Create a premium 16:9 Argentina national team fashion poster, editorial sports campaign style, bold graphic design, clean and high-end composition. A full-body young adult woman stands on the right side, with very long platinum-blonde straight hair, a blue bow hair clip, fair skin, delicate East Asian facial features, calm confident expression. She wears a stylish Argentina-inspired fan outfit: light blue and white striped cropped jersey, white high-waisted mini skirt, a white sports jacket tied around the waist, white knee-high socks with light blue stripes, blue-and-white sneakers. One foot rests on an Argentina-themed football.
The left side contains strong poster typography: top small text “LA ALBICELESTE” with three gold stars, a large blue brush-script “VAMOS”, a huge distressed bold title “ARGENTINA”, a gold handwritten script “Vamos Argentina!”, large Chinese text “阿根廷”, smaller text “PASIÓN • ORGULLO • GLORIA”, “FROM BUENOS AIRES TO THE WORLD”, and “UNA NACIÓN, UN SUEÑO.” Place an AFA crest in the lower-left corner.
Background is a stylized Argentina national theme design, not realistic scenery: sky-blue and white brush strokes, paint textures, halftone dots, splatter textures, layered graphic design, with a subtle golden Sun of May emblem on the right. Overall look is a high-end World Cup national team poster, fashionable, energetic, graphic, clean, and visually striking.
low quality, blurry face, bad anatomy, extra fingers, deformed hands, messy text, wrong spelling, crowded layout, weak typography, unrealistic body proportions, overexposed, dull colors, random background objects, casual street photo, low-detail clothing, distorted football, duplicate limbs, cartoon style, childish style, messy poster composition
Use the provided goalkeeper storyboard as the direct visual reference for the entire 15-second cinematic animation.
Follow the exact pacing, emotional intensity, goalkeeper perspective, football action choreography, stadium atmosphere, and championship climax shown in the storyboard.
The entire short film should feel like a FIFA World Cup commercial focused on a goalkeeper's greatest night.
Maintain exact character consistency throughout all shots.
STYLE
Pixar-quality cinematic 3D animation, FIFA World Cup Final atmosphere, ultra-dynamic sports cinematography, dramatic stadium lighting, emotional sports storytelling, realistic football physics, intense crowd energy, fast-paced editing, cinematic depth of field, motion blur, volumetric lights, epic championship emotion.
FOCUS
pressure, responsibility, courage, resilience, split-second decisions, heroic goalkeeping, belief, impossible save, world champion.
MAIN CHARACTER
Martin — young elite goalkeeper, messy dark brown hair, expressive eyes, green goalkeeper kit number 1, gloves, athletic build, determined personality, fearless competitor, emotional facial expressions.
[0s–1s]
SHOT 1 — WORLD CUP FINAL
Massive FIFA World Cup Final stadium.
100,000 fans roaring.
Fireworks explode above the arena.
Martin stands alone in front of goal.
Tiny against the enormous stage.
Camera:
Fast aerial stadium drop toward the goal.
SFX:
Fireworks, crowd eruption.
[1s–2s]
SHOT 2 — THE BIGGEST NIGHT
Extreme close-up.
Martin clenches his gloves.
Sweat on his forehead.
Eyes locked forward.
Everything fades except the match.
Camera:
Rapid push-in toward eyes.
SFX:
Heartbeat.
Crowd muffled.
[2s–3s]
SHOT 3 — NO TIME TO BREATHE
Attackers charge forward.
The ball moves quickly.
Players sprint from every direction.
Chaos unfolds.
Camera:
Fast handheld field-level tracking.
SFX:
Footsteps.
Shouting.
Crowd roar.
[3s–4s]
SHOT 4 — DANGER
Striker breaks through.
One-on-one.
Martin rushes off his line.
The distance closes instantly.
Camera:
Fast forward sprint shot from goalkeeper POV.
SFX:
Heavy breathing.
Boots digging into turf.
[4s–5s]
SHOT 5 — SAVE
The shot explodes toward goal.
Martin launches sideways.
Full stretch.
Fingertips connect.
Ball changes direction.
Camera:
Slow-motion diving save.
SFX:
Impact.
Crowd gasp.
[5s–6s]
SHOT 6 — PRESSURE
Corner kick.
Bodies collide.
Players leap into the air.
Ball hangs above the penalty area.
Chaos everywhere.
Camera:
Fast orbit around the crowded box.
SFX:
Crowd tension.
Players shouting.
[6s–7s]
SHOT 7 — FIGHT
Martin punches the ball away.
Mid-air collision.
Bodies crash around him.
He lands hard.
Camera:
Dynamic rotating action shot.
SFX:
Impact.
Ball strike.
Crowd roar.
[7s–8s]
SHOT 8 — HOPE
Play continues.
Martin rises immediately.
Tracks the ball from distance.
His team launches a counterattack.
Camera:
Quick pan following the attack.
SFX:
Crowd growing louder.
[8s–9s]
SHOT 9 — ONE LAST CHANCE
Final seconds.
Opposing striker fires a powerful shot.
Ball rockets toward the top corner.
Everything slows down.
Camera:
Bullet-time ball tracking.
SFX:
Heartbeat.
Crowd fades.
[9s–10s]
SHOT 10 — BELIEVE
Martin explodes into the air.
Maximum reach.
Time nearly frozen.
Every muscle stretched.
Camera:
360-degree cinematic orbit around the dive.
SFX:
Deep cinematic impact swell.
[10s–11s]
SHOT 11 — IMPOSSIBLE
Fingertips touch the ball.
The ball deflects onto the crossbar.
Bounces away.
The impossible save.
Stadium erupts.
Camera:
Ultra slow-motion goal-line angle.
SFX:
Metallic crossbar ring.
Massive crowd explosion.
[11s–15s]
SHOT 12 — WORLD CHAMPIONS
Final whistle.
Martin collapses in relief.
Teammates rush toward him.
They lift him onto their shoulders.
World Cup trophy rises into the air.
Golden confetti fills the stadium.
Fireworks illuminate the night sky.
Camera continues rising higher and higher.
The entire stadium becomes a sea of celebration.
Final image:
Martin lifting the FIFA World Cup trophy beneath exploding fireworks while teammates and fans celebrate around him.
Camera:
Epic crane-up aerial finale.
SFX:
Final whistle.
Crowd roar.
Fireworks.
Orchestral climax.
NEGATIVE PROMPT
NO subtitles
NO captions
NO text on screen
NO opening titles
NO end credits
NO scoreboards
NO logos
NO watermarks
NO speech bubbles
NO comic panels
NO readable signage
NO Chinese characters
NO English characters
NO UI elements
NO slow pacing
NO static shots
NO duplicated players
NO deformed hands
NO flickering faces
Pure cinematic visual storytelling only, fast-paced FIFA World Cup commercial energy.
SUBJECTS
Painter: adult painter wearing a paint-stained apron, positioned beside a long wooden art table, using a large flat paint brush and palette knife to trap a living paint blob. Starts calm and controlled, then becomes increasingly panicked and messy.
