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 →
Shared clips · Page 17

Made with OpenClips.AI

Watch a clip, read its prompt, make your own — free. Every link is remixable in one tap.

Inspired by Strength04_Xon X

15s 9:16: sunrise run, lace-up to viewpoint. Upload a face as @image1 and a product photo as @image2. Rebuilt from a post by @Strength04_X.

2 steps24490
MiniMax H315s · 9:16
Inspired by itsSaira_1on X

Generate a video of your avatar fighting the evil ghosts.

1 step1122K
Seedance 2.515s · 16:9
Inspired by AIwithSynthiaon X

Cyberpunk action-comedy. Same pace and beats as a missed-train revenge, recast in a neon mega-city transit station. Rain on plexi, magenta/cyan signage, wet concrete, holographic ads. No on-screen text. @image1 is the FIRST PERSON — photocopy their face, bone structure, eyes, nose, mouth, hairline. Preserve their gender presentation exactly as shown. Use they / their / them only. @image1 is FACE ONLY, not their clothes. Dress them in cyberpunk streetwear (dark top, neon piping, techwear). Do not invent different faces. @image2 is the SECOND PERSON — photocopy their face exactly. Preserve their gender presentation exactly as shown. @image2 is FACE ONLY. Dress them in cyberpunk transit wear (dark tech shirt, dark trousers). Do not invent different faces. 0–4s: @image1 runs down rain-slick neon stairs toward a waiting mag-train. Handheld, fast. 4–8s: Doors slam shut as @image1 reaches them. @image2 is inside, sees @image1 through the glass, laughs. 8–12s: @image1 stares, angry. @image1 says “Are you seriously laughing?” @image2 laughs again. 12–16s: @image1 punches the door glass; it cracks and breaks realistically, no gore. 16–20s: @image1 reaches through, grabs @image2's shirt, pulls @image2 safely onto the platform. @image2 lands awkwardly, shocked. 20–24s: @image1 calmly climbs through the same hole into the train, straightens their cyberpunk outfit, walks in. Stunned passengers watch. 24–27s: @image2 sits outside, humiliated. Passengers behind glass start laughing, then all laugh. 27–30s: @image1 looks at @image2 through the window, tiny satisfied smile, turns away. AUDIO: subway rumble, rain, glass crack, crowd laugh. No music. NEGATIVE: no pastel pajamas, no identity drift, no gore, no captions, no teleport, no regenerating glass.

1 step601.2K
Seedance 2.530s · 16:9
Inspired by ivanka_humeniukon X

@image1 is the person. Photocopy face, bone structure, hair, eyes, any facial hair and build exactly as in @image1. Preserve their gender presentation exactly as shown. Use they / their / them only. Do not keep any watermark or text from @image1. Outfit follows the beats below, not the clothes in @image1 (@image1 is identity only). @image2 is the dog in every shot where a dog appears. Photocopy this exact dog from @image2 — breed, size, coat colours and markings exactly as shown. Never a different dog. Same dog every time. 30 SECONDS, 4:3. Provençal stone farmhouse, golden morning. Photoreal. No on-screen text. BEATS 0–4.5s bedroom: they sleep on their side in charcoal sleepwear styled to suit their gender presentation as shown in @image1, the dog curled on their chest. Dog licks their jaw; they squint, sleepy smile, rub its neck. 4.5–6.5s kitchen: two eggs into a smoking cast-iron skillet, butter spit; their torso and sleepwear behind the pan. 6.5–8.5s floor: kibble rattles into a metal bowl; the dog dances then dives in; they stand barefoot over it. 8.5–10.5s table: they eat standing, toss a scrap; the dog leaps and snaps it from the air. 10.5–12.5s sink: splashes cold water on their face, slicks wet hair back. 12.5–14.5s they put on an off-white pinstripe work shirt, roll both sleeves above the elbow, pull khaki Y-back suspenders taut. 14.5–16s foot into a brown leather boot, laces yanked; the dog already waiting by the door, tail sweeping. 16–18.5s stable aisle, dust motes: they walk with the dog at heel, hand along a bay horse's neck. Two bay horses in stalls. 18.5–21.5s paddock gate: they lead both horses out, dog sweeping behind their heels; horses trot; they latch the gate. 21.5–24s chopping block: axe rises against the sun, one clean strike, log splits; they set the next log. 24–27.5s gallop left to right on the darker bay, body low; the dog sprints alongside; dust in golden backlight. 27.5–30s handheld selfie on horseback, walking pace, grin, horse ears and fields; dog trots into frame; loose two-finger salute, looks to the horizon. AUDIO: birds, skillet, kibble, water, boots, horses, axe crack, gallop, dog pant, light fingerpicked guitar under. No speech. No titles.

1 step31812
Seedance 2.530s · 4:3
Inspired by liluocheng13on X

TWO LEADS — PHOTOCOPY BOTH STILLS. Do not invent faces. Do not swap them. Preserve their gender presentation exactly as shown. Use they / their / them only. @image1 = LEAD ONE. Photocopy their face, bone structure, skin, hair, eyes and body exactly as in @image1. ALSO photocopy their outfit from that photo (the prompt has no wardrobe for them): exactly the garments, colours, footwear and accessories shown in @image1 — do not describe or change them. They fight with a jian / straight sword. Same person and same clothes every frame. @image2 = LEAD TWO. Photocopy their face, bone structure, skin, hair and body exactly as in @image2. ALSO photocopy their outfit from that photo: exactly the garments, headwear, colours and footwear shown in @image2, with a katana at the left hip — do not describe or change them. Same person and same clothes every frame. Any headwear from @image2 can tilt in motion but stays on. Never swap their outfits. Never a third human. Never OPENCLIPS.AI type. SETTING: vast ornate temple hall from the source film — gilded dragon columns, wet reflective stone floor, thousands of candles, teal mist, high vault. 16:9. 30 seconds. One continuous action sequence. No dialogue, no subtitles, no on-screen text. LIGHTNING (required on every clash): whenever the two swords collide, a bright white-blue lightning arc flashes along both blades and a fork of electricity cracks the air at the contact point — not ordinary orange sparks alone. Every bind, parry and strike that meets steel = lightning. CORE: zero-delay chaining; scene changes only via their bodies (slam a column, leap from a pillar, crash through candelabra); real weight — blocked hits shove the other back, feet slip, bodies twist. Camera follows limbs; never orbit a frozen pose. BEATS (30s) 0–2s already sprinting from opposite ends of the hall, full-speed clash at centre. Blades meet with a lightning burst; both recoil half a step; floor tiles crack. No establishing pause. 2–7s close melee: @image2 sweeps a wide horizontal cut; @image1 drops almost to the floor, blade skimming their nose, a lock of their hair cut; @image1 springs up with a straight thrust to @image2’s chest; @image2 spins, wrists reverse to bind. Swords lock, shoulder to shoulder, then both shove off with lightning at the bind. Two steps back. 7–9s the shove sends @image2 into a dragon column; @image2 rebounds, runs vertically up the pillar; @image1 explosive-jumps after. Two or three lightning clashes on the column, blades scarring the gilt. 9–12s @image2 is forced to the beam; @image1’s heavy blow knocks them off; @image2 mid-air flips, diving slash; @image1 drops from the column to meet it. Landing clash — lightning + sparks, arms visibly shake. Now they are on the hall floor again. 12–17s densest round: @image1 three accelerating cuts (@image2 sidesteps, then floor-dodge, then ducks under and slashes at @image1’s waist). A corner of @image1’s outfit splits. @image2 lunges; @image1 barely slips, fabric tears at the shoulder; @image1 counters so hard @image2’s blade rings and the tsuba cracks; @image2 staggers two steps. 17–21s bind at close range, simultaneous break, charge again — they smash a row of candelabra; candles snuff then relight from the sword-wind; they keep fighting through fallen candles and oil, lightning every contact, water-mist from the wet floor. 21–26s peak speed: cut, thrust, parry, counter in two–three seconds, each hit a lightning flash plus body feedback. Teal-green sword qi spirals. No frozen frame. 26–29s simultaneous all-out strike; blades meet; a hall-wide teal-white lightning shockwave hurls both back several metres; tiles and columns crack; candles gutter; camera shake then soft defocus. 29–30s smoke thins. Both still on their feet, one knee or standing, chests heaving, sword-hands shaking from exhaustion. Remaining candles relight. Wide two-shot. Hold. No titles. AUDIO: steel, thunder-crack on every clash, stone, fire, breath, shockwave. No BGM. No speech.

