Sign up and save up to 50% on a yearly plan.Sign up free →Black Friday: up to 50% off yearly plans.See the deal →
Back to the gallery
EN
Pricing, save up to 50% on yearly plans, Black Friday: up to 50% off yearly plans
Back to the gallery
Seedance 2.515s · 16:9

Drag the clip sideways

Up next
Inspired by @sopersoneon X

@image1 is an absolute character lock. Face, body, hair, garment, materials and colours are taken from it exactly and hold without drift or reinterpretation for the entire shot. Do not restyle, re-age, re-cast or re-dress the subject. LOOK: photorealistic live action, shot on a long lens from across a forecourt — the plain unglamorous look of a phone clip of a real person, not a commercial. Hard midday sun overhead, strong directional daylight with open shade under the vehicle, deep contrast, real tarmac glare, accurate contact shadows, natural skin with visible pores and real sweat sheen, slight lens compression, fine sensor grain. Ordinary unposed body mechanics with small weight shifts and hesitations between actions. Clothing and hair carry real fabric and fibre weight on every turn. This grade governs the shot and overrides the flat neutral lighting of the reference sheet. One continuous locked-off take. The camera is fixed on a tripod at chest height and never pans, tilts, zooms, pushes or tracks — the framing is identical in the first and last frame. A pale vertical bollard stands in the near foreground at the left edge, partly masking that side of the frame throughout, so the shot reads as observed from a distance rather than staged. Medium-wide: the subject and the side of the vehicle fill the frame, ground to just above roof height. Setting is a fuel station forecourt — a large dark SUV parked alongside a pump, kerb and low planter behind it, mature trees, utility poles and distant traffic signals beyond. The subject stands between the pump and the vehicle's rear flank. The subject holds the fuel nozzle in one hand throughout, except where stated. The subject is in motion in every beat; nothing in this shot ever holds a frozen pose. Beats run in this order and each takes a comparable share of the shot: They shift their weight at the pump beside the vehicle, head dipping toward the nozzle in their hand, fingers adjusting their grip on it. They rotate toward the vehicle and extend the free hand to the filler panel, torso angling in toward the bodywork. They work at the panel with that hand, head lowered toward it, the nozzle still held clear in the other hand. They rotate their head and shoulders away from the vehicle, chin lifting, and speak a few words. Both arms open outward into a questioning shrug, palms turning up and away from the body, shoulders rising, still speaking. They rotate back, crouch low beside the rear wheel and reach toward the ground, then straighten and step in toward the vehicle as hair and clothing swing with the turn. Audio: forecourt ambience only — distant road traffic, faint pump hum, light wind. The subject's speech is indistinct at this distance. No scripted dialogue, no music, no voiceover. Exclusions: no watermark, logo, on-screen text, captions or timecode. No cuts, transitions or jump cuts. No slow motion or speed ramping. Nobody else enters frame. No beauty retouching, skin smoothing or body reshaping. No lens flare, no night, no rain, no studio lighting.