Paint Blob: palm-sized living blob made of glossy blue and orange paint, always moving low across the art table, sliding and hopping forward to the right while performing stretch-and-squash dodges, sudden stops, quick direction changes, and smug gestures. Leaves realistic wet paint trails.
ENVIRONMENT
Messy art studio with one long wooden worktable showing clear depth.
Objects on the table: paint tubes, glass jars, brushes, water cup, sketchbooks, color palette, small canvas frames, cloth rags.
Large blank canvas standing at the far end of the table.
Window is closed.
All mess and damage should accumulate naturally through the scene.
STYLE
Realistic 3D animated short film.
Playful physical comedy.
Strong object physics.
Glossy wet paint material.
Fast but readable action.
Cinematic lighting with colorful paint splashes.
CAMERA DETAILS
Main POV is a low close-following rear perspective behind the paint blob, moving forward across the table.
The painter’s brush attacks mostly enter from above and from the sides.
Only one brief frontal confrontation near the end.
Use wide-angle lens feeling during the chase for speed and chaos.
TIMELINE
0:00-0:02
Medium shot, 35mm, slow push-in.
The painter calmly paints on a canvas while softly humming.
A small paint blob quietly forms inside an open paint cup on the table.
The blob blinks, looks around, then slides out.
The painter notices the movement and slowly stops humming.
SFX: soft humming, tiny wet paint movement, quiet studio ambience.
0:02-0:04
Low-angle tracking shot, 28mm.
The paint blob suddenly accelerates to the right across the table.
The painter lunges forward and makes the first controlled brush swipe.
The brush misses and smacks a paint tube, making it squeeze paint across the table.
The blob dodges by stretching flat and sliding under the brush.
SFX: wet slide, brush slap, paint tube squeeze, quick gasp.
0:04-0:10
POV shot, 20mm, close-follow high-speed movement behind the paint blob.
The camera continuously advances forward without looking back.
The blob performs serpentine dodges, sudden stops, hops over brushes, slides around jars, and leaves colorful trails.
The painter’s brush and palette knife keep attacking from above and the sides.
Every missed hit realistically strikes table objects:
paint jars roll,
brushes scatter,
water cup spills,
paint tubes burst,
sketchbook pages flip open,
canvas frames shake.
The chaos should keep building and stay visible.
SFX: rapid wet sliding, brush impacts, glass rolling, paint splats, water spill, object collisions.
0:10-0:12
POV slows down.
The large blank canvas appears ahead.
The paint blob stops at the edge of the table, turns to face the painter directly, forms a tiny smug face, and waves with a little paint arm.
The painter freezes for half a second, furious and breathless.
SFX: sudden silence, tiny sticky blob sound, breath pause.
0:12-0:14
Medium push-in shot.
The painter throws the large brush toward the blob.
After release, the painter’s hand is clearly empty.
The brush misses the blob and hits the canvas frame.
A paint bucket tips over, creating a huge colorful splash.
The blob dives into the blank canvas and becomes a tiny painted character inside the artwork.
SFX: air whoosh, brush impact, bucket tip, huge paint splash.
0:14-0:15
Wide static shot.
The painter stands with empty hands, staring at the entire studio table now covered in spilled paint, scattered brushes, overturned jars, and ruined sketches.
On the canvas, the little paint blob smiles from inside the painting.
The painter pauses, then lets out a frustrated breakdown scream.
Use
@Image1
(the 12-panel storyboard sheet) as the visual reference for characters, costumes, the "Fable" can design and scene composition. Maintain exact appearance from the storyboard in every shot — consistent character throughout, no drift.
Brand name: "Fable" — in all spoken dialogue and narration it is pronounced 「フェイブル」(fei-bu-ru), never 「ファブル」.
Acting style: classic Japanese TV commercial performance — bright, slightly exaggerated but charming reactions, crisp comedic timing, expressive eyes, energetic and likable delivery.
Shot 1 (0-2s): Follows Panel 1-2 of
@Image1
. Blazing midsummer Japanese suburban street, heat haze rising from the asphalt. A high school girl in a summer sailor uniform trudges uphill, fanning herself, visibly wilting. Camera: slow push-in. Lighting: harsh overhead midday sun, strong contrast.
Dialogue (girl, drained, comically breathless): 「あっつい〜…」
Shot 2 (2-4s): Follows Panel 3-4. She stops, then notices a glowing vending machine in the shade; her eyes lock onto one frosted can of "Fable". Camera: slow pan from her face to the vending machine. Lighting: cool blue glow from the machine against warm sunlight.
Dialogue (girl, hopeful gasp): 「…ん！？」
Shot 3 (4-7s): Follows Panel 5-7. Macro shot of the ice-cold "Fable" can dropping into the tray, condensation droplets flying; she presses it to her cheek with blissful relief, then the pull-tab opens with sparkling carbonation spray. Camera: fixed macro close-up. Lighting: crisp backlit product lighting, droplets glittering.
Dialogue (girl, melting with relief): 「つめた〜い…」
Shot 4 (7-10s): Follows Panel 8-9. She takes a big satisfying gulp, head tilted back against the deep blue sky, bubbles catching the light — then her eyes snap open, sparkling, energy surging back. Camera: low-angle push-in to her face. Lighting: brilliant summer sunlight, lens flare.
Dialogue (girl, explosive joyful shout, classic Japanese CM delivery): 「生き返るーっ！」
Shot 5 (10-13s): Follows Panel 10-11. She sprints up the hill past wilting students, ponytail flying, then at the top raises the "Fable" can high toward the summer sky and grins straight into the camera. Camera: smooth tracking shot from the side, ending on her hero pose. Lighting: vivid golden sunlight, dynamic and energetic mood.
Dialogue (girl, confident smile to camera): 「夏に、負けない。」
Shot 6 (13-15s): Follows Panel 12. Clean final product shot: the chilled "Fable" can centered on a bright background with ice and splashing soda, logo sharp and legible.
Camera: fixed product close-up.
Lighting: clean bright studio-style commercial lighting.
Narration (warm male CM voice, pronounced fei-bu-ru): 「フェイブル。」
Text: "夏に、負けない。フェイブル"
Style: photorealistic live-action Japanese TV commercial, cinematic quality, natural colors, bright summer palette (blue sky, white highlights, cool aqua product accents), 4K, sharp resolution.
Avoid: jitter, distortion, deformation, blur, flickering, ghosting, character drift, warped text on the can.
[Create a 15-second live-action fantasy battle filmed from the perspective of a spectator sitting in the audience. One continuous wide handheld audience shot. No cuts. No angle changes. No random scene changes.
Setting: ancient Japanese-inspired fortress arena with stone walls, wooden gates, watchtowers, cloth banners, dusty ground, stairs, trees, and battle damage. Natural daylight, soft shadows, earthy colors, realistic dust and debris. Audience silhouettes and phones visible at the bottom of frame.
Characters:
Sand Titan: massive humanoid made of compacted sand, clay, dirt, and small rock fragments. Rough cracked body, broad shoulders, glowing amber eyes, sand constantly falling from joints.
Steel Guardian: human-sized armored hero in realistic brushed steel armor, scratched plates, agile but believable.
