighting flashes, and seamless motion transitions. Each outfit must remain visible long enough to understand its full design. 8–11 seconds: Show the fourth outfit in a wider architectural studio environment. The model walks slowly toward the camera while the fabric moves naturally. Add controlled wind, soft shadows, and reflective surfaces. 11–14 seconds: Reveal the fifth outfit as the hero look. Use a dramatic low-angle shot, slow orbiting camera movement, and stronger cinematic lighting. Emphasize the silhouette, construction, and key design details. 14–15 seconds: End with all five outfits appearing rapidly in rhythmic editorial cuts, followed by a clean final frame with the hero outfit centered against a minimal background. Camera: Smooth dolly shots, macro textile close-ups, slow orbit, low-angle fashion shots, controlled handheld energy only during transitions. Lighting: High-contrast luxury studio lighting, soft rim lights, precise highlights on fabric, metal, leather, and accessories. Avoid overexposure. Motion: Natural model movement, restrained confident poses, realistic walking, subtle fabric physics. No exaggerated dancing. Editing: Fast but elegant editorial pacing. Clean match cuts between outfits. Every transition should feel intentional and synchronized with the music. Important: Preserve the exact identity and design of all five apparel references. Do not mix clothing elements between outfits. Do not change logos, prints, colors, garment length, footwear, accessories, or materials. Do not add random text, subtitles, watermarks, extra garments, duplicated limbs, distorted hands, warped fabric, or unstable faces.
Platinum-blonde subject, black patent-leather trench, orange firelight across the coat. Nighttime blaze, black smoke.
VHS glitches, CCTV dropouts, 90s grain, scanlines, chromatic aberration, flash-to-white cuts.
15s, one gen.
A UI/UX motion showcase video for a high-performance luxury sports car brand landing page, created as an image-to-video project based on Product Image 1, with the car in the image remaining the core subject throughout.
First screen – Hero Section:
A premium black background, with the car positioned at the center of the page as the main visual focus. The camera slowly pushes in. A minimalist navigation bar appears at the top of the page:
"MODEL"
"DESIGN"
"PERFORMANCE"
"TECHNOLOGY"
"CONTACT"
On the left side, a large brand headline appears:
"UNLEASH THE FUTURE"
Below it, a subtitle reads:
"PURE PERFORMANCE. LIMITLESS SPEED."
At the bottom, two buttons appear:
"EXPLORE MODEL"
"BOOK A TEST DRIVE"
Scroll down into the vehicle design showcase section:
Main headline:
"DESIGNED FOR SPEED"
Showcase text:
"AERODYNAMIC BODY"
"CARBON FIBER STRUCTURE"
"PRECISION ENGINEERING"
These are paired with close-up shots of the car’s front fascia, headlights, wheels, and body lines.
Continue scrolling into the performance section:
Headline:
"ENGINEERED TO DOMINATE"
Display performance specification cards:
"POWER"
"HORSEPOWER"
"TORQUE"
"ACCELERATION"
Use dynamic, high-tech animated numeric displays for:
"0–100 KM/H"
"3.2 SEC"
Enter the interior showcase section:
Headline:
"DRIVER-FOCUSED INTERIOR"
Showcase text:
"PREMIUM MATERIALS"
"DIGITAL COCKPIT"
"ADVANCED CONTROL SYSTEM"
Final screen:
A full view of the car is displayed, while light sweeps across the body in the background.
Centered text:
"READY TO DRIVE"
Button:
"CONFIGURE YOUR CAR"
Visual style:
A premium automotive brand website, similar to a supercar launch page. Dark metallic materials, carbon fiber textures, dynamic lighting, aerodynamic lines, and a cinematic luxury car advertisement aesthetic. The webpage uses large, bold, slightly slanted sans-serif typography, with fast yet smooth scrolling animation, parallax effects, mouse-hover zoom interactions, highlight scanning effects, floating information cards, and animated button feedback.
REFERENCE USAGE:
Image 1 — the KALDR bottle. Preserve the smoked charcoal glass, bevelled edges, pale blue liquid, brushed gunmetal cap and the etched silver KALDR mark exactly.
Image 2 — the closing brand lockup. Preserve the letterforms, tracking, silver finish and the COLD KEEPS line exactly. It appears only in the final shot, alone on black.
Image 3 — the location, palette, cloud, surf and film texture for the whole film.
Image 4 — a three panel character sheet of the woman. Use it only to match her face, hair, frost detail and black greatcoat. Do not reproduce the sheet's panel layout, its grey backdrop or its flat studio lighting. She must appear as a single person inside the Image 3 environment, lit by that location.
Audio 1 — the voice for the woman's spoken line. Match its timbre, pitch, accent, breathiness and pacing exactly. Use it only for her voice, not as background audio or ambience.
Premium luxury fragrance brand film. Photoreal 35mm anamorphic, high contrast, fine grain, cold specular highlights, deep crushed blacks. Palette strictly black sand, gunmetal, glacial blue and silver, with no warm tones anywhere. Setting: a black volcanic beach on a northern coast at blue hour under heavy storm cloud. Tone: severe, violent, expensive. This is a fast, aggressive fashion edit, not a calm product film. Never slow, never ceremonial, never a slideshow of pretty holds.
[0-1.5s] Cold open, no establishing shot. Camera at water level, lens half submerged, [Static shot]. A sheet of freezing surf races straight at the lens. Her boots stride hard into frame through the water, coat hem whipping. HARD CUT.
[1.5-2.6s] Extreme macro insert. Frost crystals race across black glass and flood the etched KALDR mark with rime, filling the letters. HARD CUT.
[2.6-4.2s] Behind her, low and close, [Tracking shot] pushing fast. She walks straight into an oncoming wave that towers over her, coat streaming sideways, never breaking stride. HARD CUT.
[4.2-5.4s] Reverse, low angle from the water. The wave collapses over her. Camera [Shake] on the impact. Cut on the peak of the white spray. HARD CUT.
[5.4-9s] SLOW MOTION. The wave freezes solid around her mid collapse. She stands inside a shell of blue black ice, the spray suspended in the air as a thousand hanging shards, her coat frozen mid snap, her face calm and unbothered. Camera [Tracking shot] orbits right through the suspended shards, holding her at centre. This is the hero image of the film.
[9-9.8s] Snap back to real time. The ice shell detonates outward. Camera [Pull out] fast and hard through the exploding shards. HARD CUT.
[9.8-12.6s] Tight close up, [Push in]. She walks out of the collapsing ice straight at the lens, ice water running off her coat, looking directly into camera. She says quietly: "I was never meant to melt." She holds the look for a beat after the line. HARD CUT.
[12.6-13.8s] The bottle alone, upright on wet black sand, shot low and close on a macro lens. Frost blooms outward from its base toward the lens. No text of any kind in this shot. HARD CUT.
[13.8-15s] Pure black frame. The brand lockup from Image 2 appears alone, centred, exactly as in the reference. The wordmark KALDR emerges from darkness at low opacity, letter spacing opening over 0.4 seconds into sharp focus with a faint edge glow, and the line COLD KEEPS sits smaller beneath it. Nothing else is in this frame. Critical: the bottle, the woman, the beach and the wordmark must never share a frame. The lockup must never overlap or be occluded by the bottle, and the etched mark on the glass must never appear in the same shot as the lockup. Hold the lockup to the end.
Dialogue and lip sync: only one line is spoken, in the shot beginning at 9.8 seconds: "I was never meant to melt." Match the voice in Audio 1 exactly, including its timbre, breathiness, pacing and the way the sentence lands without rising at the end. Do not substitute a different voice, do not add reverb or processing that changes its character. Her lip movement must match the words frame accurately and stop when the line ends. Her breath fogs on the words. Do not repeat the line and do not add any other spoken words anywhere in the film.
Pacing: hold every cut until its stated timecode and do not shorten the last two shots. The first four shots are fast and aggressive. The slow motion shot is the only long hold in the film. Everything after it is fast again.
Audio: hard coastal wind, heavy surf, a low sub bass drone. At 5.8 seconds, one deep impact hit, a splintering glass freeze crackle and a reversed swell. Then cut the wind, the surf and all low end to complete silence from 6 seconds to 9 seconds, leaving only isolated ice ticks and faint crystal ring in that window. This silence is mandatory and must be obvious. At 9 seconds the full mix slams back in with a hard low kick and the crash of shattering ice into water. As she speaks, duck the wind, surf and low end so her voice sits forward and dry. The final second holds one sustained low string chord decaying into wind. No voiceover, no narrator, no lyrics, no recognisable melody.
Do not add other people, boats, buildings, vehicles, modern objects, subtitles, on screen captions, watermarks, or any text other than specified. Do not warp or distort the bottle or the wordmark. No cartoon or plastic CGI water or ice. Keep skin texture real, no over smoothing. Never let the ice or spray form a face, eyes, or a creature.
High-end luxury auto commercial, cinematic night-to-dawn lighting, wet reflective surfaces, anamorphic lens flares, rich emerald green and deep black color grade, heavy film grain.
Use @Audio1 for background music
Use the provided 4x4 grid as the only visual reference @Image1 . You must show ALL 16 panels from the grid in sequence. Lock the exact same character (blonde swept-back hair, stern heavy-browed face, green-and-black checkered haori) and the exact same green-and-black checkered sports coupe in every shot. Do not invent new shots or change anything.
[TIMELINE - ALL 16 PANELS]
0.0-0.9s: Panel 1 – Extreme wide rain-soaked city road with distant headlights and skyline
0.9-1.8s: Panel 2 – Character standing arms crossed under streetlight
1.8-2.7s: Panel 3 – Extreme close-up of character’s angry scowling face
2.7-3.6s: Panel 4 – Character standing next to the checkered car under city lights
3.6-4.5s: Panel 5 – Character walking toward the car from behind in the rain
4.5-5.4s: Panel 6 – Close-up of hand gripping the door handle
5.4-6.3s: Panel 7 – Character sitting in the driver’s seat, intense expression
6.3-7.2s: Panel 8 – Dashboard and steering wheel close-up with green lights
7.2-8.1s: Panel 9 – Low rear three-quarter shot of the car accelerating in the rain
8.1-9.0s: Panel 10 – Side tracking shot of character driving the checkered car
9.0-9.9s: Panel 11 – Car driving on mountain road at sunset
9.9-10.8s: Panel 12 – Aerial/coastal highway shot of the car at sunset
10.8-11.7s: Panel 13 – Character standing next to the car on rooftop with city skyline
11.7-12.6s: Panel 14 – Character leaning on the car, arms crossed, hero shot
12.6-13.5s: Panel 15 – Extreme close-up of the car’s front headlights and grille
13.5-15.0s: Panel 16 – Character and car silhouetted against the rising sun
coherent character and vehicle identity across every cut 📷Image1 , cinematic color grade, heavy film grain, no artifacts, movie-level continuity, fast-paced 15-second commercial.
Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, makeup, skin tone, body proportions, pearl necklace, rings, and facial consistency throughout every shot.
Create a 15-second ultra-realistic luxury lip gloss commercial. The video opens with a close-up of the woman looking directly into the camera while confidently holding the lip gloss beside her face. She then gracefully walks down an elegant marble staircase as the camera smoothly tracks backward. Cut to her sitting on a luxurious blush-pink velvet sofa, smiling softly while placing the lip gloss on a marble coffee table. Cinematic macro shots showcase the applicator being removed, the glossy texture, and the premium packaging. She applies the lip gloss while looking into a vanity mirror, followed by extreme close-ups of her glossy lips catching soft studio light. Finish with a confident beauty pose holding the lip gloss beside her face, then transition to a premium floating hero shot of the product rotating above a glossy marble surface with warm rose-gold lighting.
Ultra-realistic beauty cinematography, luxury cosmetic campaign, smooth gimbal movement, realistic skin textures, macro product photography, shallow depth of field, creamy bokeh, premium color grading, 4K HDR, 16:9, no text, subtitles, logos, or watermarks.
Duration: 15 seconds | Aspect Ratio: 16:9 | Style: Authentic UGC / iPhone selfie-vlog, handheld, natural light, slight motion blur, TikTok/Reels energy — NOT cinematic, NOT overly polished. Feels like a real creator filmed this on their phone.
Product Reference: Use the uploaded assorted sushi platter image as the only product reference. Keep the sushi arrangement, fish cuts, rice texture, garnish placement, colors, and proportions identical in every shot—do not redesign or alter the food.
Camera: iPhone 15 Pro front + back camera switching, handheld with natural wobble, slight autofocus breathing, vertical-style framing cropped to 16:9, occasional finger near the edge of the lens, realistic phone HDR, warm apartment lighting, subtle reflections on the takeaway container.
Character Description
Name (for reference): Aoi
A young Japanese woman in her early 20s with a naturally beautiful, approachable appearance. Straight shoulder-length black hair with soft bangs, light natural makeup, warm expressive eyes, wearing an oversized beige knit sweater. Friendly, energetic personality like a genuine lifestyle creator. Sitting in a cozy modern Tokyo apartment with warm ambient lighting.
Shot Breakdown
SHOT 1 (0–2s) — The Reveal
Selfie angle, laughing while holding the sushi takeaway box toward the camera. Quick jump cut.
Dialogue: "Okay... sushi night it is."
SHOT 2 (2–4s) — The Open
Overhead handheld shot as she opens the container. Fresh sushi is revealed with slight camera shake as she leans closer.
SHOT 3 (4–6s) — The Close-Up
Quick punch-in on the sushi. Autofocus locks naturally onto the salmon and tuna while the background softly blurs. Ambient apartment sounds only.
SHOT 4 (6–8s) — The Pick-Up
Low candid angle as chopsticks lift a salmon nigiri. Natural movement, slight handheld shake like a friend filming across the table.
SHOT 5 (8–10s) — The Reaction
Back to selfie cam. She takes a bite, smiles with widened eyes.
Dialogue: "Wow... that's amazing."
SHOT 6 (10–12s) — The Cutaway
Close handheld shot of the sushi tray on the table while her hand reaches in for another piece just outside the frame. Casual lifestyle b-roll feel.
SHOT 7 (12–14s) — The Wrap-Up
Selfie angle. She raises a piece of sushi with chopsticks toward the camera.
Dialogue: "Best decision tonight."
SHOT 8 (14–15s) — End Tag
Quick freeze on the sushi tray with natural handheld wobble. Soft handwritten-style overlay: "sushi night = perfect 🍣" Cut to black.
Look & Feel
Warm indoor lighting, slightly grainy smartphone sensor look, imperfect framing, authentic reactions, minimal dialogue (3 short lines), hard jump cuts, casual pacing, genuine creator content.
Negative Prompt
cinematic color grading, overly smooth gimbal movement, studio lighting, professional voiceover, staged acting, CGI food, unrealistic fish texture, distorted sushi, extra fingers, warped hands, text glitches, logo distortion, overly polished commercial feel.
Premium food commercial. Extreme macro shot of a single ripe strawberry falling toward a white ceramic bowl. Before it lands, the environment changes through four seamless seasonal match cuts: a sunlit spring greenhouse, a hot summer picnic, an autumn kitchen and a candlelit winter dining room. The strawberry stays in exactly the same screen position, size, orientation and downward motion through every transition. It lands in fresh cream during the winter scene, sending one graceful crown-shaped splash upward. Photorealistic food texture, high-speed product cinematography, clean commercial lighting. Each season has distinct environmental sound, but one continuous musical phrase connects the entire sequence. No hands, labels or additional fruit.
Create a premium 9:16 fashion-eyewear commercial. Match the reference video’s shot rhythm, edit speed, white-cyclorama look, and severe fashion attitude. Use a seamless minimal white studio with clean, bold, avant-garde art direction worthy of a global luxury campaign.
- Use Image 1 for the key visual: two full-body female models, one Black and one white, preserving their elevated wardrobe, body language, studio lighting, runway presence, and cool attitude. Use Image 2 for facial details. Both models wear futuristic luxury eyewear based on Image 3: wraparound curved lenses, a sharp cat-eye/goggle hybrid silhouette, mirrored reflections, streamlined temples, and the finish of a premium fashion accessory.
FORMAT:
15-second cinematic vertical car transformation film
9:16 aspect ratio
Ultra-realistic automotive commercial aesthetic
Japanese street culture + luxury cinematic realism
High-energy transformation pacing
CONCEPT:
“FROM STOCK TO STREET WEAPON”
A normal Maruti Suzuki Swift slowly transforms into a fully modified street machine through cinematic garage sequences, mechanical close-ups, aggressive lighting, and dramatic reveal shots.
TIMELINE:
0:00–0:02
Old stock white Maruti Suzuki Swift parked inside a dim industrial garage.
Dust particles in sunlight.
Static realistic atmosphere.
Soft engine ticking sounds.
0:02–0:04
Quick cinematic close-ups:
tools dropping on metal table,
garage lights turning on,
mechanic gloves tightening,
car jack lifting vehicle.
Fast-paced editing begins.
0:04–0:06
Transformation montage:
new alloy wheels installed,
wide tires mounted,
lowered suspension,
custom front bumper attached,
black spoiler fitted.
Mechanical sparks and cinematic motion blur.
0:06–0:08
Paint transformation sequence.
Original white paint peels away into glossy metallic midnight black.
Water droplets and reflections across body panels.
Neon garage lighting reflects on paint.
0:08–0:10
Interior upgrade shots:
digital dashboard glowing,
sport steering wheel,
bucket seats,
ambient red lighting,
push-start ignition.
Engine rev echoes.
0:10–0:12
Aggressive cinematic reveal:
modified Swift exits garage slowly.
Headlights turn on through smoke.
Low-angle tracking shots.
Wet asphalt reflections.
Turbo flutter sound.
0:12–0:15
Final hero sequence:
car speeding through empty city streets at night,
rolling shots,
drifting corner,
rain reflections,
motion blur,
camera orbit around vehicle.
End with parked hero shot under neon lights.
FINAL TEXT:
“SWIFT — REBORN.”
VISUAL STYLE:
Fast & Furious-inspired realism
Moody cinematic lighting
Japanese underground street-racing atmosphere
Wet asphalt reflections
Practical garage lighting
High-detail metallic textures
Subtle film grain
Deep contrast shadows
Realistic smoke and sparks
CAMERA:
ARRI Alexa Mini LF aesthetic
Anamorphic lens look
Low-angle tracking shots
Wheel close-ups
Slow-motion mechanical shots
Drone-style orbit reveal
Handheld garage realism
SOUND DESIGN:
Metal tool impacts
Hydraulic jack sounds
Engine revs
Turbo flutter
Deep bass transitions
Tire screeches
Cinematic trailer hits
Aggressive phonk-inspired background energy
QUALITY:
Masterpiece-level automotive realism
Luxury commercial production quality
Pinterest-saveable cinematic car edit
Ultra-detailed reflections and textures
Feels like a premium car modification advertisement
Create a dynamic product-landing-page UI/UX demo inspired by Nike's digital language, built around the product in Image 1. Use oversized, bold, italicized sans-serif typography and backgrounds that combine speed-driven light streaks with dark carbon fiber or breathable performance-mesh textures. Show a smooth, fast, powerful scroll through the page, plus high-impact hover interactions with scale-ups and color inversion.
Create a 15-second ultra-premium cinematic luxury perfume commercial designed to fully showcase MiniMax H3's multimodal capabilities.
Output Settings:
• Duration: 15 seconds
• Resolution: 2K (1440p)
• Frame Rate: 24 FPS
• Aspect Ratio: 9:16 Vertical
• Native Stereo Audio
• Commercial-grade quality
Scene 1 (0–3s)
Extreme macro shot of a crystal luxury perfume bottle resting on polished black marble. Golden sunrise light passes through the glass, creating realistic caustics and sparkling reflections. Tiny perfume particles float naturally in the air. Slow cinematic push-in with perfect depth of field.
Scene 2 (3–6s)
A luxury fashion model wearing an elegant black dress walks confidently through a futuristic golden hallway. The camera smoothly circles around her while she gracefully picks up the perfume bottle. Hair moves naturally, realistic fabric simulation, premium fashion campaign quality.
Scene 3 (6–10s)
She sprays the perfume. The mist transforms into flowing golden particles that evolve into blooming flowers, liquid gold ribbons, shimmering butterflies, floating crystal fragments, and elegant light trails surrounding her. Every movement is physically realistic with seamless cinematic transitions.
