Made with OpenClips.AI

@image1 is LANA — photocopy their exact face and hair exactly as in @image1. IGNORE the clothes and accessories in @image1. Eyes visible. Lana MOVES. @image2 is the OUTFIT. Photocopy every garment, colour, fabric and accessory exactly as in @image2, worn in motion. Never add garments that are not in @image2. NEVER a studio cyclorama. 10-second 9:16. Ultra-real 35mm street fashion. Busy New York — yellow cabs, pedestrians, lights. LANA is ON the CROSSWALK (white stripes), walking toward camera mid-stride. The @image2 outfit moves with the stride. Crowd and traffic are BEATS. [TIMELINE — 10 SECONDS] 0–2s: Lana steps onto the crosswalk, the @image2 outfit moving, NYC behind. 2–6s: Walks toward camera on the stripes. Cabs. People around Lana. 6–10s: Closer, slight head turn, outfit still moving. Designed hold. Audio: city, footsteps, horns far. No lyrics.

@image1 is the absolute character lock for the opening state: face, body, hair and clothing are taken from it exactly, with no drift or reinterpretation. @image2 is the absolute lock for the state after the transition: hair and makeup match it exactly. The person, the clothing and the location are the same before and after — only the hair and makeup change. One continuous handheld shot at arm's length, the subject framed from the chest up. They face the lens with the chin dipped slightly and lift one open palm toward the camera. The palm rises and sweeps across until it fills the frame completely in motion blur. As it clears to the opposite side they are revealed in the state of @image2, already settled and facing the lens. They raise one hand and rake the fingers slowly back through the hair from the temple, releasing the lengths to fall. They turn the head to one side and back, the hair swinging out and resettling against the shoulder. They lower the hand and square up to the lens, a small closed-lip smile arriving as the last of the hair comes to rest. Constant handheld micro-movement throughout, the framing breathing gently as if the camera is held in one hand. The palm crossing the lens is the only transition — everything on either side of it runs as one unbroken take. The camera holds its distance: no push in, no pull back, no orbit. No spoken dialogue, no on-screen text, no watermark.

2 steps80

Your avatar runs a five-move dance medley on a retro TV soundstage. Music only, loud. See the video step for the full prompt.

@image1 (nine-look reference sheet) is an absolute appearance lock. Read it left to right, top row first: cells 1 through 9 are the nine looks, in that order. Face, body and skin tone are identical in every shot and taken from the sheet. Hair and clothing change only to the next cell's look, with no drift, reinterpretation or invented variation. [Style] Studio photography quality, warm beige solid-colour background, portrait lighting, smooth beat-based transformation rhythm. [Scene] The seamless warm beige studio background remains unchanged throughout. Front softbox portrait lighting, slight rim light on the hair edges. Background colour, light direction and exposure are identical from the first shot to the last. [Camera] Fixed vertical medium close-up from just above chest height, subject centred and facing the camera. The camera never moves. [Transition mechanism] Every change of look uses the same cut: at the end of a beat the subject turns their head to the side and whips their hair, the fast hair movement throwing motion blur across the frame and briefly covering the face, and the cut lands inside that blur. They turn back already wearing the next look. All nine transformations use this transition, with the spoken hairstyle name and a centred subtitle switching at the same moment. [Beats] All nine beats carry equal weight and equal screen time. None is rushed and none is held longer than the others. Beat 1, cell 1 — they face the camera and say "Long black straight." Turn and whip hair. Beat 2, cell 2 — the curls bounce with the turn as they say "Wool curls." Turn and whip hair. Beat 3, cell 3 — they raise a hand to say hello and say "Big waves." Turn and whip hair. Beat 4, cell 4 — the hair ends sway slightly as they say "Shoulder-length bob." Turn and whip hair. Beat 5, cell 5 — the ponytail swings with the movement as they say "High ponytail." Turn and whip hair. Beat 6, cell 6 — the hair falls gently as they say "Collarbone-length hair." Turn and whip hair. Beat 7, cell 7 — they say "Princess cut." Turn and whip hair. Beat 8, cell 8 — they make a heart shape to the camera and say "Egg roll curls." Turn and whip hair. Beat 9, cell 9 — they turn back with a wink and say "Super short hair." The subtitle pops up and they settle into a held final pose. [Audio] Upbeat beat-driven music underneath. Each turn and whip is paired with a whoosh of hair cutting through air and a click. The ending carries a rising freeze-frame sting. Spoken lines and subtitles are in English. Do not generate any text other than the nine subtitle lines named above. No logo, no watermark, no additional captions. The background never changes colour or texture. No camera movement, no zoom, no orbit, no push.

2 steps31629.1K

A 15-second product comedy ad, vertical 9:16. The product does the talking. Pick a presenter, upload one photo of the appliance, and swap LINE for whatever you want it to say.

2 steps

MODEL: Seedance 2.5 — use this model specifically. Do NOT use MiniMax or any other model for this generation. FORMAT: 9:16 (vertical video) QUALITY: High-fidelity, 4K render, sharp detail, no compression artifacts AUDIO: Generate synchronized natural audio for this scene — ambient light rain outside, a rising whoosh as time freezes, near-silence during the freeze, then a sharp splash and a delighted laugh as time resumes. No music, no voiceover, no narration. ASSET MAP: @image1 — the subject. Photocopy this person. PHOTOREAL LIVE-ACTION — HIGHEST PRIORITY AFTER IDENTITY: Real camera, real tiny human, real jacket pocket. Not CGI, not a figurine, not a doll, not a sticker, not a composite. Match grain, colour and lighting between the person, the droplet and the fabric so the shot is one photograph. SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. Exact face, facial features, eye shape, skin tone, build and gender presentation. Hair, makeup, jewellery and clothing exactly as in @image1. Do not beautify, restyle or alter identity. Only scale changes. Refer to them only as they/them in this prompt. THEY ARE INSIDE THE POCKET BAG — NOT ON IT: The subject is a few centimetres tall and sits DOWN INSIDE the jacket-pocket cavity. Fabric walls surround them. They stand and move on the inner fabric floor, not perched on the outside of the pocket like a brooch. Their legs and hips sink into the cloth; folds wrap them; they cast a contact shadow; they occlude the weave behind them. POCKET READ FROM FRAME 1: This is a real JACKET POCKET on a different full-sized adult's coat (never the subject's face on the wearer). A first-time viewer must instantly recognise a clothing pocket — not a fabric cave, not a bag, not a tunnel of cloth, not a person glued onto the pocket front. Camera sits just outside the garment at chest/hip height, looking down and IN through the pocket opening. The opening is angled slightly upward toward grey drizzle sky so daylight and rain can enter. In every frame keep visible at once: - the coat: outer fabric, seam, stitching, welt or flap, pocket-edge hem - the pocket as a 3D pouch sewn onto the jacket, with a clear opening - the tiny subject inside that pouch, a few centimetres tall, pocket bag huge around them Do not crop so tight that only fabric walls remain. If the pocket silhouette would leave the frame, pull the camera back. Outdoors, light drizzle, pale daylight shaft through the opening, dust and mist in the beam. Same light on their skin, the droplet and the fabric. Pores, flyaways, fabric weave. cameraFixed unset. CONTINUOUS MOTION: Real visible physical motion for almost the entire duration — no calm establishing pause longer than 1 second except the designed freeze below. 0-1s HOOK — already mid-action: pale daylight cuts into the pocket. They are already reacting, shielding their eyes, off-balance, down inside the pouch. Pocket opening, coat stitching and sky visible. 1-3s: One giant raindrop breaks through the opening and falls straight toward them in real time, growing larger. WOW — TIME FREEZE + ORBIT: The instant the drop is inches from them, everything FREEZES. Spherical droplet hangs, refracting daylight, faintly reflecting their silhouette. They are frozen mid-flinch, hair and jacket caught in motion, mist particles suspended. Camera does a slow cinematic 180-degree orbit around the frozen droplet and subject, shallow depth of field, still showing the pocket opening and coat. Freeze holds about 2 seconds. TIME RESUMES at full speed — droplet bursts past them in a splash, fine spray outward. 6-8s: Half-drenched, they laugh, wipe their face, notice a small puddle forming on the fabric floor beside them, their reflection in it. Still down inside the pouch; pocket hem and coat stitch in frame. 8-10s: They scoop a little puddle in cupped hands, watch it catch the light, look straight into camera and grin triumphantly, still dripping, still inside the cavity. SCALE: Pocket stitching and fabric weave, raindrop surface tension and puddle reflection read at true scale next to the tiny subject. No on-screen text, no watermark, no subtitles, no second copy of their face on the wearer, no gym, no vanity lights from the still.