1 step531.7K
Seedance 2.530s · 16:9
Inspired by @AvaSmith771on X

ONE SHOT. VERTICAL. ONE PRODUCT ONLY. LUXURY PRODUCT FILM. ASSET MAP - every reference is bound here and cited by tag below: @image_1 - the product. This is the only product in the film; its shape, colour, finish, material, proportions and every detail come entirely from @image_1 and never from this text. PRODUCT LOCK - HIGHEST PRIORITY: the product on camera is exactly the product in @image_1. Preserve its silhouette, proportions, colour, finish, surface texture and every constructed detail identically from the first frame to the last. Do not restyle it, do not redesign any part of it, do not change its colour or its material, and do not add a marking, a logo, a label or lettering that is not already on it. One single product, alone, for the whole film. ATTACHED IMAGES ARE MANDATORY AND FINAL: if a reference is attached, that is the product - reproduce it exactly, in every frame, and never invent a different one. The attached reference outranks every word written below it. WORLD: a high-end studio with no visible walls, floor or horizon - only deep shadow falling away behind the product. Large soft key light from the upper left and a narrow rim along the back edge, so the surface carries one long clean specular highlight that travels as the camera moves. A tight contact shadow holds the product to the ground. Behind it, a single panel of heavy silk drifts slowly across the darkness, catching light in soft folds and never touching the product. Fine dust-fine sparkle particles hang in the air and drift, lit only where the key catches them. The colour of the film comes from the product itself: whatever dominant colour @image_1 carries, the silk, the rim light and the particles take that same colour, and the rest stays deep near-black. Shot 1: THIS IS THE ONLY SHOT AND IT RUNS FROM THE FIRST FRAME TO THE LAST - there is no cut anywhere in this film. The product is already in frame, already lit and already large at the very first frame, held upright and perfectly still. The camera begins in a slow macro push-in toward it, close enough that the surface texture and the light travelling across it are readable, then without stopping eases into a smooth orbit around the product, circling it at the same slow speed while the specular highlight slides along the surface and the contact shadow rotates with the move. The silk behind keeps drifting, the particles keep floating, and the product itself never moves, never tilts, never spins and never leaves the centre of frame. The camera comes to rest on a clean three-quarter view and holds there to the final frame. AUDIO: a very low room tone, one soft sustained pad that stays at a single even level, a faint high shimmer as the particles drift, and the quiet rustle of heavy silk moving in the dark. No voice, no narration, no lyrics. Do not generate subtitles, captions, on-screen text, a caption card, a timestamp, a recording indicator, an interface overlay, a logo or a watermark. No second product, no packaging, no box, no hands, no person, no readable lettering or numerals anywhere in frame beyond the product's own label and logo, kept exactly as shown, no cuts, no reflections that resolve into a room or a face, and no change to the product's shape, colour or finish at any point.

1 step28560
Seedance 2.010s · 1:1
Inspired by AIwithSynthiaon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. @image1 is identity only — face, bone structure, skin, hair and eyes exactly as shown, age, body. Not wardrobe. Do not keep any clothing from the photo. Keep their hair exactly as in @image1. WARDROBE: simple, casual at-home clothes that suit the person in @image1. Same outfit the full 30 seconds. SETTING: bright modern bedroom, unmade white duvet, white pillows, cream wall, golden-hour sun from camera-right throwing a sharp silhouette of the person on the wall. Handheld smartphone UGC, subtle shake, cinematic commercial grade. One person only. No on-screen text, no logos, no subtitles, no watermarks, no end card. PRODUCTS (match the source clip, no brand marks on the devices): - A book-style foldable phone: closed it is champagne-silver on the lower back with a glossy black camera bar, vertical triple cameras on the left of that bar. Opens like a book to a large inner screen. - A white rectangular retail box on the bed. - A gold-case smartwatch with a white sport band. 30 SECONDS. Native room tone + their spoken lines only. No BGM. BEATS AND LINES (lip-sync these exact lines): 0–5s — already sitting on the bed facing camera, box and watch on the duvet. Smiling. Says: "I genuinely wasn't expecting to love this foldable phone this much." Picks up the box, opens it, lifts the folded phone. 5–9s — holds the closed phone toward camera, rotates it slowly (thin frame, hinge, camera bar). Says: "The design already feels incredibly premium." Then: "The design is so sleek, and I really love how the foldable screen opens up." Unfolds it. 9–16s — phone fully open, colorful app grid on the inner display. Scrolls, opens camera, points it around the room. Says: "And the camera quality is seriously impressive. Everything looks so sharp and detailed." Closes and opens the phone once. Says: "Plus, the battery is supposed to be better too, which is honestly a huge win for me." 16–23s — sets the phone on the bed, picks up the gold-and-white smartwatch, holds it close to camera (case, crown, strap). Says: "And the new smartwatch is actually really nice too." Buckles it onto their left wrist, raises the wrist to camera, scrolls the face. Says: "I love how clean it looks, and having all these features right on my wrist is so convenient." Turns the wrist in the sunlight. 23–30s — picks the folded phone back up. Holds phone in the right hand and shows the watch on the left wrist. Looks into camera, warm smile. Says: "Honestly... this might be one of my favorite upgrades yet." Soft laugh, glance down at both, then holds the phone beside their face with the watch clearly on the wrist. Slow push-in. Last frame still in the bedroom — no fade to black, no titles. Frame 1 is already on the bed in the scene — never a studio portrait or the attached still. Photoreal skin, real hands, five fingers. Same foldable and same watch the whole time.