0-2s: Sand Titan rises from a collapsing sand mound at center arena. Dust rolls outward. Steel Guardian stands opposite in defensive stance.
2-4s: Titan charges with heavy footsteps. Guardian sidesteps and lands two fast armored punches into Titan’s chest. Sand bursts from impact points.
4-6s: Titan swings a huge arm. Guardian ducks and slides across dirt. Sand scatters naturally. Both stay in the same arena positions.
6-8s: Guardian fires a focused gauntlet blast. It tears through Titan’s shoulder. Sand erupts into a thick debris cloud.
8-10s: Titan’s shoulder rebuilds as sand pulls back into the wound. Titan slams both fists into the ground, sending a sand wave toward Guardian.
10-12s: Guardian jumps over the sand wave, lands hard, charges forward, and drives an energy punch into Titan’s torso. Massive sand explosion.
12-14s: Titan collapses from the center outward. Chunks of sand and dirt fall apart. Dust fills the arena. Guardian backs away.
14-15s: Titan collapses into a giant mound. Guardian stands victorious through drifting dust. In the background, a weathered wooden arena banner has “Vidfield AI” carved into it like part of the set, subtle and natural, not a watermark or overlay.
Style: realistic live-action stunt show, grounded superhero fight, practical VFX, believable physics, continuous choreography, realistic sand simulation, cinematic arena spectacle, detailed armor, natural daylight, audience-view perspective, fun escalating action.
Negative prompt: random cuts, multiple angles, closeups, shaky unusable camera, floating bodies, cartoon motion, unrealistic physics, inconsistent character design, changing armor, changing sand body, extra limbs, warped hands, bad anatomy, flickering sand, disappearing objects, blurry action, teleportation, giant random beams, overpowered effects, text overlays, watermark, logo overlay, UI elements, inconsistent arena, low-quality render.]
A high-octane 15-second cinematic action sequence featuring a stylish young Asian man with long, flowing silver-blue hair and sharp facial features, in a dark cyberpunk post-apocalyptic world.
He is wearing a black leather jacket, tactical pants, and heavy combat boots. Dynamic, fluid, and extremely detailed animation.
Scene sequence:
0-3s:
He runs powerfully through a dark abandoned industrial hallway filled with smoke and sparks, back view showing "LRG" text on his jacket, then turns and sprints forward as explosions and muzzle flashes light up the corridor.
3-6s:
Intense close-ups of his face and hair flowing dramatically, followed by a powerful boot kick that shatters debris, then he dives and rolls while firing dual pistols with bright muzzle flashes.
6-9s:
Epic slow-motion jumps — he leaps through a large glass window, shattering it into thousands of pieces, then performs a mid-air acrobatic flip while surrounded by flying glass and fire.
9-12s:
He jumps out of a burning building through flames, lands in a destroyed city street at night with burning cars and explosions in the background, then crouches low in a dramatic hero pose.
12-15s:
Final intense close-up of his determined face with hair dramatically blowing, then he charges forward directly toward camera with intense expression as the entire city burns behind him.
Cinematic lighting, dramatic rim lighting, heavy smoke and sparks, realistic physics on hair and clothing, highly detailed, photorealistic, epic action movie style like John Wick meets Cyberpunk 2077, dark moody color grading, 8K quality, smooth 60fps motion.
the same character, consistent anime rendering,
dynamic cinematic motion.
Here’s the exact prompt I used 👇
PROMPT
Subject
Image reference: charismatic anime bartender in a luxury cocktail bar at sunset
Action
she prepares a cocktail with ninja-like precision, cuts ingredients in a spectacular choreography, pours everything into a shaker, shakes it with insane rhythm, then begins pouring liquid into a glass
Camera
dynamic anime action camera, fast whip pans, macro ingredient close-ups, slow motion slicing, orbit shots around her body, elegant low angles
Scene
luxury bar lounge, golden bottles, marble counter, warm sunset through panoramic windows, refined atmosphere
Style
premium anime action commercial, elegant energy, liquid VFX, sparkling particles, high-end lighting
Sequence
- She stands behind the bar, confident smile, golden light reflecting on bottles and marble
- She throws lime, orange and herbs into the air, slices them mid-air with precise ninja-like bar tools, juice droplets sparkling in slow motion
- Ingredients fall perfectly into the metallic shaker, close-ups on ice, citrus, syrup and glowing liquid splashing inside
- She shakes the shaker with explosive choreography, fast hand movements, body turns, hair and jewelry moving naturally, liquid energy glowing inside
- She stops sharply, opens the shaker, first stream of glowing cocktail liquid begins pouring into an elegant glass
CUT EXACTLY HERE FOR CONTINUATION
Use @shoe
the Gravity Runner 01 shoe reference, @kai
as the athlete Kai reference, and @sky
as the futuristic skytop city environment.12-second ultra-cinematic futuristic sportswear commercial opening sequence at sunrise above a megacity.Opening shot begins with a slow aerial camera descent through clouds toward the massive spiral skytop training tower suspended above the city. Blue energy lane lights pulse softly across the running circuit while morning sunlight reflects off glass and titanium structures.Cut seamlessly to Kai standing alone at the start gate platform overlooking the skyline. His black technical sportswear moves subtly in the wind. The glowing blue accents on the Gravity Runner 01 shoes pulse gently.Slow cinematic push-in toward Kai’s face. Calm focused expression. Reflections of the city lights move across his eyes and jacket surfaces. Subtle atmospheric fog drifts around the platform.Close-up macro shots of the Gravity Runner 01 shoes: carbon mesh textures, glowing propulsion chambers, reactive sole technology, blue energy flowing through the midsole channels.Kai steps forward slowly onto the smart track surface. The lane beneath his feet activates with synchronized blue light waves extending into the distance.Final shot: low-angle side profile of Kai preparing to sprint while the sunrise floods the skyline behind him. The camera holds briefly, creating a perfect transition point for future video extensions.Style: ultra-premium futuristic sports advertisement, cinematic realism, luxury tech aesthetic, grounded motion, smooth camera movement, atmospheric sunrise lighting, reflective materials, subtle blue energy VFX, no text overlay, no subtitles.Audio: ONLY realistic sound effects, no music. Soft wind ambience, distant megacity atmosphere, subtle electronic hums, shoe energy activation sounds, quiet fabric movement, futuristic track system pulses.
Use the uploaded visual development sheet as the only visual reference and transform it into a complete cinematic animated short film. Do not generate the sheet itself as a document or page. Do not show borders, labels, captions, frames, color swatches, or layout elements. Extract the visual world from the sheet and turn it into a continuous animated film.
The story takes place at dusk by a quiet seaside shrine. A lonely child arrives near a weathered wooden torii gate by the rocky shore as shell wind chimes sway softly in the sea breeze. The sky is blue-gray with a warm sunset glow near the horizon, while tidepools begin to shimmer with bioluminescent cyan ripples. The child notices the strange light, and a small glowing sea spirit slowly emerges from the water. It is soft, gentle, luminous, and semi-transparent, with a rounded form that feels cute, magical, and ocean-like.