MODEL: Seedance 2.5 — use this model specifically. Do NOT use MiniMax or any other model for this generation. FORMAT: Vertical video, 9:16 aspect ratio. DURATION: 8 seconds. AUDIO: Generate synchronized natural audio for this scene — soft fabric rustling as the subject climbs and grips the pocket edge, a sharp metallic clink when the coin drops in, a startled gasp, and a genuine laugh at the end. No music, no voiceover, no narration. ASSET MAP: @image1 — the subject. SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. Exact face, facial features, hairstyle, skin tone, build and gender presentation stay unchanged — only their scale changes. Do not beautify, restyle or alter identity. Photocopy @image1. Face, hair, skin and outfit exactly as in @image1 stay. POCKET READ — MUST BE OBVIOUS FROM FRAME 1: This is a real jeans FRONT POCKET on a pair of blue denim jeans worn at the hip of a different, full-sized adult (never the subject’s face). A first-time viewer must instantly recognise it as a clothing pocket — not a fabric cave, not a bag, not a tunnel of cloth. Camera sits OUTSIDE the garment, slightly above hip height, looking down and in through the pocket opening. In every frame keep visible at once: - the jeans: waistband, a belt loop, bartack stitching, rivet, denim weave - the pocket as a 3D pouch sewn onto the jeans, with a clear U-shaped opening and a folded pocket-edge hem - the tiny subject inside that pouch, a few centimetres tall, with the pocket bag huge around them Do not crop so tight that only fabric walls remain. If the pocket silhouette would leave the frame, pull the camera back. CONTINUOUS MOTION REQUIRED: Real, visible physical motion for almost the entire 8 seconds — distinct actions, never one static pose held for seconds. Indoors, soft natural window light from one side. The wearer of the jeans is a different full-sized adult — never give them the subject’s face. 0-1.5s: Wide enough to read the jeans pocket on the hip. Tiny subject sits inside the pocket bag, looking up at the opening and the light. Waistband and belt loop still in frame. 1.5-3.5s: They grip the folded pocket-edge hem with both hands and climb, hoisting themselves up until perched on the rim of the pocket opening, legs dangling over the outside of the jeans, catching their breath. The U-shaped pocket opening stays readable. 3.5-5s: The person wearing the jeans shifts their weight; the whole pocket pouch sways. The subject grips the hem tightly, body rocking, still clearly inside a jeans pocket on a hip. 5-6.5s: A coin drops in from above through the pocket opening and lands with a clatter beside them in the pouch — the subject flinches back, startled, both arms raised. The coin is enormous next to them. Pocket opening still visible. 6.5-8s: They relax, walk over and pick up the coin with both hands, straining against its size, then hold it up over their head in triumph, laughing — still standing inside the jeans pocket, waistband in frame. SCALE REALISM: Stitching, denim weave, belt loop and coin are true size next to the tiny subject. Match lighting so it reads as one photograph, not a composite. No on-screen text, no watermark, no subtitles.

SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. Photocopy their exact face, facial features, hairstyle, skin tone, build and gender presentation. Do not beautify, restyle, de-age or alter identity. Only their scale changes. @image1 is the subject. Keep their clothes and accessories exactly as shown. Only size changes: they are a few centimetres tall. CONTINUOUS MOTION REQUIRED: Real, visible physical motion for almost the entire 8 seconds — not a static pose. Something is always moving: the giant finger descending, the subject dodging, the grab, the swing, the landing. Do not default to a calm, mostly-still shot. SCENE: The subject, shrunk to a few centimetres tall, stands on an open human palm — a different, full-sized adult hand, not the subject’s own. The hand is held at roughly waist height, palm up, fingers relaxed and slightly spread, indoors with soft natural window light from one side so the skin texture and the subject both read clearly. Photoreal. One continuous real photograph, not a composite. SCALE REALISM: The palm’s skin texture, lines, and the finger’s fingerprint ridges must read at true full size relative to the tiny subject — every texture detail on the hand looks enormous next to them. Match lighting and colour grade between the subject and the hand throughout. Keep the camera framing wide enough that the entire arc of motion (finger descending, the grab, the swing, the landing) stays visible in frame. Never open on the attached studio still or a grey headshot. No on-screen text, no watermark, no subtitles. No other people except the giant hand that holds them. 9:16. TOTAL DURATION: 8 SECONDS. 0-1s: Subject stands calmly in the centre of the palm, weight settled, looking around at their surroundings. Full body of the tiny subject is readable. Palm lines look enormous next to them. 1-3s: A giant index finger slowly descends from directly above the frame toward the subject — clearly visible entering from the top, moving at a deliberate, readable speed, not too fast to track. As it nears palm height, the subject notices, reacts with a startled flinch, and dodges sideways just in time, the fingertip passing close beside them. 3-6s: Before the finger retreats, the subject changes their mind mid-motion — they lunge forward and grab onto the fingertip with both hands, fingers wrapped around the tip. The giant hand lifts slightly, carrying the subject a short distance up and sideways through the air in a small arc — a genuine swinging motion, not just a lift. The subject’s legs kick slightly, hair and clothing trailing with the motion, face showing visible thrill and a wide grin. 6-8s: The finger lowers the subject back down onto the palm. They let go, stumble half a step to find their footing, then straighten up and give the giant finger a playful pat with one hand, laughing. Original instrumental music throughout — cinematic, no lyrics, no known songs.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT standing on a dark surface in a broad wedge of soft daylight, and it defines the object's colour, material, surface finish, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE SIGNATURE — read this before the timeline: THE SIGNATURE is whatever part of THE OBJECT a person would recognise it by. If THE OBJECT has a face, that is its signature. If it does not, its signature is its most distinctive feature — a label, a logo, an opening, a handle, a cap, a pattern, a moulded detail, a corner, whatever makes it that object and not some other object. Wherever this film refers to THE SIGNATURE, use whatever that is on @image1. THE LIGHT: the only light in this film is the broad soft wedge of daylight from @image1 — the kind that falls through a window and lies diagonally across a surface. It is wide, it spans a large part of the frame, and its edge is soft and diffuse. It keeps exactly that width, that warmth and that soft edge for the whole film, and it moves the way afternoon sun moves: slowly, as one big soft shape drifting across the scene. HOW IT MELTS — the most important rule: every part of THE OBJECT stays joined to every other part for the entire film. It changes only by softening and flowing, the way warm honey and thick syrup behave. Its surface is one continuous unbroken skin at every moment, and its silhouette is always a single closed outline that sags, rounds and slumps. At any instant the shape is simply a softer, rounder version of the instant before — the change is always gradual and always connected. Whatever THE OBJECT is made of in @image1 — soft or rigid, glass, metal, plastic, card or fabric — under this heat it behaves as one thick warm syrup: it holds together and it flows, staying whole as it goes. Summary: a cinematic ASMR film in which the warmth of moving daylight melts THE OBJECT down completely, the camera moving through five distinct shots — extreme macro on the sunlit surface, a fast pull back to the whole figure, an orbit around it as it collapses, a punch in to THE SIGNATURE, and a crane up over the pool at the end. Timeline: 0–2s — Extreme macro on THE OBJECT's sunlit surface. The camera creeps closer still. The daylight glows through the material and a soft broad highlight slides gently across it as a wet sheen spreads. The first bead swells and starts to run. 2–4s — The camera pulls back fast and smoothly, opening out to reveal the WHOLE of THE OBJECT standing in the wedge of daylight. It is already going: its outline softens and its material runs down its sides, pooling around its base where the light is warmest. 4–6s — The camera orbits steadily around THE OBJECT as it collapses. It sags and folds in on itself, its sides slump outward, and the molten material spreads into a widening glossy pool that carries the soft daylight across its surface. 6–8s — The camera punches in fast to what remains of THE SIGNATURE, filling the frame. The daylight lies across it warm and broad, and it rounds off, softens and slides. 8–10s — The camera cranes up and over, rising to look straight down on the pool as the last of the shape sinks into it. The wedge of daylight drifts slowly onward across the surface, rings spread out and flatten, and the pool holds glossy and still at the final frame with THE OBJECT's colour glowing through it. Notes: THE OBJECT keeps exactly the colour, translucency and surface finish it has in @image1, and everything that runs and pools is that same material in that same colour, holding the same hue and the same darkness throughout. The material behaves as one thick viscous liquid: slow, heavy and continuous, and volume is conserved — the pool grows by as much as the object loses. THE OBJECT melts down completely over the ten seconds, and THE SIGNATURE is the last part of it to go. Whatever the daylight lies on is warm and softly lit; whatever falls outside it stays in gentle shadow, and the boundary between them is always soft and wide. The surface carries whatever real fine detail @image1 actually shows the whole way — seams, grain, moulding, weave or print as the case may be — with micro-texture and a slightly uneven sheen. Each of the five camera moves is smooth and continuous within its own section and the film runs as one unbroken take with no cuts. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — the faint wet creep of the sheen spreading, a fat clean drip as the first bead runs, a low heavy sagging tone under the collapse, a soft rush of air as the camera moves, thick wet slumping as the shape gives way, and the quiet settle of the rings flattening out.