1 step9111.1K
Seedance 2.530s · 16:9
Inspired by ZarnishNaelon X

CHARACTER LOCK: The person in every shot is exactly @image2. Face locked. Gender presentation as shown. They/them. No other people. Do not describe the person. @image2 is face and identity only, not the outfit. @image1 is the product. Do not name it. Do not describe it. Match @image1 exactly whenever the product is on screen. 20 seconds, 16:9. Baby-blue environment throughout — walls, floor, light, not pink or crimson. @image2 wears clothes that fit a luxury commercial. Hands visible. NO ON-SCREEN TEXT, logos, brand end cards, titles, subtitles. 0–4s. @image2 walks forward down a baby-blue corridor of arches. Floor is glossy, scattered with dark roasted coffee beans (not cherries). 4–8s. Close: they spray the product from @image1 onto their neck. Mist in the light. Baby-blue backdrop. 8–12s. They sit at a bar holding an espresso martini (coffee-brown, foam, coffee bean garnish — not a red cocktail). Warm light, baby-blue around. 12–16s. Macro: they step onto a coffee bean with one shoe. The bean compresses. Product from @image1 nearby. No cherry, no red juice. 16–20s. They hold the product from @image1 at chest height, look at camera, and say clearly: "As addictive as an espresso." No logo, no end card. Cut. SOUND: diegetic footsteps, spray hiss, glass, bean crush, then the spoken line exactly. No music bed that drowns the line. NEGATIVE: red cocktail, cherries, brand text not printed on @image1, extra people, studio headshot as frame 0, pink/magenta corridor.

2 steps668.5K
Seedance 2.520s · 16:9
Inspired by @Diplomemeon X

FICTIONAL RECREATION — Hyper-realistic unscripted water-park obstacle challenge, photorealistic live-action, ONE CONTINUOUS TAKE, no cuts, no transitions, no time jumps, no camera teleportation. One face reference used strictly for identity consistency. Preserve facial identity, facial proportions, hairstyle, skin texture, apparent age and recognizable features throughout the entire shot. No face swapping, no identity drift. Preserve their gender presentation exactly as shown. Use they / their / them only. CHARACTERS: @image1 = main contestant. From the @image1 reference take ONLY the face, facial identity and hair — do NOT copy any clothing from the reference. Dress @image1 in swimwear appropriate for a water park (a modest swimsuit or swim trunks), fully clothed and decent, no nudity. Wet hair and skin, natural body proportions. THE FRIEND = a second contestant invented for this film (no reference), dressed in swimwear. @image2 = the featured device, exactly as its reference — it can be a smartwatch OR a phone OR a similar wearable/handheld gadget; match @image2's shape, colour and screen precisely. If @image2 is a wristband/watch it is worn on @image1's wrist; if it is a phone or handheld device @image1 holds it in one hand. Its screen stays clearly visible and readable in its close-ups. SETTING: large modern outdoor water park on a bright summer afternoon. Giant inflatable obstacle course floating in a big pool, climbing platforms, floating balance beams, slippery ramps, overhead water jets, inflatable barriers, spectators behind safety rails, lifeguards, wet concrete, colorful umbrellas, realistic resort architecture. Hundreds of subtle background actions create authentic environmental life without distracting from the main action. 0-3s: opening — @image1 brings @image2 up toward the camera in a relaxed, anatomically natural pose (a wrist turned gently to face the lens if @image2 is worn, or the device held up in one steady hand if it is a phone/handheld), the arm, wrist and hand clearly belonging to @image1 and connected naturally to their body, with correct orientation and no strain. @image1 taps @image2's screen once with a finger, then says clearly and naturally, "Let's track my time," and grins before turning toward the course. Handheld camera at pool level, autofocus settling on @image2's screen, then on the contestant. 3-7s: camera roughly three meters behind @image1 at pool level, handheld but professionally operated, following as @image1 runs toward the first floating obstacle while the friend watches from the side. Small realistic handheld movement, occasional water droplets crossing the lens. 7-11s: @image1 jumps onto a wet inflatable platform; the landing is slightly unstable, one foot slides forward unexpectedly, they recover for a moment, laugh nervously, then continue. Camera moves closer keeping continuous spatial relationship and human-scale perspective. 11-16s: @image1 attempts a narrow floating balance beam; a foot slips, they grab a flexible overhead rope and swing sideways with real momentum, the rope stretching and pulling their body back toward the obstacle. The friend reacts from the adjacent platform, stepping backward to avoid the swinging contestant. 16-20s: @image1 regains balance but accidentally kicks a large inflatable obstacle; it shifts dramatically and a nearby water jet activates into it, throwing up a sudden burst of spray. A loose inflatable flamingo float drifts free across the water behind them. The camera operator instinctively steps back while still filming, briefly losing perfect framing before quickly reacquiring @image1. 20-25s: @image1 tries to escape across a slippery ramp but loses traction completely and slides uncontrollably downhill; their sunglasses fly off and land on the drifting flamingo. The friend reaches toward them but misses. @image1 collides softly with a large inflatable barrier, rebounds, spins naturally and falls backward into the pool. 25-30s: a huge realistic splash momentarily covers the camera lens; the operator wipes it while staying in the same physical spot. Through droplets and distorted reflections, @image1 resurfaces laughing, glances at @image2 (its screen still running) and grins, while the friend laughs in the background. Camera settles into a final medium-wide composition showing both contestants, the obstacle course, lifeguards and surrounding spectators. PHYSICAL REALISM: every movement follows believable human biomechanics and real water physics — correct body weight, inertia, friction, momentum, buoyancy, splash displacement, wet-surface slipperiness, inflatable deformation, rope tension, water spray and gravity. All arms, wrists and hands stay anatomically correct and naturally connected to their owner. No floating bodies, rubbery limbs, impossible recoveries, teleportation or cartoon physics. Exactly two hands per person, believable at all times. CAMERA REALISM: authentic handheld operator behavior — natural micro-jitter, slight bobbing while walking, imperfect framing during sudden action, realistic autofocus hunting, exposure adaptation between bright sun and shade, lens water droplets, temporary obstruction, realistic motion blur. The camera physically moves through the environment rather than cutting between viewpoints. LIGHTING: strong natural afternoon sunlight, realistic reflections on wet skin and inflatable surfaces, physically accurate water highlights, soft shadows, subtle haze, consistent sun direction throughout. AUDIO: pure location sound — running footsteps, splashing water, inflatable material flexing, distant conversations, excited spectators, water jets, lifeguard whistles, @image1's spoken line "Let's track my time" delivered clearly and lip-synced, and their laughter, the friend shouting a spontaneous reaction, heavy splash impact, water dripping onto the camera microphone. No music, no cinematic sound effects. CONTINUITY LOCK: one single continuous take, no cuts, no hidden cuts, no camera teleportation. @image1 remains identical to their reference throughout; @image2 stays the exact device from its reference and never changes type; preserve hairstyle, body proportions, wetness progression, environment, obstacle positions and sunlight direction. Every action logically causes the next. Negative: @image2 changing type or turning into a different device (a phone becoming a watch or vice versa) — keep exactly what the reference shows; a twisted, inverted, over-rotated or backwards forearm or wrist; the arm or hand looking detached or like it belongs to a different person; a disembodied or floating arm; unnatural wrist rotation; more than two arms; the jacket, blazer, coat or any outdoor clothing from the reference image; formal or street clothes; anyone dressed in non-swimwear near the pool; any gendered, ethnic or racial description of either contestant; nudity; identity drift or face swapping; letters, words, on-screen text, captions, logos or numbers (except the screen of @image2); a third hand, extra arm, more than two hands, extra or missing fingers; cartoon or exaggerated physics; visible cuts; watermark.