Scene 4 (10–13s)
Hero beauty sequence. Slow-motion close-ups of the model's face, glowing skin, elegant eyes, glossy lips, luxury jewelry, and the perfume bottle. Beautiful bokeh, premium studio lighting, realistic reflections, cinematic lens movement.
Scene 5 (13–15s)
Epic ending. The perfume bottle rotates slowly on a glossy black pedestal surrounded by floating golden particles and soft luxury lighting. The model stands elegantly in the background. Premium cinematic composition worthy of a global luxury brand campaign.
Visual Style:
Luxury brand commercial, Dior Beauty, Chanel, Tom Ford, Apple-level production quality, Hollywood cinematography, ultra-photorealistic, ray tracing, global illumination, volumetric lighting, realistic reflections, premium color grading, cinematic depth of field, physically accurate materials, ultra-detailed textures, smooth camera movement, flawless facial animation, natural body motion, production-ready advertising quality.
Negative Prompt:
Low quality, blurry, noise, flickering, unstable motion, distorted anatomy, bad hands, bad face, duplicate objects, watermark, logo, text overlay, compression artifacts, oversaturated colors, unrealistic physics, low-detail textures.
TITLE: Luxury Emerald Necklace Commercial Storyboard
FORMAT:
• Single-page premium storyboard
• 3:4 portrait ratio
• Editorial presentation board
• 8 cinematic frames arranged in a clean luxury grid
• Ultra-high-resolution, 8K
HEADER:
• Elegant serif typography
• White, emerald green, champagne gold, and black luxury palette
• Premium information cards
• Luxury jewelry icons
• Section: "Why This Style Works"
STORYBOARD SCENES:
1. A handcrafted emerald necklace resting inside an elegant velvet jewelry box on polished black marble under a dramatic spotlight.
2. The jewelry box slowly opening as warm golden light reveals the brilliant emerald necklace.
3. Extreme macro close-up of the emerald gemstone and diamond accents with breathtaking clarity, crystal reflections, and luxurious sparkle.
4. A graceful woman preparing for an exclusive gala, delicately lifting the necklace from the box.
5. The emerald necklace being elegantly fastened around her neck, emphasizing craftsmanship and sophistication.
6. Emotional cinematic close-up highlighting the necklace glowing against flawless skin with soft luxury lighting.
7. High-fashion editorial portrait featuring the model in an elegant couture gown, with the emerald necklace as the unmistakable focal point.
8. Hero product shot of the emerald necklace displayed on a glossy black reflective pedestal surrounded by floating emerald particles, subtle golden dust, dramatic rim lighting, and premium luxury branding composition.
STYLE:
Inspired by world-class luxury jewelry campaigns, premium fashion editorial, soft cinematic lighting, refined elegance, crystal-clear gemstone reflections, ultra-realistic textures, shallow depth of field, award-winning commercial photography, luxury branding aesthetic, 8K masterpiece.
Cinematic 15-second commercial shot, fast-paced editing, dark humor, creepy comedy style. Ultra-realistic, 8k resolution. A surreal hamburger restaurant with moody neon lighting (red and green). Close-ups of distorted, wide-eyed hungry people smiling creepily while eating massive juicy cheeseburgers. Fast cuts: sizzling bacon in flames, towering stacks of burger trays, a mysterious retro waiter with a unnerving wide smile. Hyper-detailed melted cheese, glossy sauce drips, chaotic and fun atmosphere, 90s thriller aesthetic crossed with a fast-food ad.
15-second hyper-stylized financial motion graphics sequence.
0–2s: A minimal black credit card rotates slowly in empty space. Embossed numbers catch the light.
2–4s: Camera pushes extremely close into the card numbers. The digits detach from the surface and begin floating in three-dimensional space. Hundreds of numbers stream past camera like financial data.
4–6s: The numbers align into columns and suddenly print themselves onto an impossibly long receipt. Camera races downward along the receipt as transactions rapidly appear.
4.50
12.99
48.20
127.00
TOTAL
6–8s: The receipt folds upward like paper architecture. Its printed numbers become vertical bars, transforming the paper into a physical financial graph.
8–10s: Graph bars rise and fall dramatically. A thin line races across their tops while percentages and tiny data labels appear.
10–12s: One graph point shoots upward and becomes a spinning metallic coin.
12–14s: Hundreds of coins rain downward, bounce, stack and organize themselves into the exact rectangular proportions of the original credit card.
14–15s: The coin structure instantly becomes the black card again.
Premium financial identity, tactile paper simulation, kinetic typography, metallic coins, elegant data visualization, satisfying physics, seamless object transformations, luxury fintech commercial meets experimental motion design.
Create an ultra-realistic, cinematic luxury perfume commercial with a romantic evening atmosphere.
Scene 1: A beautiful young woman with a short brunette bob haircut, elegant features, and natural makeup stands in front of a mirror, wearing a sophisticated white evening dress and delicate gold jewelry. She smiles softly while getting ready for a special evening.
Scene 2: Close-up of her smartphone resting on a bedside table as she receives a message. Warm ambient lighting creates a cozy, intimate mood.
Scene 3: She opens her wardrobe and chooses an elegant white dress. Capture natural movements, realistic fabric physics, and cinematic framing.
Scene 4: A macro close-up of her hand holding a luxurious transparent glass perfume bottle with pink fragrance. She gently sprays the perfume on her wrist. Highlight the fine mist, glass reflections, and premium product details.
Scene 5: She turns away from the mirror, her short hair moving naturally as she prepares to leave. Use a smooth cinematic camera movement.
Scene 6: A beautiful European city street at night, with warm restaurant lights, passing cars, and soft reflections on the pavement. The woman walks gracefully toward a stylish restaurant.
Scene 7: A romantic close-up of the woman and a handsome young man meeting outside at night. They exchange warm smiles and look into each other's eyes, creating a subtle romantic moment.
Visual style: Premium luxury perfume advertisement, cinematic storytelling, warm golden lighting, realistic skin texture, shallow depth of field, elegant camera movements, soft bokeh, natural human expressions, sophisticated color grading, photorealistic details, 4K quality.
Maintain consistent character identities, realistic movements, seamless transitions, and a refined romantic atmosphere. No text, no subtitles, no logos, no watermark.
0–2s — THE SIP
Fast close-up of the ginger-haired golfer on a sunny golf course. She grabs the Sprite can, cracks it open — PSHHHT! — condensation and tiny droplets flying in slow motion. She takes a refreshing sip and gives a confident little smirk.
2–4s — GAME ON
Hard cut. She tosses the Sprite can slightly upward, catches it, grabs her golf club, and steps into position. Quick whip-pan around her as sunlight flashes across the frame.
4–7s — THE SWING
Rapid montage: close-up of her gripping the club → golf ball on the tee → her eyes locking onto the ball → skirt and ponytail moving as she swings. She hits the ball with a powerful, perfectly timed CRACK!
7–10s — FOLLOW THE BALL
Ultra-fast camera follows the golf ball flying across the bright green course. Speed ramp as it passes trees and sunlight, then lands perfectly near the hole.
10–12s — HOLE IN ONE
She watches it drop into the hole. Quick reaction shot: she smiles, spins the club casually, and walks toward the camera like she absolutely knew that was happening.
12–15s — HERO SHOT
She grabs the cold Sprite can again and takes another sip. Camera pushes in as she lowers the can, smiling confidently. Condensation sparkles in the sunlight. End on a clean product close-up of the Sprite can beside the golf ball.
On-screen text:
“REFRESH. RELOAD. PLAY.”
SPRITE — THIRSTY FOR MORE.
Fast cuts, energetic commercial pacing, whip transitions, speed ramps, crisp summer lighting, realistic golf physics, dynamic camera movement, refreshing splash effects, premium sports-ad aesthetic.
One-Line Prompt: Syrup Cools into a Frost Pattern (Local Open Weights)
15s16:9
Minimax H3, open weights, generated locally. Sunday breakfast, cabin rules.
Prompt: "it cools into a lacy amber pattern like frost on a window"
Duration: 15s. Camera: locked, slightly above. Rendered locally in ComfyUI, then Topaz to 4K.
The pitcher travels one way across the tray. The lace line grows in the same direction, so the model has a path to draw.
Luxury Sunglasses UGC Unboxing Review (Character + Product References)
15s3:2
These sunglasses might just be my new obsession. 🖤✨
Created in Minimax H3
Prompt:
Use the attached girl as the exact character reference. Preserve her facial identity, facial features, eye color, long wavy brown hairstyle, makeup, skin tone, body proportions, jewelry, and overall appearance consistently across every shot.
Use the attached sunglasses as the exact locked product reference. Preserve the black oval-shaped frames, dark lenses, gold detailing at the temples, hinge structure, proportions, materials, and finish exactly. The sunglasses must remain identical in every frame.
Create an ultra-realistic luxury UGC creator review filmed entirely in an elegant modern lounge area, not a bedroom. The lounge should feel sophisticated, warm, expensive, and naturally lived-in: cream boucle sofa, marble or stone coffee table, soft neutral cushions, elegant floor lamp, subtle gold accents, large windows, tasteful décor, and warm late-afternoon sunlight entering from the side.
The woman wears the same cream/white knit sweater, beige trousers, gold hoop earrings, delicate pendant necklace, and rings from the reference image.
STORYBOARD — 15 SECONDS
SHOT 1 — 0–2 sec | Casual introduction
Medium handheld smartphone shot. The woman sits comfortably on the cream sofa in the lounge with the sunglasses box and leather carrying case placed naturally on the coffee table beside her. She looks directly into the camera with a genuine smile and says:
“Okay, these are way nicer than I expected.”
Natural creator energy, relaxed posture, subtle handheld movement.
SHOT 2 — 2–4 sec | Picking up the packaging
She leans toward the coffee table and picks up the luxury sunglasses box. Camera moves slightly closer as she turns the box toward the lens. She opens it naturally.
Capture realistic packaging texture and believable hand movements.
She says:
“Even the little details feel so well done.”
SHOT 3 — 4–6 sec | Case reveal
Close-up from slightly above her hands as she reveals the leather sunglasses case inside the box. She lifts the case out and opens it.