2 steps

IDENTITY LOCK — @image1: keep the exact face and identity locked. AUDIO — music only, loud. See the video step for the full prompt.

Photoreal cinematic street scene, premium commercial grade, sunny palm-lined luxury shopping street, shallow depth of field, natural daylight, subtle filmic grain, realistic skin, fabric and liquid — an accidental sidewalk bump that spills a coffee and knocks the sunglasses off, played spontaneous and glossy, building into two hyper-zoom ultra-slow-motion brand-name hero shots, never aggressive. LEAD is exactly the person in @image1 — preserve their exact face and identity throughout, real skin, exactly two hands. They hold a smartphone in the LEFT hand pressed against the LEFT ear, clearly mid phone call to someone else, hand visibly gripping the phone at ear level (never tucked under the arm or armpit). In the RIGHT hand they hold a coffee cup exactly like @image2 (same cup, colours and readable brand logo exactly from the reference). Sunglasses exactly like @image3 (same frame and readable brand logo on the temple exactly from the reference) worn on the head. They walk relaxed, smiling, talking into the phone, saying only: "Hello, OpenClips AI?". A SECOND PERSON with a dog enters diagonally from the right on their own independent path that simply happens to intersect — clearly a different-looking person, not resembling @image1. He glances at the dog; @image1 is on the call. Neither targets the other, neither accelerates — no lunge, squared shoulder, push or body-check. BEATS (one continuous take; real-time, then hyper-zoom ultra slow motion on the brand names, then real-time): 0-2.5s camera tracks BACKWARD at heel height then tilts up to a medium of @image1 walking toward us, the phone in the left hand at the ear mid-call, the @image2 cup in the right hand, the @image3 sunglasses catching sun. 2.5-4.5s the second person and the dog cross in from the right on their own line, paths converging naturally. 4.5-6s they notice each other at the last instant, both twist to avoid contact, shoulders clip tangentially — a glancing touch, small stumble, NOT a hit; the @image2 cup jolts free and the lid pops; the @image3 sunglasses lift off the head and tumble; @image1 keeps the phone in the left hand. 6-11s BRAND HERO 1, HYPER ZOOM + ULTRA SLOW MOTION: rush into an extreme macro of the airborne @image2 cup nearly frozen in the air, its brand NAME filling the entire frame, razor-sharp and perfectly readable; a hard highlight sweeps slowly across the lettering so each letter GLEAMS, coffee droplets suspended and glinting. Hold long on the readable name. 11-16s BRAND HERO 2, HYPER ZOOM + ULTRA SLOW MOTION: match-cut to an extreme macro of the @image3 sunglasses turning almost imperceptibly, the brand logo on the temple filling the frame, razor-sharp; a highlight sweeps slowly across the logo so the name GLEAMS, lenses flaring. Hold long. 16-18s speed eases back: wider, @image1's smile turns to wide eyes and parted lips, phone still in the left hand; the second person recoils with an apologetic open palm reaching to steady them AFTER contact; the dog takes one startled step. Spontaneous surprise, not anger or fear. 18-20s FINAL: the @image2 cup and @image3 sunglasses settle together on the pavement in the spilled coffee, a slow rack focus drifting between the readable @image2 brand name and the @image3 brand name — both crisply accented — then hold and end. CAMERA: gimbal backward track and tilt up to open, handheld through the bump, two deliberate hyper-zoom pushes locking onto the brand names in ultra slow motion, ease wide for reactions, finish on a low static two-brand shot on the ground; natural autofocus, realistic exposure. No impossible camera move. Realistic physics on the stumble, the liquid arc, the falling sunglasses and the dog; natural motion blur, cinematic slow-motion, no soap-opera look. Exactly two hands each. SOUND: real street ambience — footsteps, distant traffic, faint chatter, dog tags jingling, a soft gasp on contact, a deep whoosh as the ultra-slow-motion brand shots engage, a crisp settle as the cup and glasses land; only @image1's single line "Hello, OpenClips AI?" spoken into the phone; no other dialogue, no invented language. NEGATIVE: the phone tucked under the arm or armpit, the phone not held in the hand at the ear, @image1 talking to themselves with no phone, or mumbling to no one; any aggression — lunge, squared shoulder, shove, body-check or punch; pre-arranged anger or fear; @image1's identity or face changing; the second person resembling or duplicating @image1; a third hand, extra arm, more than two hands, extra or missing fingers; the coffee cup or sunglasses differing from @image2 and @image3, changing brand, shape or logo, garbled, blurry, warped or misspelled brand names or logos, or invented extra branding, storefront ads or watermark; on-screen text, captions, subtitles or numbers other than the real logos on @image2 and @image3; the coffee spilling unrealistically; the cup, sunglasses or dog vanishing, dissolving, fading or teleporting — every exit is physical; plastic or beauty-filtered skin; a scene cutting off mid-action or jumping to an unrelated scene.

Your avatar transforms into the animal from the reference image in one dramatic cinematic take, close on the face. Music only, loud. See the video step for the full prompt.

3 steps

Two avatars perform a contemporary duet in a marble museum atrium. Music only, loud. See the video step for the full prompt.

Create an ultra-realistic lifestyle video as one seamless continuous-looking shot that loops perfectly. @image1, @image2 and @image3 are absolute locks. @image1 is LOOK 1, @image2 is LOOK 2, @image3 is LOOK 3. Face, hair, body, proportions, garments, materials and colours are taken from these references exactly, with no drift or reinterpretation in any frame. Every accessory shown in a reference stays present and unchanged whenever that look is on screen. Natural Instagram lifestyle Reel, relaxed and relatable. Soft autumn daylight, restrained warm grading, realistic skin, fabric and clothing movement. Not a luxury campaign, runway video or cinematic commercial. Camera on a locked tripod across the street, facing the subject straight-on and showing their full body. The framing never changes: no pan, tilt, zoom, tracking, dolly, handheld movement, reframing, stabilization drift or angle change. The subject stands naturally beside a pedestrian traffic-light pole on a simple city sidewalk, near the centre of frame, with the pedestrian signal clearly visible to their right. Keep the environment clean and minimal: a sidewalk, neutral urban background, road and one traffic-light pole. The pedestrian signal stays red for the entire clip. Beats, each given equal weight: They wait naturally beside the red signal in LOOK 1. A dark gray SUV passes through the extreme foreground and completely hides them. During full occlusion, instantly change to LOOK 2. LOOK 2 is revealed. They make one small, natural posture adjustment. A cream city taxi completely hides them. During full occlusion, instantly change to LOOK 3. LOOK 3 is revealed. They casually shift their weight. A black family sedan completely hides them. During full occlusion, instantly change back to LOOK 1. LOOK 1 is revealed again and they wait naturally beside the red signal, in the same stance, the same position and the same framing as the opening frame. There are exactly three outfit changes and three complete outfits. Every change is performed through a practical foreground vehicle wipe. Each vehicle passes close to the camera and completely hides their head, face, hair, hands, handbag, torso, legs and shoes. Switch outfits instantaneously only while they are 100% invisible behind the vehicle. Never show two outfits simultaneously. No morphing, dissolves, flashes or magical transformations. Their identity, hairstyle, proportions, standing position and background alignment remain perfectly consistent. All three vehicles travel one at a time in the same horizontal direction with natural speed, wheel movement, shadows and motion blur. The last frame must match the first frame so the clip loops with no visible seam: same outfit, same stance, same hand and bag position, same light, same red signal, same background alignment. Strictly no camera movement, visible cuts, outfit morphing, partial transformations, identity drift, face changes, sliding feet, warped hands, extra limbs, disappearing accessories, vehicles passing behind the subject, crowded scenery, a green signal, walking out of frame, text, logos or watermark.