1 step1024.8K
Seedance 2.530s · 9:16
Inspired by itsSaira_1on X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. Use they/them throughout. No other people. @image1 is face and identity only, not the outfit. Address the reference only as @image1. Do not describe the person. Clothes suited to an enchanted night library. They carry a wand in one hand. Both hands visible whenever the frame shows the torso. 30 seconds, 16:9. Photoreal cinematic. No on-screen text, captions, logos, or watermarks. Setting: a vast enchanted library at night. Tall dark wood shelves, a long aisle, a stone pedestal with a closed ancient book at the far end. Floating candles everywhere — all unlit at the start. No clockwork, no gears, no machine-flowers, no forest. OPENING: already in the dark library. Never a studio portrait, grey backdrop, or the attached still as frame 0. Candles are off. Only faint moonlight through high windows. TIMELINE (30 s): 0–6s: Wide — dark aisle, unlit floating candles. @image1 walks forward, wand in hand, swinging it in a slow arc — on the very first swing the nearest candle flares alight beside their face. 6–16s: As they walk and swing the wand, candles light one after another along their path — warm flame, not electric bulbs. The aisle brightens behind them. Keep walking. Do not stop to repair a candle. 16–22s: They reach the pedestal. Closed book on it. They raise the wand. 22–30s: Wand touches the book. The book begins to shine from within. Pages turn by themselves. Hold on the glowing book and @image1. Cut. CAMERA: gentle follow and push-in, shallow depth of field, volumetric dust in candlelight. SOUND: diegetic — footsteps, soft whoosh of the wand, candles catching (tiny flame pops), pages turning. No music, no speech. NEGATIVE: clockwork, gears, lightbulbs, spa robe, waffle robe, forest, extra people, studio headshot, text, unlit candles after they have already passed.

1 step1301.9K
Seedance 2.530s · 16:9
Copycat

subject_definitions: @image_1 is the performer. Gender, face, hair, skin and body proportions come entirely from @image_1 and not from this text. @image_1 defines identity only - its clothing, pose, framing, background and lighting are ignored. The sprite is a fictional cartoon invented from this text alone and comes from no reference: a tiny 2D cel-shaded character with clean black outlines and flat colour fill, pointed ears, large round eyes, a simple pink-and-white tunic and translucent pink wings. The sprite stays flat 2D in every frame and is roughly the size of @image_1's hand. summary: [reference generation] The target video is a 15-second 16:9 live-action film in which @image_1 and one tiny 2D cartoon sprite play off each other across eight shots inside an empty neon roller rink at night, ending with both of them facing camera. retention_analysis: @image_1 (appears in [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6], [Shot 7], [Shot 8]): fully_preserved - gender, face, hair, skin and body proportions stay exactly as in @image_1 in every shot. detailed_description: The target video is live-action and cinematic, lit only by hard magenta and ice-blue neon tubes along the rink walls, with a glossy varnished floor that mirrors every light, and a palette of magenta, cyan and black. Only two characters exist: @image_1 and the sprite. The rink is otherwise empty, with no other people and no reflection that resolves into a face, and no lettering, numerals, signage or screens anywhere in frame. @image_1 wears the same outfit in every shot: a plain, simple everyday outfit that suits them. That outfit's cut and colour are fixed and only its drape adapts to the body; @image_1's gender, face, hair and skin come from @image_1 and never from this text. [Shot 1] A low-angle wide shot frames a black vintage convertible parked at the edge of the rink floor. Only the sprite is visible, sitting behind the wheel. The sprite waves, snaps its wings open, rises past the windshield, clears the open roof, half-spins and flies off frame right, leaving the driver seat empty. The camera pedestals up slowly. [Shot 2] At 00:01.800, the shot cuts to @image_1 leaning against the open car door, head down, turning a ring on one finger. The sprite curves in and stops at @image_1's shoulder in a proud ta-da pose. @image_1 lifts their head, looks at the sprite, then at camera. The camera pushes in slowly from beside the headlight. [Shot 3] At 00:03.600, the shot cuts to a waist-up framing as @image_1 flicks one finger toward the sprite on a hard beat. The sprite tumbles through one continuous half-spin to camera right and rights itself as @image_1 breaks into a crooked grin. The camera arcs right with large amplitude at fast speed. [Shot 4] At 00:05.400, the shot cuts to the sprite flying a full circle around the outer edge of a hanging mirror ball, passing above and below it, never through it. The camera tracks with the sprite and finds @image_1 sitting on the rink barrier, one foot on the rail. @image_1 holds up a thumb and the sprite copies it beside @image_1's face. [Shot 5] At 00:07.200, the shot cuts to @image_1 opening one palm flat. The sprite descends in one continuous motion and visibly lands, both feet making contact with the skin, then plants a proud stance and copies the tilt of @image_1's head. @image_1 holds still, then smiles. The camera pushes in slowly from the hand up to both faces. [Shot 6] At 00:09.000, the shot cuts to the sprite lifting off the palm first. @image_1 stands and takes three unhurried steps onto the rink floor, their reflection moving under them, while the sprite flies backward in front of them. The camera tracks backward with large amplitude at slow speed along a lateral arc. [Shot 7] At 00:11.000, the shot cuts to a low angle with the convertible sitting diagonally behind @image_1. @image_1 plants a confident stance and brushes one shoulder off with a flick of the hand; the sprite copies the gesture on its own shoulder and @image_1 notices and laughs. The camera pushes in slowly. [Shot 8] At 00:13.000, the shot cuts to a medium close-up of @image_1 raising two fingers in a peace sign beside their face. The sprite hovers at @image_1's shoulder, wings spread, both arms up in the same sign, and both look straight into camera. A single camera flash fires on the last beat and the neon holds its level through it. The camera holds a static shot through the final frame. overall_soundscape: The empty rink carries a low room tone with the electric hum of the neon tubes and the far-off whirr of a ventilation fan. Footsteps land and squeak on the varnished floor, fabric shifts as @image_1 moves, and the sprite's wings make a light dry flutter each time it changes direction. One short breath of a laugh lands near the end. non_diegetic_music: Bubblegum dance pop at 128 BPM with a punchy kick and snare, a bouncing bass line, crisp handclaps and sparkling synth arpeggios. The arrangement stays at one even, moderate level from start to finish, with accents landing on the wing snap, the finger flick, the landing on the palm and the final flash.