1 step166103.6K
Seedance 2.514s · 9:16
Katarina

VERTICAL 9:16 15s. The person in @image1 takes a SELFIE of THEMSELVES. They hold the phone. NO second person. NO held hands. NO POV partner-arm at the bottom of frame. 0.5x handheld selfie, they are the only person in the selfie (crowds may exist behind them in Tokyo and NYC). Photocopy FACE and hair from @image1 in every cut, exactly as shown, with any jewellery exactly as in @image1. Preserve their gender presentation exactly as shown. Use they / their / them only. Outfit and place come from each look line below; each outfit is styled to suit their gender presentation as shown in @image1. They MOVE. Never a frozen JPEG. ENERGY: travel TikTok influencer, EXCITED about each place. Bigger reactions than a polite smile: gasp, laugh, “oh my god” face, look at the landmark then whip back to the lens. Still not identical wide teeth every cut — different hype each city. TRANSITION (copy the classic 0.5 travel vlog): last ~0.4s of every city they DROP the phone — arm swinging down, frame falls toward their chest. HARD CUT. Next city STARTS already HIGH (lots of sky / forehead, they sit low in frame) and they LOWER the phone into a normal selfie over ~0.4s. Hand-down → hand-up-coming-down. Then they LIVE in the frame, excited. Then dip again. LOOK 1: Singapore Supertrees, rust-red satin. Excited gasp, look at the trees, back to lens. LOOK 2: Petronas, butter-yellow. Laugh, glance at the towers, hyped. LOOK 3: Bali rice terraces, white eyelet. Softer wonder then a big “this is insane” smile. LOOK 4: Tokyo night crossing, leather + silver. Neon hype, laugh, look at the scramble. LOOK 5: Times Square, camel coat. Talk to camera, excited, cab behind. LOOK 6: Copacabana, emerald wrap. Playful, look at the hill, laugh. LOOK 7: Cancun, coral crochet. Warm finish, bigger smile, hold. No dip out. 0.0-2.0 LOOK 1 hold then dip 2.0-4.0 LOOK 2 start high, lower, hype, dip 4.0-6.0 LOOK 3 start high, wonder, dip 6.0-8.0 LOOK 4 start high, neon laugh, dip 8.0-11.0 LOOK 5 start high, NYC talk, dip 11.0-13.0 LOOK 6 start high, Rio laugh, dip 13.0-15.0 LOOK 7 start high, Cancun smile, hold Same person every cut. No on-screen text. No logos. No second face in the selfie.

1 step
Seedance 2.515s · 9:16
Anthem in the Stands

Generate a live race-day broadcast where the camera finds you singing along in the grandstand, moved to tears.

2 steps
Seedance 2.510s · 9:16
lansenai

16:9 30 seconds. Photocopy @image1 exactly: face, hair and skin tone exactly as shown. Wardrobe: a long, distressed hooded coat that moves in the wind, with gloves and boots, fitted to them as @image1 presents. Do not restyle hair. Do not put them in armor. Do not beautify. No other people. Preserve their gender presentation exactly as shown. Use they / their / them only. World: an empty pale desert — huge flat sand, pale grey-blue sky, haze at the horizon. Thin dust, wind in the long hem. ENERGY LANGUAGE: replace every black ink / black smoke / 黑墨 with PINK ink-smoke. Rose-pink calligraphy strokes, magenta fly-white brush, rose-gold hairline cracks, pink mist. Not black. Not ordinary game VFX. Pink Chinese ink invading 3D space. Dark-gold cores may stay as rose-gold. They move light, quiet, almost careless. Tiny gestures trigger huge pink-ink reactions. No weapons. CAMERA: never a game-skill front pose. Low rear-side follow, FPV, orbit, whip, 3/4 profile. Strong motion blur. Time ramps. 0–2.5s: 墨步 / pink step Start already walking, right-rear low 24mm, head slightly down, wind in the long hem. 0.7s their right foot taps the sand — a pink ink ring races across the ground, one-frame pink shock. 1.0–2.5s their body stretches into a long pink brush-stroke, three zigzag dashes, camera skims the sand. 2.5–6s: 水镜 They stop hard. Time ramp. Casual right hand up. Thin glass-like water sheets in the air. Camera flies between them. They close their fist. Sheets fold and crush a stone pillar into spiral gravel. Pink ink flies off the shards. Heavy impact: pink shock-frame, camera dip. 6–9s: 墨掌 Spin. 3/4 side. Half-palm push. Pink ink collapses into a tiny core then BLOWS into a huge pink-gold palm-pressure. Camera flies backward through it. Hits the sand — circular crater, dust, pink splash. No fire. 9–12.5s: 流墨回身 They lean back almost to the ground, toe-tap, low spin, the long hem becomes a pink-ink arc. Light kick. A thin pink spatial cut flies; three distant pillars split after a delay. 12.5–16s: 水墨坠 Leap. Camera under their boots. Water droplets rise. Pink ink dots orbit. At the apex they press their palm down. World goes quiet. Then the ground collapses — rose-gold ring cracks, PINK ink erupts into a circular ink-landscape shock. 16–20s: 墨莲 Hover 30cm off the sand. Orbit 270°. Pink mist, pink brush-strokes, rose-gold threads, giant pink-ink lotus petals painted in the air. Stones float. 20–23.5s: 五行 Calm glance. They vanish. FPV chase: water around them, then wood-like pink branches, then burnt-paper rose-gold “fire”, then geometric rose-gold cracks, then sand+pink ink vortex. Still ink language, not rainbow game VFX. 23.5–30s: 墨界 Dive. Freeze 0.5m above ground. One finger down. Full-screen pink-ink impact frame, negative, flash, radial shake. Three rings: pink ink, water, rose-gold — merge into a giant pink-gold shockwave. Hundreds of meters of sand become a living pink ink landscape. Giant pink brush-strokes shoot to the sky. Then everything sucks back into them. Quiet. They walk on, same as the open, a thin PINK trail behind their boot. Wind in their hair. Cut to black. No logos, no UI, no on-screen text. Same face every frame.