4 steps099

IDENTITY LOCK — @image1: keep the exact face, bone structure, eyes, eyebrows, nose, mouth, skin tone, hairline, hairstyle, hair length, texture and colour, freckles or marks, apparent age, build and proportions identical in every frame. The attached @image1 outranks every word: where text and image disagree, follow the image. @image1 is an adult, the only person in the frame, and never turns into anyone else. The clothing comes from @image1 and never changes; fully dressed, ordinary closed shoes on at all times, never barefoot. THE ROUTINE — a set commercial hip-hop combination performed by a trained dancer, technical and hit-driven, not freestyle. GROOVE BASE: the bounce drives down on every count and releases on the and-count, never dropping. HITS: chest pop, shoulder snap and arm hit, each accelerating fast and stopping DEAD with a visible lock and micro-vibration. TUTTING: forearms build two or three precise right-angled frames in front of the chest and face, wrists breaking cleanly on the count. WAVE: one unbroken body wave fingertip-wrist-elbow-shoulder-chest-ribs-hips-knees, each segment a fraction after the one above. FOOTWORK: kick-ball-change into a cross-step behind, a heel-toe swivel, then a double-time shuffle under a still upper body. LEVEL CHANGE: a controlled drop into a deep squat on the beat, one hand sweeping a low arc, a push back up on the next count. TURN: a single clean inside turn on the ball of one foot spotting the lens, landing square on the beat back into the groove. DIRECTION — one continuous handheld-on-gimbal take: medium-wide in the key beam, snap-push on the first hit, orbit a quarter-circle through the tutting, glide low and lateral on the wave, drop to knee height on the footwork, sink and rise on the level change, crane up and back to a wide on the final hit; continuous screen direction, no cuts, no spinning camera, no teleporting. SCENE — a professional black-cyc dance studio: seamless dark floor with a soft sheen, black walls falling off into nothing, one hard key light from camera-left, a cool blue rim from behind, light haze, a faint floor reflection. Nobody else, no mirrors, no clutter. Let each beat play out fully; ONE continuous coherent take, no cuts. 0-2s ready bounce, head snaps up, first chest pop locks; 2-4s four hits each stopping dead, camera snap-push; 4-6s three tutting frames then a shoulder roll, camera orbits; 6-8s one full body wave, camera glides low; 8-10s kick-ball-change, cross-step, heel-toe swivel, double-time shuffle, camera at knee height; 10-12s deep squat level change with a floor sweep and controlled rise; 12-14s clean inside turn back into the groove plus two fast hits; 14-15s final hit locks hard, one arm into the beam, eyes to lens, camera cranes up and back. CHOREOGRAPHY — trained technique throughout: full arm extension, clean lines, dead stops on every hit, controlled weight, spotting on the turn, accurate foot placement, natural knee compression, realistic hair and fabric movement. ANATOMY — @image1 has exactly two arms and two hands with five fingers per hand, two legs and two feet, both feet contacting the floor cleanly on every landing. LOOK — ultra-photorealistic, 35mm and 28mm low, deep focus so the feet and the floor stay sharp, one hard key beam from camera-left, a cool blue rim from behind, visible haze, a faint floor reflection, deep true blacks, realistic grain, natural motion blur, cinematic shutter. AUDIO — music only, mixed loud and full so the music dominates the entire soundtrack from the first frame: an original hard hip-hop instrumental (heavy 808 sub, crisp snare on the backbeat, tight hi-hat rolls, a dark synth motif, stab accents that land exactly on the hits, a short filter build into the double-time bar). NO background or ambient sound of any kind, no studio room tone, no footsteps, no shoe squeak or scuff, no foley, no recognisable copyrighted melody, no spoken dialogue, no invented language. NEGATIVE — any background, ambient or foley sound, room tone, footsteps, shoe squeak or scuff audio competing with the music, music too quiet or not clearly audible; amateur or tentative movement, freestyle flailing, generic arm waving, swaying with no footwork, pausing to find the next move, moves blurring with no dead stops; the groove dropping; hits off the beat; the wave breaking into separate isolations; the turn wobbling or landing off the beat; the squat collapsing; feet hidden or cropped out of frame; floating, sliding or skating feet, gait glitching; the camera cutting, teleporting or spinning; a scene cutting off mid-action; jumping to a random unrelated scene; skipped or truncated beats; @image1 vanishing, dissolving, fading or teleporting; a second person or a duplicated @image1; @image1's face, hair, skin tone, body or age changing; a third hand, extra arm, more than two hands, extra or missing fingers; extra or missing legs, warped or morphing limbs, blurred or duplicated feet, body distortion; bare feet, barefoot, a single shoe, changing outfit; slow motion, speed ramps, repeated movement loops, aerial shot; plastic or beauty-filtered skin, anime, cartoon or CGI look; mirrors, studio clutter, on-screen text, captions, subtitles, numbers, readable signage, invented logos or watermark; only the elements explicitly described appear.

IDENTITY LOCK — @image1: keep the exact face, bone structure, eyes, eyebrows, nose, mouth, skin tone, hairline, hairstyle, hair length, texture and colour, freckles or marks, apparent age, build and proportions identical in every frame. The attached @image1 outranks every word: where text and image disagree, follow the image. @image1 is an adult, the only person dancing in the frame, and never turns into anyone else. The clothing comes from @image1 and never changes; fully dressed, ordinary closed shoes on at all times, never barefoot. THE MOVE — an afrobeats street routine danced low and loose, driven from the knees and hips: fast alternating heel-and-toe LEGWORK with knees bent and turned slightly out, feet low and quick, weight rocking, upper body bouncing; a SHOULDER BOUNCE lifting and dropping on the off-beat while the legs tap underneath; an ARM SWEEP arcing over the head as the opposite leg kicks out low and the torso leans away, landing on the beat; a LOW BOUNCE sinking into a wide half-squat for two beats then rising; a TRAVELLING STEP of three quick side steps with a small hop on the last, carrying the body across frame without breaking the bounce. Loose and grounded — heavy feet, light shoulders, free hips, never stiff, never on the toes. FRAMING — full body from the top of the head to the shoes, feet always visible with margin below, a slight low three-quarter angle so the legwork and knee bend read, the camera tracking laterally with the travelling step at the same speed; never crop above the knees. SCENE — a sunlit late-afternoon courtyard: worn concrete, a flaking painted wall, a corrugated roof edge throwing a hard diagonal shadow, a big speaker on a plastic crate, washing lines overhead, green leaves in one corner; two onlookers stand well back clapping, never dancing and never entering the dance area. Let each beat play out fully and finish before the next begins; ONE continuous coherent take, no cuts and no scene changes. 0-2s ready rock beside the speaker, head lifts, legwork starts; 2-5s eight fast heel-toe taps, shoulders bouncing, dust lifting; 5-7s arm sweep with a low kick, once each side; 7-9s wide half-squat low bounce twice, rise back into legwork; 9-11s three travelling side steps with a hop, camera tracking laterally, roof shadow crossing the body; 11-12s final pose, knees bent, one arm up, chest lifted, into the lens. CHOREOGRAPHY — the bounce never stops, clear preparation before the kick and hop, accurate foot placement, natural knee compression, loose hips and heavy grounded feet, realistic hair and fabric movement. ANATOMY — @image1 has exactly two arms and two hands with five fingers per hand, two legs and two feet, both feet contacting the ground cleanly on every tap and landing. LOOK — ultra-photorealistic, 28mm from slightly low, deep focus so the feet and the concrete stay sharp, hard late-afternoon sun as the key with a warm bounce off the wall, strong diagonal shadow, fine dust, realistic grain, natural motion blur on the fast legs, cinematic shutter. AUDIO — music only, mixed loud and full so the music dominates the entire soundtrack from the first frame: an original afrobeats track (log-drum bass line, shakers and woodblock percussion, a syncopated kick, a bright plucked melody and wordless vocal chants), a clear steady beat every tap lands on. NO background or ambient sound of any kind, no courtyard tone, no clapping or crowd, no footsteps, no foot taps or shoe scuff, no foley, no recognisable copyrighted melody, no spoken dialogue, no invented language. NEGATIVE — any background, ambient or foley sound, clapping, crowd, footsteps, foot taps or shoe-scuff audio competing with the music, music too quiet or not clearly audible; generic jumping, marching, skipping or freestyle flailing instead of the legwork; the knees straightening or the dancer rising onto the toes; the bounce stopping; the onlookers joining in, copying the dance or entering the dance area; more than two onlookers; feet hidden or cropped out of frame; floating, sliding or skating feet, gait glitching; a scene cutting off mid-action; jumping to a random unrelated scene; skipped or truncated beats; @image1 vanishing, dissolving, fading or teleporting; a duplicated @image1 or an onlooker resembling @image1; @image1's face, hair, skin tone, body or age changing; a third hand, extra arm, more than two hands, extra or missing fingers; extra or missing legs, warped or morphing limbs, blurred or duplicated feet, body distortion; bare feet, barefoot, a single shoe, changing outfit; slow motion, speed ramps, repeated movement loops, spinning camera, aerial shot; plastic or beauty-filtered skin, anime, cartoon or CGI look; on-screen text, captions, subtitles, numbers, readable signage, invented logos or watermark; only the elements explicitly described appear.