1 step
MiniMax H315s · 1:1
Inspired by nastassiavideoon X

Exactly 15 seconds, 16:9. ONE CONTINUOUS UNBROKEN TAKE. Live-action fantasy comedy, 35mm grain, bright noon daylight, saturated but natural skin. Same world palette as before: floating grass islands, red-and-white mushrooms, green pipes, gold coins, waterfalls, pink-roofed castle, red-and-white curb, blue sky with big clouds. @image1 is GREEN — lock this exact face 100%. Preserve their gender presentation exactly as shown. Use they / their / them only. Hair exactly as in @image1, green cap, denim overalls, cream top, white gloves, brown boots. Green kart. @image2 is RED — lock this exact face 100%. Hair exactly as in @image2, red cap, denim overalls, cream top, white gloves, brown boots. Red kart. Do not swap faces. Do not open on a studio portrait; frame 1 is already racing. The Royal at the finish line, slightly to one side of the checkered stripe: blond curls, gold crown, pink costume, arms open. Directly BEHIND the Royal, not beside: Bront the teal-scale copper-shell horned creature, white crest, brown eyes. Bront is clearly behind the Royal. 0-2s — Already racing, side by side. RED shouts, exact lip sync: "My royal!" GREEN: "No! MY royal!" 2-6s — GREEN steers hard into RED and SHOVES RED completely off the track. RED's red kart leaves the road entirely — over the curb, off the floating island, falling away. GREEN stays on the racing line and keeps going. This is a full knockout, not a bump. 6-10s — GREEN alone, full speed, drifts the last bend, crosses the finish line still in the green kart. The Royal is ahead with arms open. GREEN does NOT stop in front of them. GREEN drives past them, around their left side, and brakes behind them next to Bront. 10-13s — GREEN jumps out, ignores the Royal, runs around them and throws both arms around Bront. Tight hug. Bront grins. The Royal turns, confused. 13-15s — The Royal drops to their knees and sobs, kicking. GREEN keeps hugging Bront. RED is gone off-track. Abrupt end. One uninterrupted shot. No cuts. Audio: engines, a hard kart impact, wind, two spoken lines, hug, the Royal sobbing. No music, no subtitles, no logos. No on-screen text. Duration: exactly 15 seconds. Aspect ratio: 16:9.

1 step472K
Seedance 2.515s · 16:9
Inspired by saranshvfxon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. The avatar reference shows their face and build, not this outfit — put the outfit on them. Fit each garment to the character's body naturally without altering its design, cut, proportions or colour — the garment is fixed, only its drape adapts. VISUAL CONSISTENCY: the person in the attached reference, frost-dusted face, tattered pale-blue and silver samurai armor, ice katana — adapt only pose, lighting, and surroundings. Do not alter their facial structure. STYLE: Highly realistic dark fantasy, brutal close-quarters combat, subterranean glacial cavern, falling ice crystals, cinematic wide scale, dramatic chiaroscuro lighting, deep atmospheric depth. 0–5 SEC — DESCENT INTO THE ABYSS Ice-lit subterranean ruins → obsidian-blue frost-demons scale massive frozen pillars → ice crystals fall heavily → camera tracks downward rapidly → the fighter plunges into the abyss, hair whipping, pale armor glowing in the ambient cold → rapid cinematic tracking dive directly toward the demonic swarm. 5–10 SEC — IMPACT The fighter crashes onto a shattered frozen platform → cracked ice, frost shards, and snow explode outward → fierce shockwave scatters the nearest demons → camera circles rapidly as they rise from the crater → katana drawn, gleaming with reflected glacier light → they dash forward as demons lunge from the shadows. 10–18 SEC — THROUGH THE HORDE The fighter slices through the horde with fluid, brutal precision → katana severs frost-black limbs, spraying glittering ice-blood → sparks and ice shards burst from sword clashes → aggressive tracking and rapid whip pans follow each strike → brief slow-mo captures flying shards, falling snow, and their unyielding expression → they push deeper without losing momentum. 18–24 SEC — THE PLUNGING STRIKE The fighter leaps off a crumbling ice pillar high into the cavernous airspace → camera follows vertically through cold shimmer → a towering ice beast emerges from the frozen lake below → they grip their katana with both hands, cyan energy building rapidly along the blade → they dive downward into a devastating plunging strike. 24–27 SEC — FROST ERUPTION Katana pierces the ice beast's chest → massive burst of cyan and silver energy erupts → shockwaves shatter surrounding ice pillars → lesser demons disintegrate into snow → ice splashes, shattered frost, and glowing shards fill the frame → camera pulls rapidly backward and upward revealing the immense destruction. 27–30 SEC — VICTORIOUS ENDING Remaining demons crumble to dust → smoke and snow drift slowly → the fighter stands at the center of the shattered platform → hair and tattered garments move naturally in the rising icy winds → frost-stained katana rests at their side → camera pulls back into a final wide aerial shot → they stand alone and victorious amidst the glowing rivers of ice. CAMERA & MOTION: Rapid cinematic movement, rapid whip pans for impacts, smooth aerial tracking, realistic motion blur, natural camera inertia, no random teleportation. PHYSICS & VFX: Cold shimmer, realistic snow and cloth interaction, believable ice-blood, grounded creature movement, controlled energy blasts, large-scale shockwaves integrated into the environment. QUALITY: Photographic skin, detailed weathered metal, glowing glacier lighting, cinematic depth of field, high dynamic range, epic fantasy realism. NEGATIVE: No cartoon, no anime style, no plastic armor, no modern objects, no inconsistent character design, no deformed anatomy, no extra limbs, no random costume changes, no text, no watermark.

1 step2145
Seedance 2.530s · 16:9
Inspired by shanyanggmon X

Create a 15-second 9:16 ultra-realistic cinematic video of @product. @product is the enormous life-sized matchstick replica from the storyboard, same silhouette and proportions as the product, sculpted entirely from wooden matchsticks, red match heads as texture. Same replica every frame. The attached product photo is the source for its exact shape, proportions and details. Life-sized on a white table, dark studio, 85mm, shallow depth of field. OPENING: Frame 1 is already the replica on the table, sharp. No grey still. 0–3s: @product stands still. Soft haze. Two hands enter with a match, strike it. Realistic match-strike sound. 3–8s: The lit match touches its base. Fire spreads naturally across the matchsticks. Crackling wood, popping match heads. Replica stays standing. 8–13s: Flames climb the whole replica. Orange glow from inside, sparks, smoke. No explosion. 13–15s: Fully charred black silhouette of @product still standing. Embers. End hold. AUDIO required: match strike, crackle, pops, flame. No voiceover. No on-screen text. Hands only, no faces. Duration 15s. Aspect 9:16.