Preserve the design consistency from the reference sheet throughout the whole film, including the child, the spirit, the shrine elements, the rocky shore, and the twilight color palette. Let the emotional arc build quietly as the child approaches, reaches out, and forms a tender bond with the sea spirit. Then expand the scale of the story as glowing cyan trails spread across the sea and an enormous whale spirit rises from the water in a majestic, awe-filled climax. End on a calm and healing wide shot with the child, the small spirit, and the fading presence of the whale near the seaside shrine.
Create a 15-second ultra-cinematic sneaker commercial for the Air Jordan 4 Military Black based on the provided storyboard reference.
Style:
Luxury sneaker campaign mixed with modern sportswear advertising. The video should feel sleek, premium, energetic, cinematic, and visually expensive.
Visual tone:
Black studio environments, glossy reflections, dramatic contrast, moody spotlighting, realistic textures, wet pavement reflections, luxury fashion-commercial grading.
Sneaker details:
Air Jordan 4 Military Black.
White leather upper, black mesh side panels, grey suede overlays, visible Air unit, black lace cage structure, layered sole.
Video format:
16:9
15 seconds
4K cinematic look
Fast premium pacing
Mix of cinematic motion and selective 120fps slow motion
Sequence flow:
0:00 - 0:01
Jordan box drops onto reflective black floor under spotlight. Cinematic smoke drift.
0:01 - 0:02
Box lid slowly opens with bright white light leaking out.
0:02 - 0:03
Hero rotating beauty shot of the sneaker on dark platform.
0:03 - 0:04
Extreme macro shot of side mesh texture and stitching details.
0:04 - 0:05
Close-up of grey suede overlay with moving reflections.
0:05 - 0:06
Lace tightening sequence with cinematic tension.
0:06 - 0:07
Macro shot of visible Air cushioning with glossy reflections.
0:07 - 0:08
Sneaker enters stylish urban environment in shallow depth of field.
0:08 - 0:09
Low tracking walking shot across wet reflective pavement.
0:09 - 0:10
Fast stair-running sequence with dynamic motion blur.
0:10 - 0:11
Sneaker floating in black studio while camera performs smooth orbit.
0:11 - 0:12
Slow-motion impact landing with cinematic dust burst.
0:12 - 0:13
Sharp white light scans across sneaker silhouette in darkness.
0:13 - 0:14
Final premium hero shot on reflective black floor with dramatic spotlight.
0:14 - 0:15
Minimal cinematic end frame with “AIR JORDAN 4” style branding composition.
Camera movement:
Smooth push-ins, macro glides, low-angle tracking, orbit movement, cinematic slow motion, premium handheld stabilization.
Motion style:
Controlled, elegant, expensive, polished. No shaky camera. No chaotic edits.
Audio design:
Deep cinematic bass, paper rustle, subtle whooshes, lace tension, wet footsteps, impact hits, airy studio reverb, modern trailer-style electronic beat.
Important:
Keep sneaker proportions and design consistent across all shots.
Maintain premium commercial realism.
No subtitles.
No cluttered overlays.
Focus on cinematic sneaker storytelling and luxury product presentation.
Use the storyboard image only as a shot reference. Create a continuous live-action commercial film, not a storyboard page.
Start inside a fast-food restaurant where a tired young employee works behind the counter. Another person hands him a black insMind Energy bottle. Show a cinematic close-up of the bottle with condensation and strong lighting.
After he drinks it, his energy instantly activates in an exaggerated Thai-commercial style. The restaurant transforms into a massive World Cup football stadium with dramatic floodlights and roaring crowds.
Show dynamic football shots:
– close-up grass-level movement
– football control and kick
– stadium celebration after scoring
Then suddenly cut back to reality:
The employee is awkwardly posing behind the restaurant counter while the bottle falls onto the floor.
End with a premium product packshot of the black insMind Energy bottle under stadium lights.
Style:
Fast-paced cinematic sports commercial, realistic lighting, energetic camera movement, premium Nike/Adidas-style football visuals mixed with Thai-style comedy contrast.
Use
@Image1
as Raiken Storm Warrior reference,
@Image2
as Raikō Thunder Priestess reference, and
@Image3
as the storm fortress environment reference.
15-second anime cinematic sequence at Hakuganjo, a massive mountain fortress during violent rain and lightning.
Raiken stands on a wet stone bridge, black cloak whipping violently in the storm, thunder katana glowing blue in his hand. Across from him, Raikō appears at the fortress gate, long robes and talismans moving in the wind, sacred spear charged with divine lightning.
The camera slowly tracks between them as rain explodes against the stone floor. Lightning strikes the towers behind them, illuminating banners, waterfalls, rooftops, and storm clouds.
Raikō raises her spear and summons vertical bolts of lightning from the sky. Raiken draws his katana fully, blue electricity crawling across his armor and blade.
Both charge forward at extreme speed. Their weapons collide in the center of the bridge, releasing a massive shockwave that pushes rain outward in a circular blast. The camera orbits around the clash as blue lightning arcs between sword, spear, armor, and wet stone.
Raiken slides back, then launches a fast katana strike. Raikō pivots gracefully, blocking with the spear and sending lightning across the bridge. Stone cracks beneath their feet.
Final moment: both warriors stand locked in combat under a giant lightning strike, faces intense, clothes and hair moving violently, fortress glowing behind them through storm fog.
Style: high-end anime action, dark storm fantasy, cinematic lightning VFX, heavy rain, wet reflections, dramatic cloth motion, fast but readable choreography, no text, no overlays.
Use @[storyboard ref] as the complete cinematic shot blueprint: follow its panel order, staging, camera logic, timing rhythm, composition, action beats and motion continuity, but do not treat it as one collage image.
Create a 15-second 16:9 cinematic anime action video.
Dawn mountain temple training yard above a misty gorge, uneven wooden pole tops, cracked stone platform, loose dust, splinters, falling debris, distant cliffs and huge vertical emptiness below.
Final-video look: dawn gold rim light, cool blue mist, soft cel shadows, sharp silhouettes, anime brush texture, controlled motion blur, readable orange-blue flame trails, ember particles, cracked wood and stone chips.
Fight: the girl crouches on a high pole as the mech charges, then pole-sprints, evades smashed supports, wall-runs, dodges overhead shockwave impacts, flips through debris and uses orange-blue flames for recovery. Keep gravity heavy, height dangerous, footing unstable and motion disciplined, never floaty.
Final role reversal: the girl kicks off a falling fragment and lands safely on a remaining pole or platform edge as her flames fade, while the mech overcommits, breaks his own support and falls alone into the misty abyss.
VFX must stay readable and physically motivated: orange-blue flame trails cling to the girl's acceleration, impacts throw ember bursts, pole breaks release splinters and dust clouds, stone hits create sharp debris chips, and all particles fall downward with heavy gravity into the misty gorge.
No text, no subtitles, no UI, no watermark.
#Image1 standing at the very top of a gigantic gothic clocktower overlooking a massive Japanese cyber-feudal city at night, violent wind blowing through her silver hair and black-red outfit, cinematic moonlight, glowing neon reflections, ultra detailed anime movie aesthetic, epic anime style, insane atmosphere.
Slow cinematic orbit camera around her as she stares down at the city with cold determination. Suddenly the ground violently trembles. Explosions erupt across the streets below.