MOTION SOURCE — this recipe was reconstructed from a source clip hosted on this platform, which is the reference for the choreography: https://cdn.openclips.ai/community_workflows/3c31cff5-41fd-4c04-9704-df1df83a5657.mp4 (15s, 9:16, the original 'silly cat' dance — conformed to exact 9:16, audio intact) The dance beats written into step 2 were transcribed from that clip frame by frame at 2fps: the springy two-step, the alternating front paws, the knee lifts, the head bobs, the tail counterweight, and the wide-shrug and raised-paw accents. The one-legged spin is an addition, not in the source. IMPORTANT — the clip is NOT passed to the model, and cannot be. Two placements were tested and both fail: inside a step's params it is refused outright ('params carries videoUrl, which seedance-2.0 does not take'), and at step level it is accepted by the API and then silently dropped from the stored row. So step 2 DESCRIBES the choreography instead of copying it, and users get these moves at the model's own timing, not beat-for-beat with the source. If videoUrl is ever accepted on a step, attach the clip above as the motion reference on step 2 and the dance will be copied beat for beat — that is how the preview video on this workflow was actually produced (Seedance 2.0, videoUrl + character + backdrop reference, via a direct generate call rather than a workflow run). AUDIO: the source clip's own soundtrack cannot ride either — audio: 'original' needs Kling's videoUrl, and audioUrls is refused at render. Step 2 uses generateAudio instead, prompted for a silly bouncy beat.

2 steps

SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly — photocopy their exact face, facial features, hairstyle, skin tone, build and gender presentation throughout. Do not beautify, restyle, de-age or alter their identity in any way. Only their scale changes. No other people share their face. @image1 is the subject. Keep their clothes, accessories and jewellery exactly as shown in @image1. Only size changes: they are a few centimetres tall. CLIMB LOCK — CRITICAL: They must climb like a normal person on a vertical cliff. The OPEN PALM is the GROUND they stand on. The SIDE of the giant hand / wrist is the WALL they climb. Chest faces that wall. Both hands reach UP to skin folds above them. Feet push on the palm, then find footholds on the side of the hand. Head up, looking toward the watch. Face and front of the body readable to camera — they are on the CAMERA-FACING side of the hand, never the far/hidden/opposite side. FORBIDDEN (do not do any of these): - sitting, crouching or scooting on their backside along the inner wrist - treating the inner wrist as a floor they crawl across - climbing the far side of the wrist so we only see their back - hanging from the buckle before they have climbed - a watch worn on the inner/palm side of the wrist — the giant watch sits on the OUTER/DORSAL wrist, the normal place a watch is worn CONTINUOUS MOTION REQUIRED: Real, visible physical motion for almost the entire 12 seconds — climb, leap, swing, landing. Never one static pose. SCENE: The subject, a few centimetres tall, starts standing in the centre of an open human palm — a different, full-sized adult hand, not the subject's own. Indoors, soft natural window light from one side. Photoreal. One continuous real photograph, not a composite. The giant wrist wears a fabric-strap watch on the OUTER wrist, high above them at the top of the climb. 0-2s: They stand upright on the centre of the palm (feet on palm skin — this is the ground). They look UP the vertical side of the hand toward the watch on the outer wrist. They start climbing that wall like a rock climber: both hands grab skin folds near the wrist ABOVE their head, feet push off the palm, body upright against the wall, face visible. Real effortful climbing. Not a sit. Not a scoot. 2-4s: Still chest-to-wall, they reach the top of the outer wrist, brace with their feet on the side of the hand, and leap UP to grab the edge of the fabric watch strap with both hands. They swing slightly on impact, then steady. They arrived by climbing the wall, not by crawling along the inner wrist. 4-6s: The giant hand slowly rotates at the wrist, lifting them into the air still gripping the strap. They hold on tightly as the rotation carries them through a wide arc, hair and clothing blown by the motion, expression shifting from tension to excitement. 6-8s: At the peak of the arc, they let go deliberately, pushing off with their legs into a controlled fall back toward the palm below. 8-10s: They land on the palm in a tuck-and-roll to absorb the impact, rolling once across the skin before catching themselves on one knee. 10-12s: They rise, dust off their hands, plant them on their hips, and break into a confident grin, pumping one fist in the air in triumph. SCALE REALISM: Hand skin, wrist folds, strap stitching and fabric weave read at true full size relative to the tiny subject. Match lighting and colour grade. Camera wide enough that the climb up the wall, the leap to the strap, the arc and the landing all stay in frame. Never open on the attached studio still or a grey headshot. No on-screen text, no watermark, no subtitles. AUDIO: Synchronized natural audio — soft ambient room tone, fabric rustling as they climb, a faint metallic clink from the watch strap, breathing and effort under the climb, a triumphant exhale and laugh at the landing. No music, no voiceover, no narration. 9:16. TOTAL DURATION: 12 SECONDS.

A 10-second vertical 9:16 cinematic ballet film. Photoreal, dynamic, cool. One lead only. @image1 IS THE CAT AND OUTRANKS EVERY WORD BELOW. Reproduce the cat in @image1 exactly — their coat colour and every marking in its exact place and shape, fur length and texture, eye colour, nose and paw-pad colour, whisker colour, ear shape and set, build and breed character — identically in every frame. Do not add or remove a marking, do not recolour, do not lighten, do not swap them for a different cat. Wherever this text and the attached photo disagree, follow the image. The cat@image1 is the dancer: standing on their hind legs, keeping their own face and head exactly as shown. Elegant and charming throughout, never uncanny, never a human face. WARDROBE: a WHITE ballet dress — romantic tutu, puffed sleeves, pale blue sash, white ballet slippers on the forepaws. The garment is fixed in design, cut, proportions and colour; only its drape and fit adapt to this cat's own body. Nothing else worn. STAGE: a dark theatre, painted burgundy-and-cream baroque backdrop, scuffed black dance floor, warm spotlights. No other people, no second dancer, no audience in frame. CAMERA: handheld follow, slightly low, full body in frame. Dynamic — the cat@image1 turns, opens their forelimbs to second position, executes a pirouette and a leap. AUDIO: beautiful orchestral ballet — strings and a soaring waltz. No lyrics, no voiceover. [0-3s] Already dancing: the cat@image1 in the white ballet dress, forelimbs open, bouncing on the black floor under the stage lights. [3-7s] Faster: a spin, the tutu flaring out, a jeté across the floor, cool and dynamic. [7-10s] Finale pose: one forelimb raised high, looking straight to camera, freeze. Hold. NEGATIVE: a human woman, a person, extra dancers, a second cat, a different cat, a human face on the cat, human hands or fingers, added or altered markings, changed coat colour, a coloured tutu, on-screen text, captions, credits, logos, watermark, horror, uncanny anatomy.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT cropped in extreme macro with its most recognisable part clearly visible, and it defines the object's colour, material, surface finish, and the look of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE SIGNATURE — read this before the timeline: THE SIGNATURE is whatever part of THE OBJECT a person would recognise it by. If THE OBJECT has a face, that is its signature. If it does not, its signature is its most distinctive feature — a label, a logo, an opening, a handle, a cap, a pattern, a moulded detail, a corner, whatever makes it that object and not some other object. Wherever this film refers to THE SIGNATURE, use whatever that is on @image1. HOW IT MELTS — the most important rule: every part of THE OBJECT stays joined to every other part for the entire film. It changes only by softening and flowing, the way warm honey and thick syrup behave. Its surface is one continuous unbroken skin at every moment, and its silhouette is always a single closed outline that sags, rounds and slumps. At any instant the shape is simply a softer, rounder version of the instant before — the change is always gradual and always connected. Whatever THE OBJECT is made of in @image1 — soft or rigid, glass, metal, plastic, card or fabric — under this heat it behaves as one thick warm syrup: it holds together and it flows, staying whole as it goes. Summary: a cinematic macro ASMR film in which THE OBJECT melts down completely, the camera moving through five distinct shots — extreme macro, a fast pull back to the whole figure, an orbit around it as it collapses, a punch back in to THE SIGNATURE, and a crane up over the finished pool. Timeline: 0–2s — Extreme macro, the framing of @image1. The camera creeps slowly closer still. Light refracts through THE OBJECT's material and a bright specular highlight slides across its surface as a wet sheen spreads over it. The first beads swell and start to run. 2–4s — The camera pulls back fast and smoothly in one continuous move, opening out from macro to reveal the WHOLE of THE OBJECT standing in frame. It is already going: its outline is softening, its material running down its sides and pooling around its base. 4–6s — The camera orbits steadily around THE OBJECT, holding it centred, while it collapses. Its shape sags and folds in on itself, its sides slump outward, and the molten material spreads across the surface in a widening glossy pool that the camera sweeps past. 6–8s — The camera punches back in fast, straight to what remains of THE SIGNATURE, filling the frame with it. It is soft now, rounding and sliding, and a thick runnel of material crosses it and runs off the lower edge. 8–10s — The camera cranes up and over, rising to look down on the pool from above as the last of the shape sinks into it. Rings spread out from the centre, slow and flatten, and the pool holds glossy and still at the final frame, the object's colour glowing through it and the faint outline of its shape readable in the surface. Notes: THE OBJECT keeps exactly the colour, translucency and surface finish it has in @image1 for the whole film, and everything that runs and pools is that same material in that same colour, holding the same hue and the same darkness throughout. The material behaves as one thick viscous liquid: slow, heavy and continuous, and volume is conserved — the pool grows by as much as the object loses. THE OBJECT melts down completely over the ten seconds, and THE SIGNATURE is the last part of it to go. The surface carries whatever real fine detail the material of @image1 actually has the whole way — suspended bubbles if it is translucent, otherwise its own grain, weave, moulding, seams or print — together with a faintly uneven sheen and micro-texture visible at macro magnification. The light stays one soft key from the upper left with a weak fill from the right for the whole film, and specular highlights slide across the material as the camera moves. Each of the five camera moves is smooth and continuous within its own section and the film runs as one unbroken take with no cuts. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — the faint wet creep of the sheen spreading, a fat clean drip as the first bead runs, a low heavy sagging tone under the collapse, a soft rush of air as the camera moves, thick wet slumping as the shape gives way, and the quiet settle of the rings flattening out.