2 steps
MiniMax H315s · 9:16
Inspired by Elvoryaon X

Generate a video of your avatar stopping the time.

1 step1034K
Seedance 2.515s · 16:9
Inspired by iamneuberton X

@image1 is the hero. Photocopy face, bone structure, hair, eyes, skin and age exactly as in @image1. Never recast them. Preserve their gender presentation exactly as shown. Use they / their / them only. Do not put OPENCLIPS.AI in the scene. OUTFIT for the scene (not the clothes in the still): light, practical desert clothes and scuffed hiking boots that suit them, small aviator sunglasses. Hair stays exactly as in @image1, breeze moving it. 30 SECONDS, 16:9, one continuous take, no cuts. Live-action cinematic. Late-afternoon Utah slickrock, burnt-orange sandstone, pale washed-blue sky. Bright yellow doorless off-road 4x4 on a tilted slab. They sit on the hood, back against the windshield, one knee up, phone in both hands. Yellow 4x4 is the only saturated note. Deadpan comedy. AUDIO: dry wind, raven, engine ticking. 0.8s one sharp phone ping. 1.2–4.0s chipper compressed voice-note: "Hey! Love it. Just one more quick change — can we get it as soon as possible? Thanks!" Then only wind. Optional tiny "uh oh" at 5.5s. No BGM. No on-screen text. TIMELINE 0–1s already on the hood, medium from the front bumper looking up, handheld drift, scrolling, small smile. 1–4s ping. Push to close-up face and phone. Smile flattens. They read twice. 4–7s lowers the phone. Silent uh-oh: brows lift, mouth tight. Sunglasses down with one finger, glance left at a rock wall, right at a boulder, over their shoulder through the windshield at the empty back seat, down at the phone. Micro-shrug. Taps the phone on the hood once. 7–12s smooth zoom-out to full shot: the person + whole 4x4 on the tilted slickrock, cooler and rolled tent on the back, one tyre against a boulder. They are still looking around, phone up as if hunting signal. 12–17s pull-back and rise: 4x4 a small yellow rectangle in house-sized boulders and sandstone fins; faint tyre scuff climbing a steep ledge behind. 17–22s keep rising: boulder field is a wide bowl ringed by fins and one natural arch, snow-dusted mountains on the horizon. The way out is near-vertical rock ledges — harder to drive down than up. 22–27s wide high aerial: slickrock to the horizon, 4x4 a yellow pixel, no road, no town, no other vehicle. 27–30s settle extreme wide. Shadow of a fin sweeps over the 4x4 as the sun drops. Hold. End. Keep the 4x4 near frame center. Horizon level. No other people, no other cars, no paved road, no buildings, no water, no night, no titles.

1 step1898.6K
Seedance 2.530s · 16:9
Inspired by cco_olon X

Generate a photoreal prehistoric survival chase.

1 step117.4K
Seedance 2.510s · 9:16
Inspired by recehtuitton X

TWO PEOPLE — PHOTOCOPY BOTH STILLS. Do not invent faces. Preserve their gender presentation exactly as shown. Use they / their / them only. @image1 = MAIN CHARACTER. Photocopy face, bone structure, skin, hair, eyes, facial marks and facial hair exactly as shown. Athletic street clothes for the court: a black crew-neck t-shirt, dark shorts and basketball shoes. Same person every frame. @image2 = FRIEND. Photocopy face, bone structure, hair, eyes and facial hair exactly as shown. Keep the friend's hair exactly as in @image2. Do not keep the clothes from @image2 on the court. On court the friend wears a faded navy basketball jersey over a white tee, black athletic shorts, white crew socks, worn black basketball shoes. Same person every frame. Never swap them. Never a third player. Never OPENCLIPS.AI type. 30 SECONDS, 16:9. Realistic live-action neighborhood basketball, late afternoon, worn blue-gray court, one hoop with glass backboard, chain-link fence, trees, houses. Warm sun. Handheld, fast, physically believable. Move about every two seconds. Only two people and one ball. Friend starts with the ball. After the steal, main keeps it. LINES (lip-sync): Friend at the sidewalk: "Wanna play? Loser buys the drinks." Main at the end: "I win!" TIMELINE 0–5s main exits a house, closes the door, walks to the sidewalk. Friend walks past dribbling, bobbles the ball, recovers, notices main, stops. Handheld medium-wide, pan from main to friend. 5–9s friend bounces once, gestures at the court, says the line, confident smile. Main nods and takes the ball. Two-shot, both faces. 9–12s cut to the court. Both walk on. Friend stretches, bounces on their feet. Main drops into defense. Friend starts dribbling. Establishing then low track. 12–14s friend two hard dribbles right; main slides; friend crossover left. 14–16s friend drives left; main forces the friend to the sideline; friend spin move. 16–18s main reaches; friend pulls back, pivots, protects with the shoulder. Shoe squeaks. 18–20s friend fakes a drive, stops, sprints; main bites on the fake. 20–22s main recovers, taps the ball loose. Both sprint for it. 22–24s main gets there first, dribbles to the hoop; friend chases. 24–26s two dribbles, sharp step-back behind the arc; friend contests too late. 26–28s jump shot; AFTER release, slow-mo; ball high arc. 28–29s swish, net snaps; back to real time. 29–30s main lands, both arms up, shouts "I win!" Friend head down, shoulders slump under the hoop. AUDIO: outdoor air, ball, squeaks, footsteps, the two spoken lines, rim/net. No BGM. No subtitles.

1 step9177
Wan 3.030s · 16:9
Inspired by SilvyMen11676on X

TWO LEADS — PHOTOCOPY BOTH STILLS. Do not invent faces. @image1 = PERSON 1 (ICE). Photocopy face, bone structure, hair and body exactly as shown. Preserve their gender presentation exactly as shown. Use they / their / them only. ALSO photocopy their outfit and jewellery from that photo exactly as shown. Ice-blue glow in the irises is allowed as VFX. Same person, same outfit, every frame. @image2 = PERSON 2 (FIRE). Photocopy face, bone structure, hair, any facial hair and body exactly as shown. Preserve their gender presentation exactly as shown. Use they / their / them only. ALSO photocopy their outfit from that photo exactly as shown. Fire can wrap them as an aura; do not strip their clothes off. Same person, same clothes, every frame. Never swap outfits. Never a third person. Never OPENCLIPS.AI type. SETTING from the source film: dark wet stone courtyard at night, mist, rain on the ground, dim architecture behind. 15s, 9:16. STORY: fire and ice meet, then go quiet. 0–4s already face to face, close. @image1 looks at @image2; @image2 looks back, jaw tight. Frost crystals along @image1's arms and clothing; orange fire aura crawls @image2's arms and shoulders over their top. Handheld, slightly low, rain. 4–8s they step in. Fire and ice collide between them — steam blast, embers, ice shards. Camera orbits a few degrees. They do not fight; they close the gap. 8–12s @image1 puts their arms around @image2's neck; @image2 holds @image1's waist. Steam swallows the frame then thins. Fire on @image2 dies back to a faint glow. @image1's outfit still frosted, @image2's clothes intact, wet. 12–15s forehead to forehead, eyes almost closed. @image1's hands on @image2's jaw. Quiet. A few leftover sparks and frost motes. Last frame still in the hold. No titles, no freeze-cut. AUDIO: rain, fire crackle that fades, steam hiss, breath. No BGM. No speech.