#Image2 emerges from the darkness between collapsing buildings, gigantic demonic yokai covered in cursed red-black energy, glowing eyes, monstrous aura corrupting the city. Cars explode, debris flies everywhere, civilians running in panic, cinematic destruction sequence.
Extreme close-up on #Image1 eyes narrowing. She smirks confidently.
She suddenly jumps from the clocktower in an insanely stylized anime sequence, dynamic camera spinning around her body mid-air, cape and hair flowing dramatically, dual pistols unfolding in her hands, insane sakuga animation energy, god tier motion.
While falling through the city skyline she begins firing explosive glowing bullets toward #Image2. Massive muzzle flashes illuminate the night.
Ultra dynamic anime action sequence: bullets streak through the air with glowing trails, but #Image2 calmly blocks every shot using his gigantic cursed blade, sparks and demonic energy exploding with each impact.
Final shot: both characters land facing each other in the middle of a destroyed avenue surrounded by fire and debris, cursed energy storm swirling around them, ultra intense stare-down, masterpiece anime movie visuals.
Anime horror cinematic sequence inside a cursed abandoned Tokyo subway station at night.
@Image3
establishes the environment: flooded platforms, flickering dead neon lights, wet concrete floors, occult symbols painted across pillars, long humid corridors disappearing into darkness.
@Image1
enters slowly from the station entrance wearing a black urban exorcist uniform with white gloves and ritual seals attached to his blade. His footsteps echo through puddles while cold blue light flickers overhead. Coat fabric sways subtly as he scans the darkness with calm focus.
The camera follows low behind him in one continuous cinematic movement through narrow subway corridors. Emergency lights pulse faintly red. Water drips from ceiling pipes. Occult markings glow briefly on the walls as he passes.
Suddenly
@Image2
appears far down the platform beneath broken fluorescent lights. Long black hair floating unnaturally, torn pale kimono drifting without wind, calm smile barely visible in darkness. Crimson spectral threads slowly spread across the station floor like veins.
The exorcist unsheathes the sealed blade. Ritual talismans flutter violently. Blue spiritual energy illuminates the wet station while shadows distort around the entity.
The spectral woman glides silently toward camera without moving her legs normally. Her cursed threads begin sewing through the air itself, wrapping pillars and hanging cables like living stitches.
Fast cinematic escalation: the exorcist dashes forward through shallow water, blade glowing blue, while the entity unleashes waves of floating crimson threads and distorted butterflies. Neon lights explode overhead during the clash.
Final shot: both figures stand motionless at opposite ends of the flooded platform while rainwater ripples between them and the cursed symbols pulse beneath the station floor.
Style: ultra cinematic anime horror, modern occult aesthetic, dark urban fantasy, atmospheric neon gloom, realistic cloth simulation, supernatural lighting, subtle camera shake, wet reflective surfaces, eerie restrained motion, high-detail anime film quality, no subtitles, no text overlay.
35mm and anamorphic lenses, high-contrast midday lighting, vibrant cinematic action color grade. Immersive spatial audio with high-fidelity sound design.[IMAGE REFERENCES / LEGEND]@ini
: Exact starting frame and main character reference. Maintain identical facial features, crimped/braided hairstyle, black tank top, jewelry, and "BAKU-CRUNCH" holographic snack bag design across all shots.@story
: the sequence to implement.[TIMELINE SECOND BY SECOND]0-2.5s: [Medium Shot] Exact match to @ini
. 35mm lens, slightly low angle, static camera. Main character holds the BAKU-CRUNCH bag confidently, looking directly into the camera. [SFX: Tokyo street ambience, subtle dramatic drone]2.5-5s: [Extreme Close-Up] 100mm macro lens, front angle, rapid camera push-in to her mouth biting into a textured chip. High-impact crunch animation. [SFX: Crisp, bone-shattering crunch sound effect with stereo echo]5-7.5s: [Profile Long Shot] 28mm lens, profile angle panning right. A powerful sonic shockwave from the crunch shatters nearby glass building facades and sends stylized debris flying through the air. [SFX: Glass exploding, deep structural rumble]7.5-10s: [Worm's-Eye Wide Shot] 18mm lens, low angle tilting up. Street framing warps slightly from the kinetic energy; character looks around with a cool, playful expression of surprise. [SFX: Whoosh, building distortion sounds]10-12.5s: [Close-Up] 50mm lens, slight low angle pushing in. Character looks forward, holds a single chip up, and smiles mischievously. [SFX: Rising electronic bass sweep]12.5-15s: [Wide Shot Climax] 24mm lens, slight low angle with a smooth dolly-back movement. Character walks confidently toward the camera in slow motion as parked cars flip and fire hydrants burst into massive water plumes behind her, finally shows the snack bag. [SFX: cinematic explosion][STYLE & QUALITY BOOSTERS]Photorealistic 8K, ultra-detailed textures, cinematic commercial lighting, perfect fluid motion blur, flawless character consistency, movie-level physics.
100% realistic footage, use the start frame storyboard as a reference to make a full sequence. Always adhere to the notes on the storyboard. keep the character consistent through the shots, aim to ultra realism
Using
@Image1
as the cybernetic white tiger mech reference,
@Image2
as the crimson mecha dragon reference, and
@Image3
as the futuristic Tokyo environment.
15-second ultra-cinematic mecha battle in futuristic Tokyo during heavy rain at night.
The sequence opens with the white tiger mech sprinting through rain-soaked neon streets at extreme speed. Massive paws smash into wet pavement, sending water spraying everywhere. Blue optic lights glow through steam and rain.
Above the city skyline, the crimson mecha dragon descends between skyscrapers with enormous metallic wings unfolding through the storm. Red energy pulses beneath its armored scales while neon reflections ripple across its body.
The dragon unleashes a massive plasma breath across the avenue. Explosive shockwave tears through holographic billboards and lights up the entire district in red-orange energy.
The tiger mech leaps vertically between buildings using wall-run propulsion. Dynamic anime-style camera tracking follows the movement with intense speed blur and realistic inertia.
Mid-air collision between both machines. Metal claws scrape against armor plating, sparks exploding across the rain. The dragon crashes through elevated transit rails while the tiger mech lands violently on the street below.
Final sequence: both titans face each other in the middle of flooded Tokyo streets. Steam rises from damaged armor, glowing eyes locked together while neon reflections flicker across the wet city.
Camera style: aggressive anime cinematography, fast tracking shots, low-angle scale shots, cinematic push-ins, aerial combat framing, realistic motion physics, dynamic handheld energy.
Lighting: neon cyberpunk Tokyo, rain reflections, holographic signage, blue and crimson energy glow, volumetric fog, cinematic storm lighting.
Style: ultra-detailed anime realism, premium VFX, cinematic destruction, futuristic Japanese megacity atmosphere, realistic rain simulation, mech combat spectacle, no text, no overlays.
2/2
15-second cinematic continuation shot, alternating slow-motion and real-time sequences in bookend pattern — slow-motion opening, chaotic real-time middle section, slow-motion finisher. Brutal close-quarters physical combat, no powers, no energy weapons, no time-freeze visuals, no stylized martial arts posing.