1 step10
Seedance 2.530s · 16:9
Inspired by @HeyAmit_on X

Ultra-photorealistic live-action commercial. Natural midday summer sunlight, warm low sun flaring in from the left, shallow depth of field, real skin texture and real fabric weight, subtle handheld float on the wider shots, clean modern colour grade with no stylisation. @image1, @image2 and @image3 are an ABSOLUTE CHARACTER LOCK for IDENTITY ONLY — the first, second and third character respectively. Face shape, eyes, brows, nose, lips, jawline, ears, hairline, hair, skin tone and micro-asymmetry are taken from them exactly, with no drift, no reinterpretation and no blending between them, in every shot of the film. TAKE NOTHING ELSE FROM THOSE IMAGES: ignore the clothing, footwear, accessories, background and styling in them entirely. @image4 is the storyboard and is an ABSOLUTE LOCK for wardrobe and staging: the clothing each character wears is taken from the storyboard and from nowhere else, and the shot order, framing, poses and camera height are followed exactly as drawn, with nothing added, removed or restyled. Everyone stays in the summer tee-and-shorts the storyboard shows — no coats, jackets, long sleeves, trousers, dresses or skirts at any point. The product is one compact cylindrical portable speaker in a soft off-white housing with a fine woven fabric grille and a slim metal band, held easily in one hand. It stays the same object in every shot. The speaker is held up into the near foreground, filling one side of frame and holding sharp focus while the ground and water behind it stay soft. Then the first character holds it up beside their face and presses the top control with their thumb, and a ring of light comes up on it as they smile down at it. Then they turn and pass it across into the second character's open hands, both of them laughing as the handover lands. Then the camera drops to ankle height and the three of them run across the grass and through a shallow water edge, water kicking up in bright droplets past the lens. Then they pull together into a tight cluster, heads tilting in, the speaker held between them at chest height while they laugh. Then the camera pulls back wide and all three raise their arms, lifting the speaker overhead against open sky. Each beat holds for the same length of time. One continuous camera move per beat, no whip pans, no speed ramps. Audio: bright summer pop playing from the speaker, coming up as the control is pressed and carrying to the end, under natural outdoor ambience — grass, water, birds, light laughter. No voice-over, no narration, no dialogue. Negative prompt: text, subtitles, captions, on-screen graphics, watermark, logos, brand names, extra people, changed faces, changed outfits, distorted hands, duplicated product, stylised or animated look