1 step94170.8K
Seedance 2.515s · 9:16
Inspired by Urwa_345on X

Create a cinematic 10-second premium advertisement for @product, vertical 9:16. @product is the exact product in the reference: same shape, colour, material and any built-in light exactly as shown. Same shape, materials and details in every shot. One object. Keep the product's own marks exactly as shown; never name a brand. 0–2s: Dark modern room. Camera slowly pushes toward @product as the product's own light softly comes on. 2–4s: Macro of the product's signature detail, soft ambient light shifting across it. 4–6s: Camera follows @product being placed on an elegant outdoor table at sunset. Its own light still on. 6–8s: Modern bedroom, @product on a nightstand, cozy ambient light. 8–10s: Hero, slow 360 around @product, cinematic lighting. The product is the star. Photorealistic commercial, smooth camera, shallow depth of field, no on-screen text. AUDIO required: soft whoosh, a gentle chime as the product lights up, quiet room tone. No voiceover. Duration 10s. Aspect 9:16. OPENING: already in the dark room with the speaker — no grey still.

1 step
MiniMax H310s · 9:16
Inspired by ChillaiKalan__on X

HIGHEST PRIORITY — THREE FACE LOCKS: @image1 is person 1. @image2 is person 2. @image3 is person 3. Photocopy each face from its tag. Same person every time that tag is on screen. Do not invent a different trio. Do not morph. Do not average the three faces. If @image2 wears glasses, keep those glasses. Do not describe hair, age, or body — follow the images only. They/them. Outfit is concert-stage clothes, not the stills' wardrobe. 30 seconds, 16:9. Photoreal concert. Real stage, lights, smoke, crowd in the dark, LED wall, three mics. Not a neon street. Frame 1 is already on stage — never a studio portrait plate. NO LYRICS. Mouths perform an original hook. No recognizable song, no copyrighted words. Sound: original crowd roar + stage PA + invented kick/snare. Not any famous track. 0–4s. Wide stage. All three already there: @image1 center, @image2 stage right, @image3 stage left. Faces readable. 4–10s. Close on @image1 at the mic. Face must match @image1 exactly. 10–16s. Close on @image2, then @image3. Each close-up is that exact tag. 16–24s. Trio together, three distinct faces from the three tags. Camera orbits. 24–30s. Wide pull-back. Same three people. Hold. Cut. NO ON-SCREEN TEXT, titles, lyrics, logos. NEGATIVE: different faces, extra fourth person, Bang Bang, neon rain street, studio headshot, subtitles.

1 step681.7K
Seedance 2.530s · 16:9
Inspired by auqibhabibon X

A 30-second 16:9 cinematic heist. Sound ON. The hero is exactly the person in the attached portrait (@image2) — face, hair, facial hair and eyes exactly as shown. Preserve their gender presentation exactly as shown. Use they / their / them only. PRODUCT: the exact product in @image3 (the uploaded product photo), as staged in the storyboard @image1 — same shape, colour, finish, logo and details as @image3 shows, never changing. Boxes in the product's own colours, as in @image3. STORY (mandatory ending): The person in @image2 HEARS the police (sirens, radios, shouting) before the police reach them. The person in @image2 does NOT walk past officers at the front. They take a DIFFERENT exit at the BACK of the warehouse. They get INTO A VAN with the boxes and DRIVE AWAY. 0–8s: Warehouse, the person in @image2 loads boxes onto a cart. Sirens swell. They hear the sirens, look toward the front, panic. 8–16s: The person in @image2 hauls the boxes to a rear loading dock / back door. Not the main police entrance. 16–24s: Back lot. A van waits. The person in @image2 throws/loads the boxes in, climbs in. 24–30s: Van doors slam. The van DRIVES OFF with the person in @image2 and the boxes. Police arrive too late at the front. AUDIO required: sirens getting louder, shouts, running, van door, engine pull-away. No magic hover. Duration 30s. 16:9.

2 steps
Seedance 2.530s · 16:9
Inspired by @eshal__aion X

Photorealistic live-action comedic premium tech-launch parody, cinematic, 35mm, sleek high-end commercial look, one energetic sequence intercut with glossy product beauty shots. Original — no real company or event name anywhere; the product keeps exactly the logo and markings printed on @image2 and nothing else is branded. @image1 = the main character (identity locked to reference). Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 = the featured product, ANY premium product the user plugs in (a phone, a gadget, a watch, a bottle, anything), shown exactly as its reference — shape, colour, materials and any detail identical; the product is never named in speech. TIMELINE (30 s): 0–3s: interior of a vast, gleaming modern glass HQ. A colleague (clearly different-looking, not resembling @image1) leans in urgently and says to @image1, clear and breathless with precise lip sync: "Yours is the only one left — hurry!" @image1 glances down, eyes widening in panic. 3–6s: @image1 bolts, sprinting across a polished white floor, vaulting a low bench and leaping down a wide staircase, clothes flying. 6–9s: INTERCUT premium beauty shot — @image2 floats and slowly rotates against a soft bokeh backdrop, a clean minimalist caption fades in: "Yours to hold." 9–13s: back to the chase — @image1 races through a huge multi-level glass atrium, sliding across the floor, vaulting a glass railing, leaping across an open void between balconies. A countdown overlay reads "30 seconds". 13–16s: INTERCUT macro beauty shot — extreme close-up of @image2's finest detail, caption: "Every detail." 16–20s: @image1 keeps sprinting, more desperate, dodging through corridors; countdown overlay ticks "10 seconds" then "5 seconds". 20–24s: INTERCUT side beauty shot — @image2 in clean side profile, caption: "Beautiful from every side." 24–28s: @image1 bursts into a packed launch-keynote crowd before a giant glowing stage screen (plain, no logo or brand), skidding to a stop, chest heaving, and holds @image2 up triumphantly. 28–30s: final hero beauty shot of @image2 catching the light, a last clean caption: "Yours. Finally." Then settle on @image1 grinning in the crowd. Hard cut to black. Cinematic commercial polish, believable parkour physics, exactly two hands on @image1. If no @image2 is provided, skip the product beauty shots and keep the chase the same; do not invent a product. AUDIO: fast urgent orchestral/electronic build, running footsteps, whooshes, crowd murmur, the one spoken line and @image1's breathless gasps. Negative: any real company or event name, or any brand, logo or product name that is not printed on @image2; any gendered, ethnic or racial description of @image1; the @image2 product changing shape, colour or detail; identity drift, deformed face, a third hand or extra arm, extra or missing fingers; plastic skin; watermark.