Arri Alexa 65 with 40mm anamorphic lens shot at variable framerate (24fps real-time, 120fps slow-motion conformed to 24fps timeline), shallow depth of field, aggressive horizontal lens flares, slight anamorphic edge distortion, subtle gate weave during impacts.
Bleach bypass color grading, desaturated mid-tones, crushed blacks, blown highlights, silver retention. Harsh sun-bleached canyon palette with pale limestone cliffs, oxidized copper mechanical internals, rust-coated debris, dried blood tones, deep crimson hydraulic fluid accents glowing subtly beneath fractured armor seams.
CHARACTERS (heavily battle-damaged):
— CRIMSON SENTINEL: towering white ceramic-plated combat android with cracked armor plating, deep gouges across chest and helmet, exposed copper pistons and torn hydraulic tubing visible through torso gaps, red visor flickering intermittently, left shoulder partially missing, right hand trembling from servo damage, crimson hydraulic fluid dripping onto sand, ceramic plating covered in claw marks and dust abrasion. Defensive combat stance constantly recalibrating through damaged joints.
— UNKNOWN REPTILIAN CREATURE: tall sinewy biomechanical reptilian humanoid composed of dark oxidized flesh, exposed tendon-like tendrils, wet fibrous musculature wrapped around skeletal frame, elongated claws fractured and bloodied, jaw partially split exposing layered teeth, spine protrusions flexing during motion, oily blood and dust caked across torso, aggressive feral movement driven entirely by momentum and instinct.
ENVIRONMENT: dry canyon basin under brutal midday sunlight, towering limestone walls reflecting hard heat, drifting dust clouds, scattered rusted wreckage and broken mechanical debris partially buried in sand, shimmering heat haze across the ground, dry wind carrying fine sand particles through frame.
CAMERA: slow-motion sections use floating orbital camera drifts with subtle handheld inertia, real-time sections use violent handheld tracking and rapid reactive reframing. Tight medium-close framing during impacts, low camera height near waist level to exaggerate mass and speed. Heavy micro-shake during collisions, stabilized drift during slow-motion bookends.
BEAT 1 — SLOW MOTION 5x OPENING (0:00–0:04):
The reptilian creature launches across the canyon gap in a massive forward leap, sand exploding beneath its feet in suspended particles. Tendrils whip backward through the air while saliva and dark blood trail from its jaws in slow arcs. The CRIMSON SENTINEL pivots defensively, one damaged foot grinding into rock as hydraulic pistons compress under stress. The robot raises one fractured forearm shield-first while its other arm retracts near the torso preparing a counter. Sunlight streaks across cracked ceramic plating as floating dust drifts through shallow depth of field. The reptile’s claws extend inches from the robot visor as both figures converge mid-frame.
BEAT 2 — REAL-TIME (0:04–0:06):
Instant full-speed collision. The reptile slams into the robot’s guard with a deafening metallic crack. The robot absorbs impact, rotates its hips, drives a brutal knee strike into the creature’s ribcage, then immediately follows with a savage spinning backhand across the reptile’s skull. Teeth fragments, hydraulic fluid, and blood spray across frame. Camera violently whip-pans with impact momentum.
BEAT 3 — REAL-TIME (0:06–0:08):
The reptilian creature recovers instantly and lunges upward onto the robot’s torso, claws digging deep into cracked chest armor. Ceramic plates tear free as exposed internals spark mechanically. The added momentum drives the CRIMSON SENTINEL backward onto the canyon floor. Heavy body impact sends dust and pebbles outward in a shockwave across the sand.
BEAT 4 — REAL-TIME (0:08–0:10):
Ground exchange. The reptile repeatedly rakes claws across the robot’s faceplate, carving fresh gouges into the visor housing. The robot grabs the creature’s jaw with both hands, fingers crushing into wet tissue while servos scream under load. The reptile snaps violently inches from the robot’s visor while both bodies grind through dirt and shattered stone fragments. Broken armor shards scrape across the lens foreground.
BEAT 5 — REAL-TIME (0:10–0:11.5):
Both combatants stagger upright simultaneously. The robot’s damaged arm hangs partially limp while leaking crimson fluid down its fingers. The reptile’s jaw hangs dislocated and twitching. They stand chest-to-chest at close range breathing heavily — mechanical ventilation against wet animal snarling. Heat haze distorts the air between them while canyon wind carries drifting dust through the narrow space.
BEAT 6 — SLOW MOTION 6x FINISHER (0:11.5–0:15):
Both fighters attack simultaneously. The reptilian creature swings a full-force claw strike toward the robot’s head while the CRIMSON SENTINEL drives a crushing armored punch directly into the creature’s throat and jawline. Impact occurs mid-frame in ultra slow motion. Ceramic fragments, teeth, blood mist, sand particles, and crimson hydraulic fluid erupt outward in layered detail. The reptile’s flesh compresses around the robot’s fist while the robot visor fractures from the claw impact, red optics flickering violently. Camera slowly pushes inward during suspended destruction as debris rotates through sunlight. Final freeze frame on mutual impact with both faces inches apart, bodies twisting from collision force.
Hard cut to black at exactly 15 seconds.
DIEGETIC SOUND DESIGN ONLY, NO MUSIC, NO SCORE, NO STINGERS:
— 0:00–0:04 (slow-mo): heavily lowered-pitch tendon stretching, deep metallic servo groans, elongated air displacement from leap, hydraulic creaking with extended tail reverb, sub-frequency impacts emphasized beneath canyon wind.
— 0:04–0:06 (real-time): explosive metal-on-bone collision, sharp ceramic cracking, dense knee impact thud, violent backhand crunch, rapid sand scatter underfoot.
— 0:06–0:08 (real-time): claws piercing armor plating, servo overload screech, heavy body slam into canyon floor, debris shower bouncing across stone.
— 0:08–0:10 (real-time): scraping claws against ceramic shell, jaw snapping inches from microphone perspective, grinding stone friction, strained hydraulic pressure release.
— 0:10–0:11.5 (real-time): mechanical breathing vents, wet guttural snarls, fluid dripping onto sand, distant cicadas and dry canyon wind.
— 0:11.5–0:15 (slow-mo): ultra-deep impact bass, stretched ceramic fracture sounds, slowed bone crunch, elongated fluid spray textures, massive low-frequency resonance with extended reverb tail.
— continuous ambient bed: dry canyon wind, distant cicadas, shifting sand, subtle rock debris movement, heat-driven environmental creaks.
Photorealistic, IMAX-grade tactile detail. Slow-motion frames maintain hyper-detailed debris separation and visible material deformation. Real-time combat remains violently kinetic but readable on every impact frame. No text, no logo, no watermark.
Part 1
@ Image1 as the storyboard reference. Strictly follow Storyboard 1: The Sleeping Beacon.
K-17, a small maintenance robot with matte off-white ceramic shell, brushed bronze joints, single cyan camera eye, scratched glass chest light, tiny antenna, and worn red shoulder stripe, wakes inside an abandoned lunar lighthouse outpost. Maintain the exact same robot design in every shot. Stylized 3D animation, Blender render feel, warm highlights cold shadows, tactile scratched metal and dusty glass materials. No brand logos, no readable screen text, no camera gear visible.