2 steps

A 12-second vertical 9:16 playful music-video. One continuous shot. Photoreal. @image1 is THIS cat: brown-grey tabby, white chest and paws, green-gold eyes, white muzzle. Lock that exact cat. Do not recast as a different animal or a person. The cat stands upright on hind legs in the middle of the room and DANCES like a toddler: bouncing, hip wiggles, little arms/paws pumping, head-banging, spinning in place, full of attitude. Cute, not horror, not human-faced. ROOM (CHANGED): not a white fireplace living room. A warm mid-century apartment — olive sofa, plants, wood floor, a window with afternoon light, a record player, no TV cartoon. Only the room is different; the dance energy stays. CAMERA: locked, slightly low, full body of the cat in frame. AUDIO: upbeat playful pop-funk instrumental that matches the bounce. No lyrics, no voiceover. [0-3s] Already dancing: the tabby on hind legs, bouncing, paws pumping. [3-7s] Sunglasses-attitude beat: bigger hip moves, a spin, tail for balance. [7-12s] Faster bounce, then a freeze pose looking at camera. Hold. End. NEGATIVE: a human child, a person, extra animals, the original fireplace, cartoon on a TV, on-screen text, logos, horror, uncanny human face on the cat.

Photoreal cinematic vertical dance clip, authentic handheld phone footage energy, natural daylight, realistic skin and hair — a synchronized trio dance trend, three real people side by side in a covered open-air concrete walkway with green foliage and a chain-link fence behind, upbeat and playful. THREE DANCERS — IDENTITY LOCK: three real, distinct people in a row facing camera. @image1 CENTER — exactly the person in @image1 (face, hair, identity, own outfit from the reference). @image2 LEFT — exactly the person in @image2. @image3 RIGHT — exactly the person in @image3. Preserve each one's identity, features, skin tone, hairline, hairstyle and build identically in every frame; never blend, swap or morph the three faces into each other; the attached images outrank any words. No fourth person. They/them throughout. HAND LOCK: each dancer has exactly two hands with five well-formed fingers per hand; hands stay clean and correct through every move; the three move in tight SYNC, mirroring the same choreography at the same time. BEATS (feet always planted cleanly on the ground): 0-2s three in a row, small bounce to the beat, then in unison raise both hands up near their faces. 2-4s hands sweep out to the sides as shoulders sway left then right, a light step-touch. 4-6s cross forearms in front of the chest, flick both hands open together, a small unison step to the right. 6-8s hands playfully frame the face, heads tilt in sync, a bounce. 8-10s arms pump up in rhythm, hips sway, all three mirrored exactly. 10-12s a smooth quarter turn in unison and back to face the camera, hands rolling, smiling. 12-15s big synchronized final pose together (hands up, then one hand on the hip), hold it, laughing, confident, looking to lens. CAMERA: a single steady handheld phone shot framing the three from head to mid-thigh, slight natural micro-movement, vertical, no cuts, no zoom, no impossible move; everyone stays clearly in frame. Realistic body physics, natural weight and balance, believable synchronized movement; ONE continuous take, no abrupt cut to another scene. SOUND: an upbeat contemporary dance-trend music bed driving the rhythm plus light outdoor ambience; no spoken dialogue, no invented language. NEGATIVE: any of the three faces changing, blending, swapping or morphing into another; a fourth person appearing; a third hand, extra arm, fused or morphing hands, extra or missing fingers; feet sliding, skating or not touching the ground, warped or morphing legs, gait or limb glitching during the dance; the dancers falling out of sync into jittery glitching; describing or changing their outfits away from the references; on-screen text, captions, numbers or watermark; plastic or beauty-filtered skin; a scene cutting off mid-action or jumping to an unrelated scene; any dancer vanishing, dissolving, fading or teleporting — everyone stays physically in frame.

A baby avatar performs a professional popping-and-locking routine in a studio. Music only, loud. See the video step for the full prompt.

Live-action photoreal footage in the grammar of a hand-held front-facing phone camera: real skin, real hair physics, natural indoor daylight, a constant small hand drift and breathing sway, shallow phone-lens depth. Not illustrated, not rendered, not stylised. @image1 is an absolute lock for the opening appearance — face, body and unstyled hair are taken from it exactly, with no drift or reinterpretation. @image2 is an absolute lock for the closing appearance — face, body and finished hair are taken from it exactly. @image1 and @image2 are the same person; the only thing that changes between them is the hair. The subject holds the phone at arm's length, looking straight down the lens with a flat, faintly unimpressed expression, mouthing along to the track, giving a small tilt of the head. Then their eyes flick off to one side and back, lips still moving with the words, shoulders loose, the unstyled lengths hanging heavily and barely moving with them. Then they lift one hand toward the lens and sweep it fast across the frame — the whole image smears into motion blur as the camera whips with it. Then the blur clears on the same person transformed, hair now finished and full, their head lifting into a bright open smile. Then they turn their head sharply one way and back so the styled lengths swing out wide and settle, fingers combing back through them. Then they push the hair back off one shoulder and lean slightly toward the lens, holding the smile while the lengths fall back into shape. On-screen text: the words new hair? in small lowercase serif, low and centred, present from the first frame to the last and unchanged across the transition. Audio: one upbeat pop track running unbroken from the first frame to the last — a bright four-on-the-floor kick, a bouncy synth-bass hook, handclaps on the offbeat and a bright plucked synth riff carrying the hook, confident and celebratory at a steady dance tempo. It plays quieter and slightly muffled across the opening, then opens up full and bright the instant the blur clears, and the whip lands square on a beat. Continuous hand-held motion throughout — nothing in frame is ever fully frozen. The single whip blur is the only transition; no other cut, wipe or dissolve. The subject mouths along to the track; no spoken dialogue, no voice-over, no singing voice and no lyrics — the track is instrumental. No added captions, titles, logos, watermarks or interface elements beyond the words above. No second person in frame. No cel shading, no illustration, no cartoon, no 3D render, no beauty filter, no skin smoothing.

4 steps

@image1, @image2 and @image3 are three wardrobe references of the same person. Face, body proportions, hair and identity are taken from them exactly and held without drift for the entire take. Each outfit is reproduced exactly as shown in its reference, down to footwear and accessories — no substitutions, no invented garments. Ultra-realistic throughout: real fabric, leather, suede, fur and skin behaviour, cinematic autumn colour grading, natural film grain, premium fashion-campaign realism. A fixed 90° overhead camera, locked off for the whole take. The subject lies on a luxurious autumn-toned Persian-inspired rug over walnut flooring, subtle upscale apartment furniture around the edges of frame, warm late-afternoon sunlight casting realistic shadows. A realistic wooden ceiling fan rotates continuously directly above them, hanging between the camera and the subject, its blades long and wide enough that each passing blade sweeps across their entire body and briefly occludes it. The fan is the only transition device. Wearing the outfit from @image1, they lie back on the rug, casually pick up a remote and turn their gaze up into the overhead lens. As a fan blade physically passes over their body, seamlessly reveal the outfit from @image2, the change landing under the blade itself, complete the instant the blade clears them, never a dissolve, never a fade, never a change in open frame. They settle into a new editorial pose, gaze still up into the lens. As the next blade physically passes over their body, seamlessly reveal the outfit from @image3, again changing under the blade and complete the instant it clears them. They adjust into another editorial pose, gaze still up into the lens. They hold that final pose, only the slow rise and fall of breathing and the faintest settling of fabric, while the fan keeps rotating overhead. Strictly no cuts, no camera movement, no zooms, no angle changes, no morphing, no identity drift, no outfit glitches, no warped hands, no duplicated limbs, no disappearing accessories, no text, no logos, no watermark.