2 steps2913.9K
Seedance 2.515s · 16:9
Inspired by Ferskifyon Pinterest

@image1 is the environment lock and the opening frame: the floor material, colour, pattern, grout lines, wall colour, window position and camera geometry are taken from it exactly and hold without drift for the entire clip. @image2 is the storyboard and is followed exactly — same order of shots, same framing, same stage of the cleaning in each. Look: handheld phone-camera realism throughout. Natural daylight from the window, real water physics, real foam behaviour, real surface reflection as the floor goes from matte to wet to glossy, slight handheld sway and reframing between moves, shallow natural depth, no stylisation and no colour grading beyond what the daylight gives. The floor sits dull and still, then a stream of cleaning liquid arcs down into frame and spreads across the surface in a widening pool. A long-handled floor squeegee enters and sweeps through the liquid in one broad stroke, foam blooming and running ahead of the blade. The squeegee works back and forth across the surface in overlapping passes, foam thickening and the dull film lifting away behind it. A rush of rinse water floods across the floor, and the squeegee pushes the grey water away in long raking strokes toward the far edge. A mop head is lowered into a spin bucket and wrung out, then returns and passes across the damp surface in even overlapping strokes. The final stroke clears the frame and the surface settles, dark and glossy, holding the window light in a clean mirrored reflection. Timing: 0–3s the pour spreads into a pool; 3–6s the first broad squeegee stroke, foam blooming; 6–9s the overlapping squeegee passes lift the dull film; 9–12s the rinse flood and the long raking strokes; 12–15s the mop is wrung out in the spin bucket and passes across in even strokes; 15–18s the final stroke clears the frame; 18–20s the finished mirror floor holds still, glossy and reflective, to the final frame. Camera: one move per shot, handheld — a slow push in over the pour, a low tracking follow along the squeegee strokes, a tilt down to the bucket, a slow rise back out to the finished floor. No orbiting, no spinning, no crane moves. Audio: the pour and splash of liquid, foam fizzing, rubber squeegee dragging over hard floor, water sheeting and draining, the ratchet of the mop wringer, damp mop strokes. Room tone only — no music, no voice, no narration. No text, no captions, no on-screen graphics, no logos, no brand labels, no watermark. No faces in frame.

3 steps
Seedance 2.520s · 9:16
Inspired by @ImaStudio_aion X

ATTACHED IMAGES ARE MANDATORY AND FINAL: If a reference image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. CHARACTER LOCK — HIGHEST PRIORITY: The person is exactly the person in @image1 (character sheet). Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically throughout. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people. PROPORTIONS — ADULT FIGURE CANON: a fully grown adult figure of approximately seven and a half head-heights from crown to sole. Shoulders about two head-widths across, the hip line at just under half the total height, legs from hip to sole about half the total height, and an adult jaw, chin and neck. Match the build, shoulder width and body mass shown in @image1 (character sheet). Never a child or teenage canon — not five to six head-heights, not an oversized head, not shortened legs, not rounded infantile cheeks, not enlarged eyes relative to the face. Create a high-quality fashion MV based on @image1 (character sheet), @image2 (graphic world) and @image3 (storyboard). Style: Pattern Collage Pop x Fashion Editorial x Fashion MV. The feeling is entering a magazine world made of classic patterns, geometric graphics, collage layouts and bold typography. Keep the person realistic, and keep every background and design element flat, sharp, clean 2D graphic design exactly as established in @image2. Avoid rough handmade collage; make it polished, chic, trendy, glossy and editorial. Follow @image3 exactly for shot order, framing, pose, shot size, graphic treatment and type placement. Slight outfit variation across looks is allowed, but they must still read as one continuous character. Motion and camera: this is a fashion MV, not a slideshow. Each segment must have a clear pose-to-pose action: half-step forward, look back, lower gaze then look up, fix hair, touch bag strap, hand near face, seated side look, crouch with soft smile, reach toward camera, light turn, final hero pose. Expressions: composed, confident, polished. Use fast but smooth lateral movement, light push-in and pull-out, alternating close, medium and full shots, detail inserts, and editorial split compositions. Typography: add large, readable fashion typography without covering the face. Use a main NAME title plus supporting English keywords. Words can include: SOFT CHIC, FASHION CUT, LOVELY MOOD, TRENDY LOOK. Vary placement, size, direction and colour while keeping a unified magazine design system. Timeline: eight stylish looks of equal weight, one flowing into the next at a steady pace, ending in a strong final hero shot where the previous graphics and keywords reassemble into a polished magazine-cover composition. Hold on the final frame. Avoid: a different person, face drift, changed skin tone, changed eye shape, changed ethnicity, restyled or recoloured hair, de-aged, child or teenage figure canon, five- or six-head proportions, oversized head, shortened legs, rounded infantile cheeks, enlarged eyes relative to the face, small receding chin, childlike face, doll or chibi proportions, stylised or anime face, beautified or slimmed body, multiple people, static poster feel, stiff motion, overly realistic backgrounds, unreadable text, text over face, childish tone, cheap filters, logos, watermarks, subtitles, exaggerated dance, or goofy expressions.