Scene 1: Wide shot of a forgotten lunar lighthouse half-buried in moon dust, Earth small in the sky. Slow dolly push over 3 seconds, eye-level horizon locked.
Narrator: “On a silent moon outpost, one little machine still remembered its job.”
Scene 2: Medium close-up of K-17 waking in a dusty maintenance bay, cyan eye flickering on. Locked-off camera, shallow depth of field.
Narrator: “For years, K-17 guarded a beacon no one answered.”
Scene 3: Over-shoulder shot of K-17 watching the tower lens fade above, no readable screen text. Slow tilt up from K-17 to the dark lens.
Narrator: “Then one night, the signal died.”
Scene 4: Close-up of K-17 uncovering a cracked amber power core beneath broken panels. Slow push from close-up to tighter close-up, reflections shifting across glass.
Narrator: “But beneath the dust, it found one last spark.”
Scene 5: Wide vertical-feeling shot of K-17 standing at the base of a huge spiral staircase, holding the heavy core. Low angle, slow pull back revealing the scale.
Narrator: “So it began to climb.”
Scene 6: Final wide shot, tiny K-17 climbing alone into the dark tower. Camera remains steady, beacon chamber above barely glowing.
Tone: quiet, emotional, lonely, hopeful.
Audio: low lunar wind, soft metal creaks, faint synth pulse, delicate piano notes.
No on-screen text.
Each individual frame of the images has been assembled to create a music video. This is an emotionally rich, MV-style production featuring English lyrics and a touching, ballad-like aesthetic.
Generate a 15s cinematic sequence 🎬🔥
This is where it comes to life.
Here’s the exact prompt I used 👇
An elegant performer inspired by a legendary moonwalk dancer, dressed in a sleek black outfit with hat, transforming into a diamond trophy through motion
His moonwalk generates energy trails that evolve into abstract light and crystallize into a diamond sculpture
Luxury cinematic: slow dolly, orbit shots, macro details, seamless transitions, final push-in
Scene
dark premium studio, black reflective floor, golden spotlight, floating particles
Ultra high-end commercial, diamond reflections, golden light particles, smooth VFX transitions
- Movement phase wide shot, smooth moonwalk, subtle light trails appear
- Energy phase, camera closer, golden trails intensify, lingering in space
body begins dissolving into light
- Abstraction phase, camera orbit, body becomes swirling luminous ribbons, abstract silhouette forms
- Form phase, energy condenses into faceted diamond structure
limbs sharpen into reflective geometry
- Design phase, full diamond figure locked in iconic pose
light glints across surfaces
Final shot, trophy on pedestal, slow push-in, luxury finish
CUT
Scene: One continuous shot - Hand-held YouTube-style video showing a woman performing a complete yoga vinyasa flow.
Character: Use IMG1 as the character we're following in the scene.
Character Motion: Use IMG2 to follow the motion and instructions exactly to complete her flow.
The scene starts at IMG1.
Direction: The woman stands in a peaceful orange yoga studio. The hand-held camera subtly pushes in on her as she begins her flow. It captures the moment in tight composition as she moves from mountain pose to upward salute.
The camera begins to pull back out as she transitions from upward salute to swan dive and stays focused on her body as she transitions from swan dive into a forward fold.
The camera begins to move right to a side profile as she plants her palms and steps back into the high plank position. The camera drops lower and pushes in towards her face for a focused close-up as she moves from chaturanga lower to upward-facing dog.
The camera again pulls out, showing her full body as she transitions to the downward-facing dog position. Finally, she holds for a deep inhale and exhale in that position.
Overall Tone: Her movements are all natural and fluid, controlled and directed, strong with natural body movements and subtle readjustments as she gets her balance.
SoundFx: peaceful ambient hum as we hear her inhale and exhale in a rhythmic fashion with each passing pose. No music.
Create a fight scene between char 1 and char 2 that takes place in Location 1 add in proper fight kind of lighting, the fight should follows the exact sequence and movements from steps 1–12 shown in img 1. The music should just be fight SFX. There should be no dialogue, text, or narration
Use @[image1] as the character reference sheet. Maintain strong consistency in face, hair, outfit, silhouette and key accessories.
Create a cinematic 15s multi-cut VFX showcase video in realistic 3D.
The scene should have a realistic 3D look with high-end CGI quality, physically believable materials, cinematic lighting, volumetric atmosphere and strong depth. The character performs a summoning in a grounded real environment.
Start with a calm setup shot. Then show the first trigger of the effect around the character or on the ground. The summon effect builds in clear stages, with energy gathering, symbols or forms activating, force rising and a visible presence emerging. Show the summoned entity, object or presence appearing gradually and clearly from the effect.
The character must move naturally with the effect and feel like they are channeling, directing and controlling the summon. Avoid stiff posing. Use body language, gesture and reaction that match the buildup and force of the effect.
Structure:
- setup shot
- activation detail shot
- build-up shot
- peak summoning shot
- emergence shot
- final hero shot with the summon fully present
Realistic 3D, cinematic, high-end CGI, visually grounded, readable VFX, smooth shot progression, believable lighting interaction, strong atmosphere. No text, no subtitles, no watermark.
Unsteady handheld phone footage shot from [SHOOTER VANTAGE / SHOOTING POSITION] at [TIME OF DAY], [LENS/PHONE PHYSICAL POSITIONING DETAIL], producing [PRIMARY OPTICAL ARTIFACT, e.g. a faint smear of condensation fog, a smudge of fingerprint oil, a streak of rain] across the [FRAME LOCATION, e.g. lower quarter, right edge, top third] of the frame and intermittent [LIGHT FLARE TYPE, e.g. glare blooms, lens halation, prismatic streaks] from the [DOMINANT LIGHT SOURCE] reflecting back against the shooter's phone camera, the image is flat, auto-white-balance toggling between [COLOR CAST 1, e.g. a cool blue cast] and [COLOR CAST 2, e.g. an orange-amber push] as [LIGHT MIXING SCENARIO, e.g. ambient street light mixes with interior glow], color entirely ungraded and slightly washed out.
At 0s the camera swings erratically [DIRECTION, e.g. left-to-right, low-to-high, side-to-side] hunting for the subject, frame wildly off-center, catching [BLURRED ENVIRONMENTAL DETAILS visible during the search] before the autofocus locks momentarily on [SUBJECT 1: physical build, age range, hair, distinguishing features] [SUBJECT 1 POSITION/LOCATION IN SCENE], [SUBJECT 1 WARDROBE: detailed top-to-bottom clothing description with fabric, color, fit, accessories, and posture/demeanor]. [OPTIONAL SUBJECT 2: positioning relative to subject 1, full physical description, wardrobe, body language toward subject 1, exuding [RELATIONSHIP/INTERACTION DYNAMIC]].
At 2s the autofocus drifts off [the pair / the subject] and [BACKGROUND ELEMENT] sharpens while [the subject(s)] go soft and blurry, the camera operator [SHOOTER REACTION, e.g. whispering urgently off-mic, cursing under breath, holding their breath] before it snaps back to focus at 4s with a visible hunting pulse.