4 steps1095.9K

@image1 is an absolute character lock: face, body, hair and the outfit are taken from it exactly, with no drift or reinterpretation in any shot. Filmed on a phone propped in place at a fixed angle, phone-vlog framing, with the pace carried by quick jump cuts between takes rather than by camera movement. Nobody ever reaches toward the camera. Photographic realism throughout: natural skin texture with visible pores and flyaway hair, true-to-life colour, soft even daylight, shallow natural depth of field. A fast-paced influencer-style "Get Ready With Me" video of someone preparing for a lunch hangout with their friends, focusing only on outfits and accessories. They turn to the camera, energetic, wearing something casual, and say, "GRWM for lunch with my friends—let's pick a cute outfit!" Quick jump cuts at a full-length mirror as they swap out of the casual outfit, with a stylish transition between the looks. They settle into the outfit from @image1 and add its finishing accessories, saying, "Okay this is giving effortless but cute!" They step into the shoes, settle the bag, and check themselves in the mirror with confident poses. They pick up their phone, smile at the camera, and say, "Alright I'm ready—see you at lunch!" Upbeat music, snappy edits, and strong influencer vlog energy throughout. Do not render: illustration, 3D render, cel shading, anime or cartoon styling, airbrushed or plastic skin, beauty-filter smoothing, on-screen text, subtitles, captions, watermarks or logos.

2 steps20712.8K

@image1 is the BOTTLE. Photocopy this champagne exactly: same glass, foil, neck badge and label — every word exactly as printed in @image1. NEVER a can. NEVER a pull-tab. 12-second 9:16 PREMIUM CHAMPAGNE commercial. Luxury rose-gold studio — not soda red. Photoreal. Ice, condensation, champagne liquid matching the bottle. Product-only. No humans. No on-screen captions except the bottle’s own label. 0–1.5s ICE IMPACT: Crystal ice exploding through glossy ROSE-GOLD. Slow-mo droplets. 1.5–3.0s BOTTLE REVEAL: Chilled @image1 bottle emerges through ice, rotating. Label readable. 3.0–4.5s FRESH SPLASH: Wave of the bottle's own champagne around it. Camera through splash. 4.5–6.0s OPEN & FIZZ: Foil and cork exactly as on @image1. Carbonation burst, mist. Not a soda can. 6.0–7.5s LIQUID MOTION: Sculptural wave of the bottle's own champagne against the rose-gold studio. Ice cubes. 7.5–9.0s BOTTLE CHASE: Multiple copies of THIS bottle at different depths in rose-gold. 9.0–10.5s HERO FORMATION: Three bottles converge. One dominant. Heavy condensation. 10.5–12.0s FINAL HERO: Ice-kissed @image1, suspended droplets. Deep rose-gold, rim light, slow push-in. Designed hold. Audio: ice, pour, fizz, luxury sting. No voiceover. No lyrics.

MODEL: Seedance 2.5 — use this model specifically. Do NOT use MiniMax or any other model for this generation. FORMAT: Vertical video, 9:16 aspect ratio. DURATION: 12 seconds. AUDIO: Generate synchronized natural audio for this scene — soft ambient fabric rustling, a held breath as the subject hides, a loud metallic jingle when the keys are pulled out, then a relieved exhale and a soft triumphant exclamation at the end. No music, no voiceover, no narration. ASSET MAP: @image1 — the subject. SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. Exact face, facial features, hairstyle, skin tone, build and gender presentation stay unchanged — only their scale changes. Do not beautify, restyle or alter identity. Photocopy @image1. Face, hair, skin and outfit exactly as in @image1 stay. POCKET READ — MUST BE OBVIOUS FROM FRAME 1: This is a real jeans FRONT POCKET on blue denim jeans worn at the hip of a different, full-sized adult (never the subject’s face). A first-time viewer must instantly recognise it as a clothing pocket — not a fabric cave, not a bag, not a tunnel of cloth. Camera sits OUTSIDE the garment, slightly above hip height, looking down and in through the pocket opening. In every frame keep visible at once: - the jeans: waistband, a belt loop, bartack stitching, rivet, denim weave - the pocket as a 3D pouch sewn onto the jeans, with a clear U-shaped opening and a folded pocket-edge hem - the tiny subject inside that pouch, a few centimetres tall Do not crop so tight that only fabric walls remain. If the pocket silhouette would leave the frame, pull the camera back. CONTINUOUS MOTION REQUIRED: Real, visible physical motion for almost the entire 12 seconds — a clear sequence of distinct actions (settle, alert, hide, reaction, climb, look out), never one static pose held for seconds at a time. SCENE: The subject, shrunk to a few centimeters tall, is inside that jeans pocket. A folded receipt and a set of keys rest on the fabric floor nearby. The pocket opening is above them. Indoors, soft natural window light from one side. The wearer of the jeans is a different full-sized adult — never give them the subject’s face. 0-2s: Wide enough to read the jeans pocket on the hip. Tiny subject sits comfortably inside the pocket bag, arranging the folded receipt like a small mat beneath them, settled and at ease. Waistband and belt loop still in frame. 2-4s: Bright light suddenly widens above as the pocket flap is pulled open — they look up sharply, alert, rising to their feet. The U-shaped pocket opening stays readable. 4-6s: A pair of giant fingers (the wearer’s, not the subject) reach down into the pocket, searching side to side. The subject scrambles and presses themselves flat into a fold of fabric in the shadowed corner, perfectly still, visibly holding their breath. 6-8s: The fingers close around the keys resting just beside the subject’s hiding spot and lift them straight up and out of the pocket — the keys jingle loudly, a gust of motion ruffling the subject’s hair and clothing as they pass close by. Keys and fingers are enormous next to them. 8-10s: The fingers withdraw and the flap falls closed behind them, light dimming back down. The subject peeks out from the fold, relieved, then breaks into motion, climbing quickly up the inner fabric wall toward the pocket’s rim. Pocket silhouette still in frame. 10-12s: They reach the rim and perch on the edge, silhouetted against the bright opening, looking out at the towering room beyond, then turn back toward camera and give a small triumphant fist pump, grinning. Waistband still readable. SCALE REALISM: Stitching, denim weave, keys and fingers are true size next to the tiny subject. Match lighting so it reads as one photograph, not a composite. No on-screen text, no watermark, no subtitles.