4 steps361.9K
MiniMax H315s · 16:9
Drift Dog Snowboardon organic

@image1 defines the dog's identity and its jacket: breed, head shape, coat pattern, eye placement, and the jacket's exact cut, colour, material, fastenings and whatever is printed on its flank. Copy that flank exactly as photographed and never re-letter it, re-space it or re-style it — and if the jacket in @image1 is blank, it stays blank in every frame: never invent a word, a logo or a brand mark the photograph does not show. Do not use @image1's background. One-line summary: a dog rides a snowboard down an alpine piste wearing its jacket while its owner films it from a chest-mounted action camera, skiing alongside — a 20-second product film for the jacket. [Global settings] Camera body: ONE camera only — a wide-angle action camera strapped to the owner's chest. The whole film is that camera's own edit: hard cuts between moments of the same run. The camera goes exactly where the owner's body goes. It has no zoom — when the dog grows in frame it is because the owner has skied physically closer, and when the dog shrinks the owner has eased back. Mild barrel distortion at the edges, deep focus, constant vibration through the skis, the horizon tipping with every turn. Physics regime: real snow behaves as real snow. The board edge cuts a visible trench and throws granular spray that arcs and falls with weight. The jacket keeps the fit and fabric it has in @image1 and moves and takes snow the way that fabric really does. The piste is groomed, packed snow — firm underfoot, not deep powder, and the dog is never buried or hidden by the spray. Hard midday alpine sun from camera-left, highlights blowing out off the snow the way a real sensor clips them, two long blue shadows running forward-left. THE DOG — one dog, exactly as @image1 shows it, riding with both front paws planted flat on the deck and its hind end low over the tail, leaning its shoulders into every turn. It moves like a real dog on a board — weight low, shoulders doing the work. [Prohibitions] No humanised dog. It never stands on its hind legs, never holds ski poles, never grips anything in its paws. THE SHADOW IT CASTS ON THE SNOW IS THE SHADOW OF A FOUR-LEGGED DOG CROUCHED ON A BOARD — never an upright human figure, never a standing snowboarder with arms out. No soft-body or rubbery bending of its legs or of the board — both stay rigid. The board never detaches from under its paws and never clips through them. No second camera, no drone, no aerial shot, no third-person angle this chest mount could not physically see. No optical zoom. No falling, no crash, no tumble. No other dogs and no other riders crossing the frame. No invented text anywhere — not on the jacket, not on gloves, not on clothing, not on equipment — and no real brand logos on the owner's gear; the jacket keeps its own wordmark and logo exactly as in @image1. No subtitles, no captions, no watermark. No fade from black and no black frames. [PRIORITY — if the film runs shorter than 20 seconds, shorten from the bottom of this list and never by inventing a beat that is not written below] 1. The air: the dog off the lip in full profile, flank square to the lens. 2. The landing and the paw tap on the owner's glove. 3. The move out to the dog's left side, rear view into profile. 4. The two carves. 5. The opening run already at full speed. Whatever the length, the last frame is the dog standing square on the board with the owner's hand in shot — never a held empty frame, never a slow drift onto bare snow. [Timestamped storyboard] 0–3s: [Already moving] Initial state: full speed from the very first frame — no run-up, no easing in. The camera looks down and forward at the dog just ahead of the lens, low on the board, a thin fan of snow coming off the tail. It stays fully visible — the spray never covers it. Its jowls press back against its cheeks and its front paws splay wider on the deck. Camera move: the owner holds straight behind it. <Wind buffeting and overloading the microphone from frame one> <the dry scrape of a board edge on packed snow> (driving indie-rock with a hard kick drum starts on the first frame). End state: the dog centred, seen from behind, pulling away down the fall line. 3–6s: [Level] Continue from the previous stage: same slope, same light, same speed. Primary event: the owner skis out wide to the LEFT and forward until level with the dog, so the dog turns from a rear view into a full left-side profile and the jacket reads across its whole flank — sitting on the dog exactly