[INTERRUPTION 1, e.g. a pedestrian, a server, a passing vehicle] [crosses / passes / blocks] the frame at 5s, briefly obscuring [the subject(s)] behind [OBSCURING ELEMENT], the shooter dipping and angling to reacquire them through [SHOOTING MEDIUM, e.g. the glass, the foliage, between parked cars].
At 6s [INTERRUPTION 2, e.g. a camera flash from another phone further down the sidewalk, a passing headlight wash, a neon sign flicker] [REFLECTION BEHAVIOR] creating a hot chromatic flare across the [FRAME EDGE], cyan and red fringing visible on the high-contrast [HIGH-CONTRAST EDGE DETAIL].
[SUBJECT NAME/IDENTIFIER] [REACTION VERB, e.g. glances, flinches, turns] briefly toward [SHOOTING MEDIUM] at 8s, [REACTION DETAIL: expression shift, body movement, instinctive shielding gesture] before [returning to conversation / stiffening / leaning back into shadow]; the shooter holds completely still for two seconds, barely breathing.
At 10s the phone [CAMERA SHIFT, e.g. dips, tilts, drifts] as the operator shifts weight, the frame [FRAMING ERROR, e.g. cutting off both subjects at the shoulders, clipping a head, losing them entirely] momentarily, [OPTICAL ARTIFACT EVOLUTION, e.g. the window fog smearing the bottom edge thicker], before rising again to reframe them, composition still imperfect, slightly tilted, [SUBJECT BODY PART] clipped by the frame edge.
[AMBIENT AUDIO BED, e.g. distant traffic noise, low restaurant chatter, lobby murmur] bleeds through the audio throughout, [MICROPHONE INTERFERENCE, e.g. wind buffeting the microphone in a low rhythmic thump, fabric rustle as the operator shifts], faint [BACKGROUND VOICES OR SOUNDS] from [SOURCE, e.g. other pedestrians on the sidewalk, nearby tables], and at 12s [HALF-AUDIBLE EVENT, e.g. an excited whisper from someone just off camera says something unintelligible], followed by [SECONDARY AUDIO EVENT, e.g. the rapid-fire click-burst of a DSLR shutter from nearby, a car door slamming, a phone notification chime].
At 14s [ENVIRONMENTAL DETAIL, e.g. the interior light flickers slightly, possibly a server passing] and the autofocus hunts one final time before the clip ends at 15s with the frame still imperfectly held on [the subject(s)] through the [SHOOTING MEDIUM CONDITION, e.g. foggy reflection-streaked glass, leaf-broken sightline], [SUBJECT QUALITY 1] and [SUBJECT QUALITY 2] both visible but never cleanly captured.
Create a seamless 15-second dance choreography video based on the uploaded reference image.
Use the female dancer from the reference image as the main character.
GPT Image 2.0 prompt for reference sheet:
[STYLE]
monochromatic grayscale illustration, 3D rendered character, clean instructional reference sheet,
white background, comic-style cell grid layout, technical diagram aesthetic
[LAYOUT]
4x4 grid layout, 16 panels total, each panel separated by thin black border lines,
numbered cells from 1 to 16, consistent panel size
[CHARACTER]
young female dancer, athletic build, ponytail hairstyle,
crop top and baggy pants, sneakers, same character in all panels
[PANEL STRUCTURE - per cell]
top-left: bold number badge + Korean title text
center: full-body character pose illustration
bottom-left: Korean description text (3-4 lines)
overlay: directional arrows indicating movement direction
[ARROWS / MOTION INDICATORS]
curved arrows, straight arrows, circular rotation indicators,
placed around the character to show movement flow and direction
[RENDERING STYLE]
high detail 3D sculpt style, soft studio lighting, subtle shadows,
no color, grayscale shading, clean linework, game concept art quality
[NEGATIVE]
no background scenery, no color tones, no extra characters,
no cluttered backgrounds
been testing a different workflow lately using tapnow. what makes it interesting is how it structures the entire process from idea → visuals → final video. instead of jumping between tools, you can actually build everything in one flow and refine it step by step like a real production pipeline. for the visuals, i'm using seedance 2.0 which is currently one of the strongest models for photoreal, human-centered video. but quick note — seedance 2.0 is currently only available in selected regions and requires a verified corporate email to access. still, the direction is clear: AI video is moving from "generation" → into "directing". also, they just launched a global challenge called "10,000 Parallel Universes" with a $200K prize pool. if you're exploring cinematic AI workflows, this is actually a good place to test ideas and push concepts further.
Use the references with strict priority and role separation:[REF_STORYBOARD] = primary guide for shot order, framing, timing, composition, and scene progression.
Follow it strictly.[REF_GIRL_MODEL] = character identity anchor for the teenage girl.
[REF_PHOENIX_MODEL] = creature identity anchor for the phoenix.
[REF_BACKGROUND] = environment and forest background anchor.Create a Japanese anime action scene of a teenage girl fighting two phoenix birds in a forest.Absolute priority:Follow the storyboard strictly for all shots and scene progression.
Keep the girl design locked to [REF_GIRL_MODEL].
Keep the phoenix design locked to [REF_PHOENIX_MODEL].
Keep the forest and path consistent with [REF_BACKGROUND].
The girl:
teenage anime girl, short black bob haircut, rust-orange headband, rust-orange wrap tunic, dark inner collar, cropped dark loose pants, agile fighter silhouette, determined expression, consistent face and costume in every shot.The phoenixes:
two large mythic phoenix birds, copper-gold-orange plumage, pale chest, broad wings, long tail feathers, flame-like crest details, powerful talons, consistent design in all shots.The environment:
lush forest path, tall trees, dense foliage, rocks, roots, grass, earthy ground, warm daylight, cinematic depth.Visual target:
clean Japanese anime linework, polished final-frame rendering, crisp cel shading, dynamic camera angles, detailed forest backgrounds, strong action readability, finished anime film look.Important: storyboard is the main source for camera and shot progression
no photorealism
no 3D CGI
no rough sketch look
Original Action Short Film: It opens with a futuristic city with almost real movie texture, gradually transitioning to a high-energy two-dimensional action style. Characters chase, leap and confront at high speed between neon viaducts and high-rise buildings. The lens language is stable at first and then explosive; the materials transition from real metal and wetland reflections to exaggerated energy lines and dynamic painting sense, forming a visual effect of "integration of real movie sense and anime explosive sense". A strong hook in the first 2 seconds, with a stable main body, coherent actions, movie-level composition and light and shadow, real texture, epic sense, strong emotion, high-definition details, suitable for social media communication.
Extreme close-up on the toe area. thousands of glowing white fibers burst out, twist and interlock, gradually forming the front shape of a sneaker. The surface develops a detailed 3D woven texture. Soft glow, high-tech feeling, sharp focus, shallow depth of field.
I finally cracked character consistency in Seedance 2.0
• Works with real humans
• Works with fictional characters
• Train once → generate infinitely
No hacks, just a solid workflow 🔥
Now open-sourced in Open-Higgsfield-AI
Seedance 2.0