MODEL: Seedance 2.5 — use this model specifically. Do NOT use MiniMax or any other model for this generation. FORMAT: Vertical video, 9:16 aspect ratio. DURATION: 8 seconds. AUDIO: Generate synchronized natural audio for this scene — soft ambient room tone, a light tap or brush sound on each landing on skin, the subject’s own breathing, small gasps and a genuine laugh at the end. No music, no voiceover, no narration. ASSET MAP: @image1 — the subject. SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. If it is a person: their exact face, facial features, hairstyle, skin tone, build and gender presentation stay unchanged — only their scale changes. If it is a product/object: its exact shape, color, materials, proportions and any label or logo text stay exactly as shown, not regenerated — only its scale changes. Do not beautify, restyle or alter identity or branding in any way. CONTINUOUS MOTION REQUIRED: This shot must show real, visible physical motion for almost its entire 8 seconds — a fast sequence of distinct actions, never one static pose held for seconds at a time. SCENE: The subject, shrunk to a few centimeters tall, stands near the wrist of an open human palm — a different, full-sized adult hand, not the subject’s own — held at roughly waist height, indoors with soft natural window light from one side. 0-1s: Subject crouches at the base of the palm, looking up at the four fingers laid out ahead like stepping stones, visibly bracing to move. 1-2.5s: The nearest finger slowly curls down closer to palm height, and the subject leaps up onto its fingertip in one quick, athletic jump, arms out for balance. 2.5-4s: Without pausing, they leap again to the next fingertip — a faster, more confident jump this time, hair or clothing flicking with the motion. 4-5.5s: A third leap to the next fingertip — they land slightly off-balance, wobble, arms windmilling, and catch themselves just in time, a flash of surprise on their face. 5.5-8s: They plant their feet and launch into one final big leap off the last finger, arcing through the air. The giant hand moves quickly underneath and cups shut around them, catching them safely. The subject throws both arms up inside the curled hand in triumph, laughing. SCALE REALISM: The palm’s skin texture, lines and fingerprint ridges must read at true full size relative to the tiny subject — every texture detail on the hand should look enormous next to them. Match lighting and color grade between the subject and the hand throughout so the whole shot reads as one real photograph, not a composite. Keep the camera framing wide enough that all three jumps and the final catch stay clearly visible in frame. No on-screen text, no watermark, no subtitles.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT standing on a thick sheet of clear glass, seen from a very low camera right down at the level of the glass, and it defines the object's colour, material, surface finish, the glass, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE SIGNATURE — read this before the timeline: THE SIGNATURE is whatever part of THE OBJECT a person would recognise it by. If THE OBJECT has a face, that is its signature. If it does not, its signature is its most distinctive feature — a label, a logo, an opening, a handle, a cap, a pattern, a moulded detail, a corner, whatever makes it that object and not some other object. Wherever this film refers to THE SIGNATURE, use whatever that is on @image1. THE CAMERA — never leaves this position: it stays right down at the level of the glass sheet for the entire film, almost touching it, looking along and slightly up across the glass. Everything happens on the glass in front of the lens, and the spreading material comes toward the camera across it. HOW IT MELTS — the most important rule: every part of THE OBJECT stays joined to every other part for the entire film. It changes only by softening and flowing, the way warm honey and thick syrup behave. Its surface is one continuous unbroken skin at every moment, and its silhouette is always a single closed outline that sags, rounds and spreads. At any instant the shape is simply a softer, rounder version of the instant before — the change is always gradual and always connected. Whatever THE OBJECT is made of in @image1 — soft or rigid, glass, metal, plastic, card or fabric — under this heat it behaves as one thick warm syrup: it holds together and it flows, staying whole as it goes. Summary: an ASMR film shot from glass level, in which THE OBJECT melts down onto the glass and its molten material spreads across the glass straight toward the lens until it fills the frame. Timeline: 0–3s — The framing of @image1. The camera creeps slowly forward along the glass toward THE OBJECT. Where it presses on the glass a wet halo appears and begins to widen, and the light coming through the object makes that halo glow. 3–6s — THE OBJECT settles downward. Its body rounds and sinks and its material runs out across the glass in a widening glossy sheet, brightest and most luminous at its thin advancing edge. The camera holds low as that edge comes toward it across the glass. 6–8s — More of THE OBJECT sinks. THE SIGNATURE, still readable, comes down with the body toward the glass, growing larger as it descends toward the lens. 8–10s — THE SIGNATURE meets the glass, flattens gently and spreads into the sheet. The material floods forward and fills the frame, and the final frame is a still, glossy field of THE OBJECT's own colour, glowing where its material lets light through, with one soft highlight lying across it. Notes: THE OBJECT keeps exactly the colour, translucency and surface finish it has in @image1, and everything that spreads across the glass is that same material in that same colour, holding the same hue and the same darkness throughout. The material behaves as one thick viscous liquid: slow, heavy and continuous, and volume is conserved — the sheet on the glass grows by as much as the body loses. THE OBJECT melts down completely over the ten seconds and THE SIGNATURE is the last part of it to go. The light stays above and behind for the whole film so the material is always lit from the far side. The glass keeps its faint reflection, its visible near edge and its micro-texture. The camera moves slowly and smoothly and the film runs as one unbroken take with no cuts. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — a soft wet creep as the halo widens on the glass, a low heavy settle as the shape sinks, the faint slide of soft material moving on glass, a thick wet spread as the sheet floods toward the lens, and one quiet settle as the surface stills.

2 steps

A 10-second dance video, vertical 9:16, photorealistic, one continuous shot. THE PET: exactly the animal in the attached photo. Keep its fur colour and pattern, every marking in the same place, its coat length, face markings, nose colour, eye colour and build. The photo outranks this text - if they disagree, follow the photo. It wears a black bandana over its head with the ears through and a thin gold chain. Nothing else. It dances upright on its hind legs, centred, full body in frame, staying on one spot. THE DANCE - a C-walk, flowing without a single pause. The hind paws stay close together and swivel: heels together with toes splayed out, then toes twisting inward as the heels push apart, twice a second, over and over. The knees bend deep and knock in and out. The body bounces, the shoulders roll, the head bobs on the beat. The front paws rest on its hips with the elbows flared wide, pumping on the beat, never leaving the hips. The dance is already running on the first frame - no still opening. SETTING: a street corner at night, one sodium streetlight overhead, wet asphalt, a chain-link fence and a low wall, a classic lowrider parked behind. Two cats of a clearly different colour sit on the wall, nodding along, never dancing. Camera locked and static, slightly low. THE FACE: deadpan the whole time, straight into the lens. Never smiles, never opens its mouth. ENDING at 9s: one front paw thrusts straight at the lens, everything stops dead, the music cuts out. Silence and stillness for the last second. AUDIO: an upbeat hip-hop beat, no vocals, no meowing. NEGATIVE: no humans, no text, no logos, no extra limbs, no distorted paws, no fur colour or pattern different from the photo, no smiling, no open mouth, no paws leaving the hips, no walking or travelling, no pausing, no camera motion, no cuts, no fade.

Subject: one figure. @image1, @image2 and @image3 are three wardrobe references of the SAME figure — face, body, proportions and surface finish are identical across all three and must not drift, be recast or reinterpreted in any shot. Hands in long matte-black gloves operate from off-frame and dress the figure remotely, never touching them. Shot 1: the figure @image1 stands centered, full-body, in their starting state. The outfit from @image1 flies in and physically dresses them. The figure @image1 strikes an editorial pose. One sharp gloved swipe pulls the outfit off and it falls to the floor. Shot 2: the outfit from @image2 flies in and dresses the figure @image2. The figure @image2 takes a strong pose. Both gloved hands pull the outfit away and the garments fall beside the first look. Shot 3: the outfit from @image3 assembles onto the figure @image3 layer by layer. Precise gloved gestures remotely tailor the waist, shoulders, lapels and cuffs with realistic fabric tension. Shot 4: the figure @image3 holds a powerful final fashion pose, surrounded by the discarded clothes. Shot 5: a gloved hand reaches forward. The figure @image3 physically takes the hand and walks confidently toward the fixed camera until their outermost layer naturally covers the lens and the frame goes to black. Scene: black seamless studio. Lighting and color: cinematic rim lighting, premium coffee palette with a burnt-orange accent. Camera: one locked frontal camera, no camera movement in any shot. Visual style: ultra-photorealistic premium fashion film. Realistic silk, leather, cashmere and wool. Realistic cloth physics, gravity and inertia. Seamless continuity between shots. Constraints: no magic, no glow, no portals, no particles, no morphing. Avoid generating any text or subtitles. Do not generate a logo. Do not generate a watermark.

4 steps1265.8K

@image1 is the absolute lock for the product: silhouette, proportions, materials, finish, colours and hardware are taken from it exactly in every shot, with no redesign, no recolouring and no invented lettering or logo. @image2 is the absolute character lock: the large portrait on it is the face, and the face in every shot matches that portrait exactly — same features, same proportions, same skin — with body, hair and garment from @image2 as well and no drift in any shot. @image3 is the storyboard and is followed exactly — the same shot order, the same framing, the same staging, the same grounds and the same colour. High-end commercial cinematography throughout: ultra-realistic, premium colour grading, true materials, accurate reflections, real optical shallow depth of field, smooth transitions between shots. Motion is slow and continuous. Each shot holds one action and one camera action, evenly weighted, and nothing moves in reverse. Shot 1 — the small points of light drift slowly through the air around the product@image1 and the fine threads behind it glint as they catch the light. The camera pushes in slowly on it. Shot 2 — the product@image1 turns a few degrees on its bed so the highlight travels the length of its surface. The camera drifts slowly along it. Shot 3 — the highlight sweeps across the front detail of the product@image1 and settles. The camera pushes in slowly. Shot 4 — the part of the product@image1 that opens, fastens or adjusts moves through its travel once, smoothly and completely, in the way its own design calls for. The camera drifts slowly across it. Shot 5 — the subject@image2 holds the product@image1 at chest height and turns it a little toward the lens, then lifts their eyes to the camera, the depth behind them sliding past out of focus. The camera rises slowly from the product to their face. Shot 6 — the product@image1 stands still and square while the rim light strengthens down its edge, the space above it staying clear and empty. The camera pushes in slowly and settles. Keep the product fully in frame and in sharp focus in every shot that features it, and keep it identical to @image1 throughout. Avoid generating any text or subtitles. Do not generate a logo. Do not generate a watermark. Do not generate any lettering or marking on the product that is not already present in @image1. No extra people. No handheld shake, no whip pans, no zoom snaps, no speed ramps, no lens flare. No illustration, no stylization, no painterly rendering, no 3D-render look.

4 steps19214.4K