Warm sunlight creates soft highlights on the leather and gold hardware.
SHOT 4 — 6–8 sec | Sunglasses reveal
She carefully removes the sunglasses from the case. Cut to a beautiful macro product shot as she holds them between her fingers.
Slowly rotate the sunglasses so the camera clearly sees the front frame, dark lenses, gold temple detail, side profile, and hinges.
She says:
“And they’re ridiculously light.”
SHOT 5 — 8–10 sec | Putting them on
Return to a medium shot. She smiles, lifts the sunglasses toward her face, and puts them on naturally.
She adjusts the temples with both hands, then gives a subtle confident smile toward the camera.
SHOT 6 — 10–12 sec | Lounge sunlight test
She stands beside the large lounge window wearing the sunglasses. Camera follows her with smooth handheld movement.
She turns slightly toward the sunlight, then angles her face left and right so the lenses catch realistic reflections.
She says:
“They actually feel this good on.”
SHOT 7 — 12–14 sec | Lifestyle moment
She walks back toward the sofa, casually removes the sunglasses, and places them beside the leather case and box on the coffee table.
Camera briefly focuses on the sunglasses before shifting focus back to her.
SHOT 8 — 14–15 sec | Final product close-up
She picks the sunglasses back up and holds them beside her face while looking directly into the camera.
Warm smile.
She says:
“Yeah… these are staying in my rotation.”
Finish with a subtle camera push-in toward the sunglasses in her hand, with the lounge softly blurred behind her.
VISUAL STYLE
Photorealistic luxury lifestyle UGC, authentic smartphone creator footage, elegant lounge interior, warm golden-hour sunlight, natural skin texture, realistic facial expressions, subtle handheld camera movement, cinematic autofocus, shallow depth of field, neutral color palette, 4K HDR, 16:9, 24fps.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Realistic everyday vlog video
SCENE
Three young Asian women wearing casual summer clothes including tank tops, t-shirts, and denim shorts, standing outside a suburban house. A large grey monitor lizard clinging to a black metal driveway gate, and a residential street with houses.
SHOT BREAKDOWN
0-4s — Medium shot of three women standing by an open residential gate, laughing and reacting as a large lizard climbs the metal bars. One woman records the animal on a smartphone while a motorcycle handlebar and rearview mirror frame the foreground.
4-8s — Wide shot of a sunny suburban street as a delivery rider wearing a turquoise helmet drives a scooter toward the camera, carrying a cardboard parcel and a square delivery box.
8-12s — Medium side-profile shot of the three women watching the lizard on the gate. The woman in the green shirt holds her smartphone close to film the reptile as it clings to the vertical bars.
12-15s — Low-angle shot looking down at the women's bare legs and feet wearing sandals and sneakers on the bright concrete driveway near the black metal gate.
CAMERA
Handheld digital camera with natural depth of field. Cuts between eye-level medium framing, a wide street view, and a downward low-angle perspective.
LIGHTING & PALETTE
Bright midday outdoor sunlight casting crisp shadows on concrete. Naturalistic colour palette featuring foliage greens, neutral greys, white, and matte black metal.
AUDIO
Ambient outdoor street atmosphere, faint scooter engine hum, and casual background laughter from the women.
AVOID
Unrealistic CGI effects, studio lighting, cinematic color grading, distorted anatomy, camera shake, on-screen text overlays.
/gen prompt: Cinematic wildlife documentary, vertical framing, subject centered, National Geographic award-winning cinematography, anamorphic lens, rich natural color, natural sunlight, natural motion blur. States: the scream never stops, the camera always rises, every touched object reacts. Characters: a blue-and-gold macaw, cobalt wings, golden chest, green crown, white face patch, black beak; a young man, short dark curly hair, olive t-shirt. Israeli white stone apartment building, living room. 0-2s macro: silence, the macaw inhales, chest swelling, throat feathers rising, the man mid-sip. 2-5s the beak opens, the world slams into extreme slow motion: a ripple of distorted air expands from the beak, rings race across his coffee, the mug shattering into countable shards, coffee hanging in ropes, his cheeks rippling back. 5-9s time snaps back; the wave blows the shutters open, the camera rides it out, straight up the facade. 9-14s rising floor by floor: laundry lines whipping, a dog howling in one window; crawl on pigeons detonating off a ledge, feathers suspended, the ripple passing them; snap back. 14-17s the roof: solar heaters trembling, tank water rippling, car alarms flashing far below; bold 3D text "105 DB" slams centered mid-frame. 17-20s hard cut to the room: the macaw fluffs, tilts its head, one tiny chirp; the man frozen with the mug handle. Audio: silence, a heartbeat on the inhale; a sub-bass shockwave, one raw macaw screech Doppler shifting as the camera climbs, glass shatter, dogs and alarms join, biggest boom on the text, ringing silence, a tiny chirp. Photorealistic, no deformation, every feather barb visible, crisp letter edges, smooth fluid motion, 8k, extreme details. , resolution:720p, duration:20s, aspect_ratio:9:16
15-second, 16:9 vertical, continuous single-take video that looks like authentic smartphone footage accidentally captured by a passerby in a city park. Overcast natural daylight, subtle handheld shake, limited phone stabilization, occasional autofocus adjustment, and realistic smartphone compression. The absurd event is filmed with a completely serious, unscripted documentary feeling. 0–3s: [Handheld medium shot] A middle-aged man wearing a dark business suit and tie crouches beside the stone edge of a pond. With a completely serious expression, he slowly scatters pieces of bread from a paper bag to several ordinary koi. Small ripples spread across the water as the fish gather in front of him. 3–7s: [Camera instinctively moves closer] An abnormally huge orange-and-white koi suddenly surges out of the murky water, briefly lifting its upper body above the surface and biting down on the entire bread bag in the man’s left hand. He freezes for half a second, then grips the bag with both hands and leans backward. Startled, the person filming steps back. The image briefly loses focus before locking onto the man and the giant fish again. 7–11s: [Close handheld action shot] The giant koi pulls violently toward the deeper part of the pond. The wet paper bag stretches, the man’s arms tense, and his leather shoes slide repeatedly across the wet stone. His knee strikes the edge of the pond. He tries to brace himself with his right foot, but the sole loses traction and his center of gravity moves past the edge. Water, pieces of bread, and fallen leaves scatter from the force as the camera operator hurriedly moves sideways. 11–15s: [Impact and final hold] The paper bag suddenly tears. The man loses all support and pitches forward into the pond, creating one heavy, realistic splash. The camera quickly tilts downward while keeping the center of the pond visible. The man resurfaces with duckweed covering his head and his wet tie stuck across his face. The giant koi calmly swims past him with the remains of the bread bag still in its mouth. The camera holds on the man’s stunned expression while the koi casually swims away beside him. Keep the man’s face, dark suit, tie, and paper bag visually consistent throughout. The koi must retain the same orange-and-white markings and enormous size. The pulling, sliding, loss of balance, and fall must show believable weight, inertia, traction, and water displacement. Natural park ambience and a realistic splash only. No dialogue, no subtitles, no music. Avoid cuts, character teleportation, changes in the fish’s size, extra limbs, and cartoonish acting.
Create a 10-second horizontal 16:9 cinematic video using the provided macOS desktop screenshot as the EXACT first frame and visual reference.
IMPORTANT:
Preserve the reference image exactly as the starting frame. Do not redesign, replace, or regenerate the desktop environment. Maintain the same mountain lake background, warm sunset lighting, wooden desk, fluffy brown-and-white cat wearing large silver headphones, laptop, plant, books, coffee mug, macOS menu bar, 18 desktop application icons, and bottom Dock.
CHARACTER:
Keep the exact cat appearance, fur pattern, face, eyes, ears, headphones, body proportions, lighting, and position from the reference. The cat is sitting on the FAR RIGHT side of the desktop beside the laptop.
CAMERA:
Static front-facing camera.
No camera movement.
No zoom.
No pan.
No cuts.
One continuous shot.
Maintain exact 16:9 composition.
TIMELINE:
0–1.5s:
The cat remains completely calm in its original pose.
It sits beside the laptop with the headphones around its ears.
Its eyes slowly blink.
Its nose twitches slightly.
The ears make a tiny natural movement.
The desktop wallpaper, menu bar, all icons, Dock, laptop, books, mug and background remain completely stationary.
1.5–2.5s:
The cat suddenly sneezes.
Its head quickly moves forward and slightly toward the LEFT.
Its ears twitch and its headphones bounce naturally.
Its fur and whiskers react to the sneeze.
A small visible soft air puff travels from the cat toward the desktop icons.
The air puff accidentally knocks ONLY THREE desktop icons loose:
Gmail
Discord
Microsoft Teams
These three icons leave their original positions in the RIGHTMOST desktop-icon column.
They physically rotate and fall downward into the open desktop area above the Dock near the center-left.
Each icon moves separately.
Each icon lands with a small realistic bounce.
Their original positions become visibly empty.
ALL OTHER ICONS MUST REMAIN PERFECTLY STATIONARY.
2.5–3.3s:
The cat immediately freezes after sneezing.
Its eyes become slightly wider.
Its ears tilt backward.
It looks toward the fallen icons with a surprised and embarrassed expression.
The cat briefly looks toward the viewer as if pretending nothing happened.
Then it looks back at the fallen icons.
3.3–7.8s:
The cat hurriedly fixes the three fallen icons ONE AT A TIME.
FIRST — Gmail:
The cat reaches toward the fallen Gmail icon.
Its paw carefully touches and grips the icon.
It lifts Gmail from the desktop.
The cat carries Gmail toward its original empty position.
It places Gmail precisely back into its original location.
The Gmail logo and label remain unchanged.
A small gentle click is heard.
SECOND — Discord:
Only after Gmail has been restored, the cat reaches down toward the fallen Discord icon.
It picks Discord up individually.
It carries Discord back to its original empty position.
It releases Discord precisely into place.
A second gentle click is heard.
THIRD — Microsoft Teams:
Only after Discord has been restored, the cat reaches for Microsoft Teams.
It picks the Teams icon up individually.
It carries it back to its original position.
It carefully releases it into the empty grid position.
A third gentle click is heard.