as it fits in @image1. Camera move: one lateral move left, then hold level. Pine shadows stripe the piste in bands. <The owner's own skis carving beside it> <the jacket's fabric rustling in the wind>. End state: the dog in full profile at one third of frame height, just right of centre, the camera level with it on its left. 6–10s: [Two carves] Primary event: the dog throws one hard turn left and one hard turn back right — exactly two, no more. Each turn drives a sheet of snow off the board edge that arcs up, strikes its flank and settles on the jacket the way its own fabric from @image1 takes snow. Its ears pin flat and its jaw sets. Camera move: the owner stays level and the horizon tips with each turn. <Two hard edge scrapes, one per turn> (the music drops to the kick drum alone). End state: the dog back on the fall line, its flank flecked with snow. 10–13s: [The lip] Continue: same formation, camera still level on its left. Primary event: a rounded mound of snow with a clear lip stands ahead and centre. The dog compresses through its front legs as it reaches it — nothing on it restricts the compression, the jacket folds at the shoulder and springs back. Camera move: the owner eases back half a length so the whole lip enters frame. Sound thins to <wind alone>, the music holds one sustained note. End state: the dog at the top of the lip, fully compressed, board still on the snow. 13–16s: [Air] Primary event: the dog launches off the lip and the board leaves the snow completely. Speed ramps down into slow motion at the moment of take-off. In the air, in full profile, the jacket keeps its own fit from @image1. Its shadow tracks it far below on the snow and is unmistakably the shadow of a four-legged dog crouched on a board. Camera move: the owner skis under and past it so the dog swells to three quarters of frame height — the jacket's flank is square to the lens and fully sharp here, every seam and marking on it legible, the single product frame of the film. (Music cuts out entirely) <one long clean hiss of wind>. End state: the dog airborne, in profile, flank sharp, board flat beneath its paws. 16–20s: [Landing and stop] Primary event: the board comes down and slaps the packed snow; snow bursts out from underneath it in a ring; speed returns to normal on the impact. The dog absorbs it through its front legs, wobbles once, holds it, then turns the board hard across the slope and brakes, throwing a wall of spray off the edge. The owner stops beside it. Camera move: one push-in as the owner glides the last metre in. <A solid thump on the landing> <a long hard hiss as it brakes> (the music returns at full level on the thump). End state and FINAL IMAGE: a held steady shot of the dog standing square on its board, side-on, snow settling around it out of the air, breath steaming from its jowls, the jacket's flank clean and square to camera, and the owner's gloved hand entering the bottom of frame — the dog lifts one front paw and taps it. The shot holds dead still on that until the last frame. [Maintain consistency] The dog is one continuous instance for the whole film — never duplicated, never split, and its head, coat and markings are described by @image1 and never redescribed. The jacket is the same garment in every frame: same cut, same colour, same markings, same fastenings. The camera stays on its left from 3 seconds onward and never crosses to its right. The sun stays camera-left and the shadows keep running forward-left. Pure video: no subtitles, no on-screen text, no watermark, no background music other than the track described above. AUDIO: wind on the microphone throughout, board edge on snow, the owner's skis alongside, the jacket's fabric rustling, one thump on the landing and a long hiss on the brake, under a driving indie-rock bed with a hard kick drum that drops out entirely for the air and returns at full level on the landing. No dialogue, no voiceover, no narration.

2 steps
Seedance 2.520s · 9:16
Pet Friendly Cafe Walk-Inon TikTok

PET FRIENDLY CAFE WALK-IN A chest-mounted action cam follows two golden retrievers wiggling down a sunny pavement, then lifts to reveal @image1 — your own cafe entrance — and carries through the door into a welcome from the resident dog. Attach one straight-on daylight photo of your frontage. 14s.

2 steps
Seedance 2.514s · 9:16
Champagne Shower

Generate a live race-day broadcast where champagne from the podium rains down on you in the crowd.

2 steps
Seedance 2.510s · 9:16
Eight Look Magazine MVSeedance 2.5 · 16:9 · 15sRecreate workflow