IMPORTANT PHYSICAL ACTION RULES:
Every icon must visibly leave its original position, fall, land, be physically picked up, carried, and placed back.
Do NOT:
- restore icons automatically
- teleport icons
- make icons snap back from a distance
- move multiple icons simultaneously
- scoop multiple icons together
- stack icons
- duplicate icons
- morph logos
- change icon labels
The cat must interact with each icon separately.
The cat's paws must remain anatomically natural.
No extra paws.
No stretched limbs.
No distorted body.
No impossible reach.
7.8–10s:
After restoring Microsoft Teams, the cat quickly returns to its original position beside the laptop.
It sits upright again with the headphones correctly positioned.
The cat tries to look completely innocent.
It gently blinks.
Its ears settle.
Its whiskers and fur stop moving.
The cat briefly glances toward the restored icons, then looks forward again.
End with the cat sitting calmly in almost exactly the same pose as the first frame.
The final desktop must match the original reference composition.
VISUAL STYLE:
Photorealistic cinematic desktop environment.
Natural animal movement.
Realistic fur physics.
Subtle headphone movement.
Natural paw interaction.
Soft warm sunset lighting.
Realistic shadows.
Realistic depth of field.
Premium Apple-style desktop presentation.
PRESERVE:
- exact macOS menu bar
- exact desktop wallpaper
- exact 18 application icons
- exact icon positions
- exact labels
- exact Dock
- laptop
- books
- mug
- plant
- cat
- headphones
- lighting
- colors
- composition
ONLY Gmail, Discord and Microsoft Teams are allowed to move.
AUDIO:
Light playful piano and subtle pizzicato music.
One cute realistic cat sneeze.
Short airy whoosh during the sneeze.
Three soft icon landing sounds.
Three distinct gentle clicks when Gmail, Discord and Microsoft Teams are restored.
Brief music pause during the cat's shocked reaction.
No dialogue.
No subtitles.
No text overlays.
FINAL FRAME:
All three icons must be restored to their exact original positions.
No missing icons.
No duplicated icons.
No changed logos.
No extra objects.
The cat returns to its original pose and looks innocent.
The final frame should closely match the first frame.
A Gentle Soul in the Park — Meeting a Majestic White Lion at Dusk (T2V)
15s9:16
She found a gentle soul in the heart of the park A magical moment shared with a majestic white lion.
Made With MiniMax H3
Prompt:
A Cinematic video of a young woman wearing a brown jacket walking in a peaceful park during dusk She walks along a path lined with glowing warm streetlamps On a wooden park bench, a giant, majestic white lion with glowing fur is calmly sitting The woman approaches the white lion and gently pets its mane and face. Close-up shot showing a warm connection between her and the gentle white lion with the lion nuzzling against her cheek lovingly Finally they are sitting together peacefully on the grass under a warm streetlamp at night Cinematic lighting, realistic, soft shadows 4k resolution, emotional and magical vibe.
15 seconds, 16:9 dark-pop music video performance. Use @Image 1 as the strict identity reference for the three women — faces, hair and wardrobe unchanged in every shot. Use @Image 2 as the reference for the two titles only: ultra-condensed heavy caps, bone white, photocopied print surface. The three women perform and sing to camera throughout. Follow the beats below shot by shot with continuous natural camera movement and real physical motion inside every frame — this is live performance footage, never a slideshow, never a sequence of held poses. VOCAL: a single female lead voice, gritty and low, close-mic'd with tape saturation. The lyric lines are: "Dead air on the line" — sung at 2.7 seconds "Run it till it burns" — sung at 6.0 seconds "I don't slow down" — sung at 10.0 seconds Lip-sync locks precisely to these lines on whichever woman is singing. Between the lines all three mouth along, breathe hard and move. [0.0–2.7s] The three stand in near-blackness, sand-beige studio crushed dark. Handheld camera drifting slowly forward, breathing. The platinum-crop woman rolls her shoulders and steps toward lens. Her hair lifts. The auburn woman in mirrored shades tilts her head up. Real movement, low energy, building. Title over the darkness: "DEAD AIR". [2.7–6.0s] The auburn woman in the mirrored shades sings the first line straight into the lens, medium-close, mouth clearly forming the words. Camera whip-pans off her to the platinum-crop woman mid-stride, then crash-zooms back. Hard cuts every 0.3 seconds. Bodies in constant motion — hair whipping, chains swinging, hips driving, hands reaching for camera. Single-frame white flashes between cuts. [6.0–10.0s] All three together, performing hard. The chestnut-haired woman takes the second line, singing directly to lens while the other two move behind her, bodies loose and driving. Camera orbits the trio fast, then whip-pans, then handheld snap-zooms. Cuts every 0.2 seconds. Hair, fur and fishnet all moving. Faces alive, mouths working, sweat catching the light. [10.0–12.7s] Slow down hard, two long shots. The chestnut-haired woman alone, medium-close, singing the third line slowly and holding eye contact with the lens all the way through. Camera almost still, only breathing. Her wet hair moves across her face. She finishes the line and her mouth stays slightly open. [12.7–15.0s] Everything detonates. Flash cutting, single-frame plates, all three thrashing and singing at once, faces close to lens, black frames and inverted negatives between cuts. Camera whipping violently. Final title hammers in: "AFTERBURN". Cut hard to black with the music. MUSIC: driving industrial dark-pop, distorted 808 kick landing at 2.7 seconds, full arrangement through 6.0 to 10.0 seconds with clipped brass stabs and heavy tape saturation, dropping to near silence and one breath at 12.0 seconds for a full second, then the final two seconds at full weight with one metallic crash on "AFTERBURN". The lead vocal sits forward in the mix. Do not imitate an existing melody. Warm sand-beige studio sweep, hard raking light from camera-left, Kodak Portra 400 grain, tape dropout, scanline tear, chromatic fringing, light leaks. Hard cuts only, full speed throughout, every shot carrying real motion. Titles spelled exactly as written, English only.
Use [Ref_Image1] as the strict character identity, design, wardrobe, color and multi-angle reference. Its six views depict the same traveler. Reconstruct one coherent 3D character without averaging or redesigning his face. Preserve exactly the crescent-shaped face, amber eyes, midnight-blue hair, proportions, mustard-yellow suit, ivory shirt, teal scarf, burgundy shoes and floating black bowler hat shown in [Ref_Image1] throughout the video.
👤 CHARACTER
The original stylized cartoon traveler from [Ref_Image1] has a tall slender silhouette, expressive crescent-shaped face and large curious amber eyes. Keep his identity, proportions, colors and clothing perfectly consistent.
🌌 WORLD
A whimsical Dalí-inspired surreal desert at golden hour, rendered as a premium 3D cartoon. Vast peach-colored sand, an impossibly curved turquoise horizon, long-legged houses walking slowly in the distance, floating doorframes, liquid staircases, stretched shadows, cloud-shaped fish and soft clock-like flowers bending in the breeze. Original imagery, not a recreation of any existing artwork.
🎬 15-SECOND ACTION
0–2s: A shadow peels itself away from the traveler’s feet, bows to him and becomes a moving staircase. He reacts with delighted surprise.
2–5s: The traveler steps onto the staircase as it glides across the desert; floating doors open onto tiny upside-down oceans.
5–9s: He returns to the sand and walks beneath extremely tall houses whose windows blink like sleepy eyes. His floating hat circles his head once.
9–12s: Gravity tilts; the horizon curves upward and he walks sideways while cloud-fish swim overhead.
12–15s: He opens a freestanding door and discovers the opening shot inside. He steps through as it closes, creating a seamless loop.
📷 CAMERA
Smooth side-tracking camera with subtle dolly movement, one continuous shot, no hard cuts, strong layered parallax, 35mm cinematic perspective and stable character scale.
✨ STYLE
Elegant surrealist cartoon, rounded expressive shapes, hand-painted textures, premium stylized 3D animation, playful impossible physics, warm peach, mustard, teal and burgundy palette, cinematic golden light, gentle film grain, 24fps.
🎵 MUSIC AND SOUND
Original instrumental LoFi: mellow vinyl crackle, dusty boom-bap drums, warm Rhodes chords, soft upright bass and dreamy reversed guitar at 78 BPM. Synchronize the shadow, doors, orbiting hat and final closure to the beat. No vocals or recognizable melody.
🔒 CONSISTENCY
Exactly one traveler. No identity or wardrobe changes, extra limbs, malformed hands, duplicate character, text, logos, watermark, flicker, abrupt cuts or photorealistic elements.
🖼️ OMNI REFERENCE — [Ref_Image1]
Use [Ref_Image1] as the strict character identity, wardrobe and multi-angle reference. Preserve Freya’s exact face, blue eyes, long platinum-blonde hair with darker roots, skin tone, age and body proportions from [Ref_Image1]. Keep the same buttoned white linen shirt, cream linen shorts, bare feet and gold bracelet shown in [Ref_Image1]. Its six views represent one person from different angles; reconstruct one coherent 3D character without averaging or redesigning her face.
🏝️ SCENE
Freya stands near the waterline on a quiet Caribbean beach in warm late-afternoon sunlight: pale sand, transparent turquoise sea, distant palms and blue sky. A gentle breeze moves her hair and linen shirt while small waves reach the shore.
🎥 15-SECOND 360° ORBIT
One uninterrupted shot with no cuts. A stabilized camera moves clockwise around stationary Freya in one complete, physically correct 360° orbit.
0–2s: Start medium-wide in a frontal three-quarter view; she makes eye contact, smiles and breathes naturally as the orbit begins immediately.
2–5s: Pass her left profile with strong shoreline parallax; she begins speaking: “If paradise had a heartbeat…”
5–8s: Reach the full back view; she turns only her head slightly toward the moving camera and continues: “…I think it would sound…”
8–12s: Pass her right profile; she looks briefly at the horizon, returns her gaze to the lens and finishes: “…exactly like this.” She smiles naturally.
12–15s: Complete the orbit and return precisely to the opening frontal composition for a seamless loop.
📷 CAMERA
Constant clockwise direction, orbital radius, horizon and subject scale. Smooth gimbal motion, 35mm cinematic lens, full-body framing from head to bare feet, realistic foreground/background parallax. The camera travels around Freya; she does not spin and the background does not rotate artificially.
✨ LOOK
Premium photorealistic travel-fashion film, natural skin and linen texture, warm sunlight, soft shadows.
Use @Image1 as the cloaked avenger identity lock and wardrobe reference. Use @Image2 as the environment, lighting, and street layout reference. Use @Image3 as the cyborg executioner identity lock, armor design, and weapon reference.
Create a 15-second ultra-cinematic confrontation in the ruined streets of Sector 7 at night. Heavy ashfall, wet pavement, orange emergency lights, smoke columns, and reflective industrial architecture strictly follow @Image2. The cloaked avenger from @Image1 faces the red cyborg executioner from @Image3 in the center of the empty street. Maintain facial features, wardrobe, armor geometry, and environment consistency across all shots. No onscreen text, no floating letters, clean visuals.
0–4s: Wide establishing shot. The cloaked avenger from @Image1 walks slowly through the rain-dark street toward the cyborg from @Image3. Camera performs a slow push-in. Coat edges move in the wind, boots splash through shallow water, ash drifts through orange backlight.
4–8s: Medium close-up on @Image1. He stops, lifts his chin slightly, and says clearly in English: “Long time I was looking for you.” Deliver slowly, low, and intense, with precise lip-sync. Camera holds a subtle handheld drift. Wet hood, tired eyes, and grim determination remain consistent with @Image1.
8–11s: Medium close-up on @Image3. The cyborg tilts its head, red visor brightening, and replies in a cold metallic voice: “finally”. Deliver with a short pause before the word and precise mouth-panel synchronization. Servo motion, red eye glow, and armored posture strictly follow @Image3.
11–15s: Sudden action payoff. Whip pan into a dynamic wide shot as @Image3 ignites the red energy blade and lunges forward. @Image1 instantly draws his blade and rushes to meet the attack. They collide at center frame in a shower of sparks, rain spray, and reflected orange-red light. End on a dramatic frozen impact moment with crossed blades, smoke and ash swirling around them, camera orbiting slightly into a powerful hero frame. Gritty cinematic realism, strong contrast, volumetric haze, realistic body momentum, normal proportions without stretch.
[FORMAT] Exactly 15 seconds, horizontal 16:9, photorealistic AAA fantasy MMORPG gameplay reveal with native synchronized game audio and music.
[OMNI REFERENCES]
[Image1] = Kael Ardyn, the exact playable arcane spellblade. Preserve his face, silver-black tied hair, pointed ears, cyan eyes, athletic proportions, navy-and-silver armor, gold filigree, teal cloth, chest focus and curved spellblade.
[Image2] = The exact Obsidian Tempest Dragon. Preserve its enormous four-legged anatomy, black volcanic-glass scales, crown horns, torn wings, cyan electrical fissures, storm-blue eyes and long spiked tail.
[Image3] = The strict Skybreak Citadel arena and spatial reference: circular black-stone platform, gold-and-cyan inlays, ruined towers, floating architecture, storm abyss and blue-hour lighting.
[Image4] = The strict visual reference for the 2026 gameplay interface: refined gold-and-cyan frames, boss bar, circular minimap, quest tracker, party frames, player status arcs, action bar, cooldown numbers and restrained typography.
Reconstruct each multi-view subject as one coherent 3D asset without averaging or redesigning it.
[DESIGN GOAL] Original next-generation fantasy MMORPG with cinematic AAA presentation and genuinely playable movement. The 2026 HUD uses elegant smoked glass, contextual information, subtle transitions, responsive cooldowns and excellent readability. It remains locked to the screen, never floating inside the world.
[15-SECOND SEQUENCE] 0–2s: Immediate hook with no HUD. Low camera behind Kael. The Obsidian Tempest Dragon crashes onto the platform ahead, wings filling frame, lightning splitting the sky and stone fragments rising from impact. Kael draws his spellblade as it roars. 2–4s: Camera settles into polished third-person gameplay. The interface assembles around the edges: top boss bar reading “OBSIDIAN TEMPEST,” player health, mana and stamina below, action bar, party frames left, minimap upper right and quest tracker reading “THE SKYBREAK SIEGE.” HUD stays sharp and screen-locked. 4–8s: Kael sprints forward and chains three abilities: cyan blade dash, circular gold runic shield and vertical storm strike into the dragon’s chest. Matching action icons illuminate once and begin radial cooldowns with changing numbers. Boss health falls from 100% to 78%. Accurate footwork, weapon contact and restrained camera shake. 8–11s: The dragon releases a ground-level electrical shockwave. A red telegraph ring appears on the arena. Kael performs a perfectly timed sideways dodge; a small centered “PERFECT EVADE” notification appears briefly and fades. Health stays stable while stamina dips and recovers. 11–13s: Kael targets the glowing chest fissure and unleashes a cyan-gold arcane slash. Brief hit-stop, one damage number, boss bar falls to 12%, then sparks and debris resume. 13–15s: Kael lands in a hero stance as the dragon recoils. HUD minimizes toward the edges. Centered title: “AETHERFALL ONLINE,” then “THE RAID BEGINS.” End on thunder and musical impact.
[CAMERA + VISUAL QUALITY] Seamless cinematic-to-gameplay transition, realistic third-person controls, premium real-time rendering, ray-traced reflections, volumetric storm light, grounded combat, coherent scale, controlled motion blur and cyan-gold contrast. Preserve the arena layout; avoid arbitrary cuts.
[UI BEHAVIOR] Anchor all UI to exact screen coordinates with consistent scale and typography. No flicker, duplication or drifting. Values change only in response to described actions. Never cover Kael or the dragon.
[AUDIO] Original hybrid fantasy score: war drums, low strings, metallic pulses and restrained electronic rhythm. Add dragon impact and roar, thunder, debris, footsteps, sword draw, arcane abilities, shield resonance, shockwave, dodge and final hit. Keep effects clear. No narrator, dialogue, vocals or recognizable melody.
[PRESERVE] Stable Kael and dragon identities, exact armor and creature design, one hero, one dragon, Skybreak Citadel geography, responsive 2026 HUD, readable specified labels and coherent combat causality.
[AVOID] Existing game logos or recognizable franchise symbols, copied interface layouts, extra heroes or dragons, turn-based combat, cinematic black bars, first-person view, random UI changes, unreadable text, floating HUD panels inside the world, excessive particles, cartoon rendering, anatomy drift, weapon changes, clipping, subtitles, additional text or watermark.
Super casual real smartphone home video footage, cozy winter cabin gathering with snow visible outside, natural mobile phone camera with slight authentic handheld shake, normal frame rate with smooth natural motion, rapidfire montage with quick jump cuts every 1-2 seconds like scrolling through phone memories, unpolished authentic phone recording of mixed ages sipping hot cocoa, chatting by the fireplace, pure raw home video feel, no cinematic polish.
Use the provided reference photo as the strict ONLY visual reference for the main woman. Maintain her exact appearance with zero deviation. Generate a mixed group of family and friends around her inside the cabin, fireplace and snow visible through the window.
0-2.5s: Shaky rapid cuts — main woman laughing near the fireplace, warm cocoa mug in hand, quick flashes of snow falling outside.
2.5-5s: Abrupt jump cuts — close-up of her smiling while sipping cocoa, then friends passing blankets and snacks around.
5-7.5s: Fast shaky — she chats animatedly by the fire, friends and family cozy on the couch nearby.
7.5-10s: Quick cut close-up — warm smile toward camera, then jump to her laughing with a grandparent by the fireplace.
10-12.5s: Abrupt edit — group gathered close, sharing snacks and stories, casual toast with mugs.
12.5-15s: Final rapid transition — main woman relaxed by the fire with family, soft smile, calm winter memory ending with gentle phone sway.
Natural smartphone video quality, slight real handheld shake, smooth normal frame rate motion, authentic casual physics, stable main character consistency, no pro stabilization or effects.
Use @[character reference] for the character's identity, anatomy, costume, colors, materials and visual style. Adapt body-region cues to its actual anatomy, replacing absent features with existing equivalents. Invent no anatomy or accessories. Select signature inserts from its most recognizable details. Rigid parts rotate; flexible materials bend or stretch.
A 15-second character-detail montage: exactly 20 shots joined by hard cuts. An empty, seamless warm-white studio background; soft directional light reveals the surfaces. Shots 1-19 are tightly cropped body details and rear angles: keep the face, eyes and facial profile entirely outside the frame, including reflections. Shot 20 is the first and only face reveal. No full-body view.
Three connected bursts: a sharp head turn with the body bracing; a coiled arm opening into a strong sweep and torso twist; one short step into a planted pivot, finishing with a sudden look into camera. Carry body state across cuts without resetting to neutral. Existing hair, clothing and attachments react naturally. Keep the character active, with clear articulation and weight shifts.
Jump between distant body regions. Mix brief visual punches with longer moving-detail reads. Use one abrupt camera move per shot except locked-camera inserts 4 and 11, where the character supplies the speed. Vary height, angle and direction. Brake moves briefly for legibility while the subject keeps moving. Local whips stay tightly cropped; changes of body region use hard cuts. Connect selected cuts through similar shapes or motion vectors, without morphing. Real-time action, no slow motion or freeze frames.
0-3s, shots 1-5. A concealed head turn triggers the first burst:
1. Extreme upper-back detail: a crash push catches its surface shifting as a sharp head turn begins entirely above the crop.
2. Fingers: a short downward snap catches them curling into a fist as the body braces.
3. Rear three-quarter shoulder detail: a tight camera arc catches the shoulder drawing back behind the turning head.
4. Locked floor-level foot detail: the grounded support foot braces, its raised heel pressing down firmly without taking a step.
5. Rear neck detail: a short upward tilt catches the nape stretching with the turn; stop below the back of the head, keeping the jaw and face excluded.
3-9s, shots 6-13. The coiled arm opens into a forceful sweep:
6. A signature upper-body detail: a fast diagonal slide catches an existing seam, joint or distinctive contour responding as the arm draws inward.
7. Elbow: a sharp lateral track catches the folding joint tightening the arm's coil.
8. Supporting knee: hard match cut from the bent elbow to the knee's similar angle; a short camera drop catches the leg compressing under the same preparation.
9. Wrist: a quick shallow orbit catches it turning outward to initiate the release.
10. Upper chest: a short punch-in catches the chest opening as the arm drives outward beyond the crop. Let this moving surface read slightly longer.
11. Locked hand detail: fingers spring open and the hand sweeps rapidly across the fixed frame. Catch one crisp, readable phase of the spread fingers before they leave the crop.
12. Upper back: a sharp sideways slide continues that screen direction as the shoulder rolls through the sweep and the torso twists.
13. A distinctive torso or waist detail: a close diagonal move catches its physical response to the twist, such as an existing fold pulling taut or an attached piece swinging. Give the material response a clear moving read.
9-13s, shots 14-19. One short step and a pivot build toward the reveal:
14. Thigh of the other leg: an abrupt low tracking move catches it driving the single short step out of the twist.
15. Advancing foot: a brief downward whip catches it landing; show clear floor contact.
16. Ankle and lower-leg detail: a fast side slide catches the landed leg accepting weight as the ankle flexes.
17. Waist: a tight orbit catches the torso rotating above the planted-foot pivot. The foot supports the turn rather than sliding across the floor.
18. Back-of-head contour: a short lateral whip catches the start of the return turn from behind. Keep only the rear contour in frame, never the facial profile.
19. A signature shoulder detail: a sharp diagonal slide catches its follow-through beneath the turning head, which stays completely above the crop. Cut at the peak of this movement.
13-15s, shot 20. First face reveal:
20. Hard cut to a frontal face close-up as the character sharply completes the turn toward the lens. An explosive short push reveals the entire face clearly for the first time and stops tightening before cropping out its features. Direct eye contact lands while hair, clothing or natural body follow-through remains alive. Keep the whole face readable through the end; finish on living motion, without a held pose or another cut.
No added props, scenery, text, graphic overlays or split screens.
A young East Asian woman, held constant every frame as the only sharp subject. She has freckles across her nose bridge and cheeks, deep brown eyes, fluffy airy bangs, a messy low bun, pearl stud earrings, natural bare makeup, and a calm, faintly composed, unbothered expression. She wears a charcoal grey double-breasted belted long wool coat over a black turtleneck, black trousers, and black block-heel ankle boots. Her posture is upright and composed. Realistic skin — visible pores, subsurface scattering, freckles and real skin texture kept, no beauty-filter plastic smoothing, no over-smoothing.
The scene is bound from the arrivals-hall reference: a bright modern airport arrivals hall by day, floor-to-ceiling glass curtain walls, a high-reflection mirror floor, cool blue-white daylight, yellow overhead signage, an open airy space. Both her identity and the hall setting stay constant every frame and are not tied to any single timestamp. Keep the design DNA, not the composition — do not copy the reference's full-frame long-exposure motion blur or extreme ground-level camera (she must stay sharp and crisp the whole way), and do not copy any triptych, split-screen, grey studio backdrop, or static front portrait pose. Airport signage stays as an environment graphic element only, kept non-legible.
Timeline
Shot 1 — 0.0s: Realistic cinematic, handheld backward tracking long take, one continuous shot. Centered in frame, Riria strides along the central axis toward the lens, calm and composed, unbothered. Dark-suited bodyguards escort her on both sides, one slightly ahead reaching out to part the crowd and open the lane. Behind the barriers on both sides an excited mixed crowd of fans and paparazzi surges — fans cheering, phones held high and waving, leaning to look; paparazzi firing cameras in bursts, flashes constantly popping — all staying behind the barriers, never entering the central lane or trailing her, just passed and left at her sides and behind. The background is the bright modern arrivals hall: glass curtain walls, cool blue-white daylight, a high-reflection mirror floor throwing everyone's reflections, yellow overhead signage. Inside the central lane there is only her, the bodyguards, and the professional operator in front. The operator holds steady, always directly in front of her, retreating at a normal real walking pace at roughly constant distance, with slight handheld breathing sway, around chest to eye height and slightly low to catch the floor reflections, no zoom.
Shot 1 continues — 2.5s: The flashes on both sides turn dense and rapid-fire and the fans grow louder. Her stride rhythm never changes, her coat swings naturally with each step, her bangs sway lightly with the pace, her calm expression never shifts. In the instant of each flash pop her face and coat are briefly blown out to bright highlight, then drop back into cool daylight.
Shot 1 continues — end: She is still stepping forward and the camera is still retreating. Constant subtle life throughout — reflections on the mirror floor rippling with the crowd, cool light shifting faintly on the glass, the bodyguards' dark suits rising and falling with movement, fans behind the barriers waving and leaning continuously, flashes flickering bright and dark, the handheld frame breathing lightly. The image hard-cuts to end while she is still mid-step and the camera is still moving back.
Sound Design
Location sound only, no dialogue. The wide airport hall's cavernous reverb and low hum, dense and real camera shutter clacks and flash charge whines overlapping in waves, fans' cheers, screams and shouts overlapping, her heeled boots and the bodyguards' dress shoes crossing on the smooth floor, the rustle of her long coat's fabric, and a distant indistinct airport PA voice. At the hard cut the image and sound both cut off naturally at once. For music, a low synth bass bed with a steady modern electronic beat and light percussive pulse, mid-tempo, steady groove, restrained, never covering the ambient sound.
Prohibited
No subtitles, text, watermark, logo, or legible readable text; the overhead airport signage may exist as an environment graphic but stays blurred and non-legible, never rendered into recognizable or garbled text. No slow motion. No speed ramps or speed gradients. No floating, frozen, or weightless movement. No rail-straight gliding gait. No shrinking her to a far dot or drowning her in the crowd. No triptych, split-screen, or multiple copies of her. No grey studio backdrop. No static front portrait pose. No frozen or still frame. No face drift from the reference (losing freckles, bangs, bun, or features). No coat color change. No rendering the bodyguards or crowd as sharp as her. No paparazzi or fans crossing the barrier into the central lane. No paparazzi or fans following behind her or trailing her. No crowd moving toward the lens with her. No front operator turning into a paparazzo or shooting her with a camera. No paparazzi running in front of her. No stiff, warped, floating, or unnaturally placed extras. No misfacing extras not looking at her. No uniform or identical fan and paparazzi clothing. No crowd of only paparazzi with no fans. No fully static camera with no handheld life, and no over-distorted shake. No global amber warm tint. No beauty-filter plastic skin.
Dance Video Character Swap — Character Sheet + Reference Dance Clip
10s16:9
【minimaxh3】
subject_definitions: <Picture 1> is the character sheet of one original woman: front, side, and back. Shoulder-length dark brown hair, cream cropped knit cardigan, light-blue wide-leg jeans, white sneakers. <Video 1> is a 10-second vertical dance clip. It supplies the dance timing, body rhythm, camera angle, and framing only. <Subject 1> is the woman whose face, hair, and outfit come from <Picture 1>, and whose dance motion comes from <Video 1>.
summary: Replace the dancer in <Video 1> with <Subject 1>. Keep the dance. Change the person and the room.
retention_analysis: <Video 1> motion, rhythm, camera angle, framing, and timing are fully preserved from 0.00 to 10.00 seconds. <Picture 1> face, hairstyle, cream cardigan, light-blue wide jeans, and white sneakers are fully preserved on <Subject 1> from start to end. The original dancer’s face, clothes, and room are not kept. The background is a bright minimal apartment with sheer curtains and afternoon sun.
detailed_description: [Shot 1] 0.00–10.00 seconds. Full-body vertical frame, one person only. <Subject 1> stands in a bright minimal apartment, large window, sheer beige curtains, afternoon sunlight on a pale wood floor. She performs the exact dance of <Video 1>: hands rise beside the head, hands move behind the head, one knee lifts, arms open to the sides, then she returns to a standing pause. Camera stays fixed at eye level, same framing as <Video 1>. Face, hair, and outfit stay matched to <Picture 1> through every turn. No text, no logos.
overall_soundscape: Soft room tone, sneaker scuffs on the wood floor, fabric movement from the cardigan and jeans.
non_diegetic_music: Upbeat light pop instrumental, no vocals.
Duration: 15 seconds | Aspect ratio: 16:9 | Style: High-fashion editorial lookbook with bold kinetic typography
SCENE
Female model with sleek hair wearing avant-garde structural fashion, including oversized blazers, metallic armor, and sharp-shouldered dresses. Backgrounds alternate between concrete brutalism, glowing metallic tunnels, and minimalist photo studios. Giant text overlays integrate with the environment.
SHOT BREAKDOWN
0-4s — Model in an oversized black suit poses against concrete pillars and a red industrial corridor. Framed center. Floating text reads: "DON'T BLINK" and "BREAK THE RULES".
4-8s — Model struts through a red metallic tunnel in a white and silver futuristic corset, then poses in a stark split-tone studio. Framed medium-wide. Text reads: "NO APOLOGIE" and "MAKE THEM".
8-12s — Model wears a reflective silver top against a dark glitch backdrop, then walks strictly in profile in a white and silver suit across a seamless white void. Text reads: "6411", "LOUDER LOUDER LOUDER", and a halftone "NO".
12-15s — Model poses in a sharp-shouldered emerald green outfit in front of a torn-poster wall, then stands motionless within a dismantled photo studio setup. Wide framing. Text reads: "WE DON'T MISS", "4:0:21.18.1 1:2:3:8", "OWN THE NIGHT", and "UNSTOPPABLE".
CAMERA
Locked-off center framing, strict linear tracking, rapid rhythmic smash cuts.
LIGHTING & PALETTE
High-contrast studio flash, harsh directional spotlights. Dominant palette: stark white, deep black, metallic silver, crimson red, emerald green.
AUDIO
Heavy electronic bass beat, rhythmic camera shutter clicks, sharp metallic swooshes.
AVOID
Soft focus, warm natural sunlight, organic environments, slow crossfades, shaky handheld camera.
Boundless Journey Across Surreal Worlds `reconstructed`
15s16:9
Duration: 15 seconds | Aspect ratio: 16:9 | Style: Cinematic surreal environment transition montage
SCENE
Young woman, dark wavy hair, white satin dress with a high slit, camel blazer draped over shoulders, emerald and diamond necklace. She travels seamlessly through rapidly changing fantastical environments.
SHOT BREAKDOWN
0-4s — Woman walks confidently through a rainy cyberpunk city with glowing neon billboards and flying vehicles, transitioning instantly to a traditional Japanese temple with falling pink cherry blossoms.
4-8s — The environment shifts to an underwater realm featuring large sharks, glowing jellyfish, and massive crystal formations. The scene cuts to a gray lunar base with astronauts; the woman turns away, facing a giant Earth in the sky.
8-12s — Seen from a profile angle, she stands in a foggy mystical forest surrounded by giant bioluminescent mushrooms. The backdrop abruptly changes to a dark volcanic landscape with actively erupting lava and smoke.
12-15s — She faces forward inside a modern minimalist penthouse with floor-to-ceiling windows overlooking a sea of clouds at sunset. The final cut places her in deep space against a brightly lit spiral galaxy and stars.
CAMERA
Locked-on tracking shot, maintaining medium-full framing. Rapid, seamless smash cuts between backgrounds while the subject's position remains relatively stationary.
LIGHTING & PALETTE
Highly dynamic and contrasting. Neon magentas and cyans, warm golden hour tones, deep aquatic blues, fiery orange lava, and vivid cosmic purples.
AUDIO
Driving electronic beat. Heavy swooshing transition sound effects synchronized with the rapid environmental cuts. No dialogue.
AVOID
Wardrobe changes, character morphing, camera shake, shallow depth of field obscuring backgrounds, muted colors.
Duration: 15 seconds | Aspect ratio: 9:16 | Style: High-energy, surreal sports montage
SCENE
Multiple athletes including a female soccer player in a green tracksuit, a male golfer in a red jacket, and a shirtless male basketball player in red shorts, situated in abstract, dark, and dramatically lit environments.
SHOT BREAKDOWN
0-4s — A woman with braids in a green and yellow jacket stares intensely, then walks forward in a dark stadium. A white soccer cleat kicks a yellow and red ball.
4-8s — A massive soccer ball dominates the foreground. Rapid cuts reveal a golfer mid-swing, extreme close-ups of a gloved hand gripping a club, and the textured dimples of a golf ball.
8-12s — A golfer wearing yellow sunglasses and a white cap reading "SUPER" swings, spraying debris. The golf ball flies into a pitch-black void.
12-15s — A shirtless basketball player raises a ball against a twilight sky, then leaps into the air with glowing red motion trails. The ball falls onto grass before the scene distorts into a melting, abstract red sphere.
CAMERA
Kinetic pacing with rapid cuts. Mix of extreme macro close-ups, low-angle hero shots, and dramatic slow-motion action freezes.
LIGHTING & PALETTE
High-contrast, directional lighting with intense crimson red gels and deep shadows. Primary palette features emerald green, vivid red, stark white, and deep teal.
AUDIO
Heavy synthetic bass, aggressive swooshes, sharp impact sounds of sporting equipment, and distorted low-frequency hums.
AVOID
Muted colors, flat lighting, continuous long takes, realistic physics, mundane settings.
Epic desert sci-fi, harsh golden-hour light, volumetric sand haze, anamorphic lens flares, subtle handheld drift, heavy atmospheric particles, 35mm film texture.
Use the provided 3x3 grid as the only visual reference. Lock the exact same woman (face, scars, green eyes, headscarf, desert armor, cape) and environments from every panel. Do not invent new outfits or faces.
[TIMELINE] 0-1.7s: [Wide establishing] Lone figure walking across endless dunes toward twin massive suns. Heat shimmer, long shadow stretching behind her.
1.7-3.4s: [Extreme close-up] Her scarred face fills the frame. Eyes locked on camera, wind tugging the dirty headscarf, grit on skin, unblinking intensity.
3.4-5.1s: [Tight detail insert] Gloved hand grips the rusted multi-tool weapon. Metal catches the orange light, cable dangling, fingers adjusting the grip with quiet precision.
5.1-6.8s: [Low wide silhouette] The towering industrial structure rises against the giant sun. Dust storms swirl at its base, scale feeling ancient and oppressive.
6.8-8.5s: [Medium tracking] She advances through thick sandstorm, lower face wrapped, cape and scarf whipping hard. Eyes visible above the cloth, determined stride.
8.5-10.2s: [Hero wide] She stands alone on the rocky outcrop, cape flowing, surveying the empty desert below. Wind howls, silhouette sharp against the hazy sky.
10.2-11.9s: [Dynamic tracking + low angle] She charges down the steep dune face, boots kicking up thick clouds of sand, body leaning forward with full momentum.
11.9-13.6s: [Macro atmospheric] Golden sand particles explode and float in extreme slow motion, backlit by the blazing sun, pure texture and light.
13.6-15s: [Intimate close-up] Inside the dark cave, shafts of light cut through. She sits against the rock, armor dusted, breathing controlled, eyes sharp and watching the entrance.
Photorealistic, ultra-detailed skin and fabric textures, perfect sand physics, coherent character identity across every cut, cinematic color grade, heavy film grain, no artifacts, movie-level continuity.
Use @Image 1 as the exact opening frame. It is a 3x3 contact sheet of nine separate portraits of the same female rapper, each in a different location. Treat every panel as its own live video cell with its own camera, lighting and performance. 12 seconds, 16:9. Keep the grid absolutely fixed for the entire shot: identical panel positions, identical panel sizes, identical white gutters, no zoom, no pan, no rotation, no drift of the grid itself. Only the content inside each panel may move. Preserve each panel's identity exactly: same face, same hair, same wardrobe, same jewellery, same background as in @Image 1. Panel 1 stage with mic, panel 2 graffiti alley, panel 3 studio console with bandana, panel 4 rooftop with pink car, panel 5 roller shutter with bucket hat and chains, panel 6 purple club, panel 7 sunset rooftop with braids, panel 8 neon alley, panel 9 black backdrop close-up. [0.0-1.2s] All nine panels sit almost still like breathing photographs, only micro-movement: hair drift, blinking, smoke, light flicker. A low sub-bass swell rises. [1.2-3.0s] The beat drops. Panel 1 raps to camera: "MiniMax." Panel 5 answers: "H3." The other seven nod on the beat. [3.0-5.0s] Panels 2, 3 and 7 trade the line one after another: "New drop." Each one takes the beat, the rest bounce in rhythm. [5.0-7.5s] Panels 4, 6, 8 and 9 answer: "Go and try it." Hands move, chains swing, ad-libs. [7.5-10.0s] All nine perform in unison, tightly lip-synced toH3, go and try it." [10.0-11.3s] The beat stops dead. In one synchronized move all nine raise a hand into a finger-gun aimed straight at the camera, chin down, hard contact. [11.3-12.0s] They fire the imaginary shot on a single low hit, a tiny recoil ripples through all nine panels at once, then freeze. Audio: one continuous hip-hop beat across all panels, roughly 92 BPM, deep 808 sub, crisp trap hats, sparse hand claps. Female voice, confident, slightly playful, not aggressive. Layer nine slightly detunedn section for a choir effect. End on one low hit plus a shorttail of room tone. Keep the lip-sync accurate to the words in every speaking panel. No subtitles, no on-screen text, no captions, no logos, no watermarks. No panel may drift, crossfade, resize or swap places. Do not add people. Dreen single shot at any point.
Overcast light, soft light, daytime, documentary photography style, mixed tones, wide-angle. This is documentary-style multi-camera coverage of a single, unchanging surreal moment: a giant octopus draped over a scaffolded Haussmannian building facade on a Paris street, its tentacles hanging down over the netting, pedestrians walking past below completely unfazed by it. @Video1 is the master reference for the octopus's exact design, color, texture, scale, and pose, the building's architecture and scaffolding, the pedestrians' presence and unbothered behavior, and the daytime overcast lighting. None of this changes across the sequence below, only the camera does — six rapid, distinct angles cover this same frozen moment in quick succession, as if six different camera crews were filming it at once. Shot 1 [0-2s] Aerial shot. A high aerial view looking down over the street, revealing the full scaffolded building facade with the octopus draped across it, tentacles hanging over several floors, pedestrians walking past below. Shot 2 [2-4s] Hard cut transition, medium shot from street level, matching Video 1's framing and distance: the building's stone facade wrapped in scaffolding, the octopus's tentacles draped down over several floors, pedestrians crossing in the foreground. Shot 3 [4-5.5s] Hard cut transition, close-up on the octopus's head and eye, its textured reddish-brown skin catching the daylight, one tentacle curling around a section of scaffolding pipe. Shot 4 [5.5-7s] Hard cut transition, low-angle shot, camera tilted sharply upward from street level, the octopus looming directly overhead against the cloudy sky. Shot 5 [7-8.5s] Hard cut transition, lateral tracking shot at eye level along the street, the building's facade and the octopus's tentacles draped along it in profile. Shot 6 [8.5-10s] Hard cut transition, over-the-shoulder shot from just behind a pedestrian walking on the sidewalk, their head tilted up toward the octopus as they pass beneath it, unhurried and unreactive. Sound: light outdoor street ambience throughout, distant traffic hum and soft wind, consistent across every rapid cut. No dialogue. No background music.
How to write, use, and pay for MiniMax H3 video prompts.
What is a good MiniMax H3 prompt?
Describe the subject, action, setting, camera movement, lighting, and sound in plain sentences. MiniMax H3 follows director-style language well, e.g. "slow dolly-in, golden-hour backlight, shallow depth of field".
How do I use a prompt from this library?
Click "Generate this" on any card. It opens the MiniMax H3 generator with the prompt, aspect ratio, and duration prefilled, so you can tweak it or generate right away.
How many credits does a MiniMax H3 video cost?
Video is billed per second: 7 credits per second at 768P and 12 credits per second at 2K, so a 4-second 768P clip costs 28 credits. Failed generations are refunded automatically.
Can I try it for free?
New accounts get free credits to try AI image generation. MiniMax H3 video needs a credit pack; the Trial Pack starts at $2.99 (¥19.9 with WeChat Pay or Alipay).
Who wrote these prompts?
The prompts are curated from the MiniMax H3 creator community. Each card credits its original author and links to the original post.
Do the prompts work for image-to-video?
Yes. Upload a reference image in the generator and keep the motion, camera, and sound parts of the prompt; MiniMax H3 will animate your image instead of creating a new scene.