1 step21224.4K
Seedance 2.530s · 9:16
Inspired by ai_lifehack55on X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. The person in every shot is exactly the person in @image1 — face, bone structure, hair exactly as in @image1, age, body. The photo is identity only, not wardrobe. IGNORE the clothes and background in @image1. Never a hair colour different from @image1. WARDROBE: black ink-wash kimono, wide dripping sleeves, wrapped sash, barefoot. The garment is made of wet sumi ink and watercolor that keeps flowing. SETTING: a sheet of white xuan paper. No studio, no floor, no crowd. Real time, 15 seconds, 4:3. Frame 1 is already dancing — never a portrait plate. No slow motion. No on-screen text. One person only. Ink and watercolor bleed from feet, hands, sleeves, hair and every joint. Each step stains the paper. After 5s most of the white is already layered with strokes. Crimson, indigo and gold mix into the black from shot 3 onward. SHOT 1 (0–2.5s) Already mid-step. Weight shifts, arms flowing. Wet ink spreads under each foot. Sleeves throw black ribbons. Full body. SHOT 2 (2.5–5s) Axis changes, low arm sweeps, short spins. Sleeve ribbons blur into clouds. Paper heavily stained. Full body, slight handheld. SHOT 3 (5–7.5s) Rotations and arm spirals. Long ink trails. Crimson, indigo and gold enter the black. Full body. SHOT 4 (7.5–10s) Reverse spin, a short dance jump (not a hop in place), torso twist, another spin. Foreground splashes and airborne ribbons. Full body to medium. SHOT 5 (10–12.5s) The ink is now the world. Two rotations and a large sleeve sweep. They stay visible. No final pose yet. Camera does not pull back. SHOT 6 (12.5–15s) Final pose: weight on one leg, one arm high, opposite sleeve hanging in the air. Body freezes; ink and watercolor keep dripping. Slow constant-speed pullback. Ends as a living sumi-e: paper fibers, uneven bleeds, hand-drawn strokes. No intro, no walking, no mid-pose freeze before shot 6, no empty white paper after 5s, no dancer vanishing.

1 step2719.2K
Seedance 2.515s · 4:3
Inspired by @ai_lifehack55on X

Animate this ink painting. 15 seconds, one continuous shot, no cuts, the camera never moves. Real-time speed, no slow motion. @image1 is the first frame - figure, garment, pose and style are already set. Continue directly from it. They are already dancing and never stop - turning, arms sweeping wide, hair whipping, the painted fabric flaring. Fast and fluid throughout. THE GARMENT KEEPS ITS OWN COLOUR. It is never recoloured or repainted. Ink follows them. Brushstroke ribbons fly off their sleeves and hem in wide arcs and dissolve. Wet spatter flicks onto the paper and pools where their feet land. Colour builds in three ways. First in the air: the trailing ribbons turn crimson, then gold, then violet and blue. Then on the fabric: blooms of those same colours soak into the garment in irregular patches, bleeding at the edges, never covering it evenly. Finally downward: in the last seconds long coloured drips run from the hem onto the paper. By five seconds the paper is already stained with layers of brushwork. Hand-painted throughout - wet ink, soft bleeding edges, visible paper grain. Never photoreal, never 3D. Audio: soft slow instrumental music, a single stringed instrument. No voices.

3 steps2316.3K
Kling 3.015s · 1:1
Cinematic Alpine Vehicle Action

ASSET MAP: @image1 — Storyboard showing the uploaded vehicle in 6 key frames across different camera angles. The vehicle in every shot is exactly the vehicle in @image1: same shape, colour, logos and markings, as a real machine, never a sketch or a generic substitute. @image2 — the member's own vehicle photo, exactly as shown: shape, colour, logos and markings; wherever the storyboard and @image2 differ, @image2 wins. [PROJECT TYPE] Reference-to-video. 30-second cinematic action sequence. High-altitude mountain adventure. [GLOBAL SETTING] Vast snow-covered alpine landscape. Mix of massive slopes, rocky outcrops, sparse alpine vegetation. Golden hour or dramatic daylight lighting. Clear sky, distant peaks. Cold, pristine atmosphere. [ACTION & PROGRESSION] 00-06s: Drone POV — Wide establishing shot of vehicle launching down massive slope. Fast acceleration, spray, power. 06-12s: Close tracking — Technical driving through tight terrain. Speed + precision. Spray catches light. 12-18s: Ground-level tracking — Low angle, vehicle charging past camera. Terrain detail visible. 18-24s: Aerial arc — High drone swooping over open white landscape, vehicle small against scale. 24-30s: Final descent — Silhouette against sunset sky, vehicle carving final turn, momentum and mastery. [TECHNICAL] Seamless transitions between camera angles. No cuts, flowing motion. Cinematic color grade. Snow/dust spray glistens. Clean, athletic, powerful energy. @image1: Reference storyboard showing exact 6-frame progression — match these shots exactly.

2 steps
Seedance 2.530s · 4:3
Inspired by 0x_fokkion X

Produce a 12-second cinematic underground breakdance short in a 16:9 aspect ratio, set at night inside an authentic multilevel concrete parking structure. @image1 is the first dancer. Preserve their facial identity, structure, eyes, brows, nose, mouth, skin, hairline, hair and build exactly. Do not beautify, slim, de-age or restyle them. Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 is the second dancer. Preserve their facial identity, structure, eyes, brows, nose, mouth, skin, hairline, hair and build exactly. Do not beautify, slim, de-age or restyle them. Preserve their gender presentation exactly as shown. Use they / their / them only. Only these two people. No crowd. No extra faces. No split-screen. No on-screen text, no subtitles, no logos. Wardrobe (dance-ready, early-2000s street): @image1 wears loose, dance-ready early-2000s streetwear. @image2 wears loose, dance-ready early-2000s streetwear with thick-soled shoes. Fit garments to each body; do not change their faces. Film everything through an ultra-wide retro fisheye optic with obvious barrel warping and exaggerated spatial depth. Footage like a compact first-generation digital camcorder on one extended arm. Minor compositional errors, horizon wander, hand tremor, walking impacts, inconsistent distance, focus hunting, directional blur. No perfect stabilization. Illuminate almost exclusively with cool fluorescent garage fixtures: faint greenish-white cast, overexposed halos, dense shadows, gray cement. Tactile realism. Raw early-2000s underground attitude. AUDIO — required: garage ambience, sneakers on cement, body hits the floor, a muted boom-bap / breakbeat bed. No dialogue, no lyrics. 0-2 seconds Already in the scene: both dancers crouch inches from the lens beside a dark motorcycle, staring coolly into the glass. Overhead fluorescent halo. Same parking structure: columns, yellow curb, a dark sedan and pale van far back. 2-4 seconds They pop up. Handheld camera circles, rolls and angles around them. @image1 flexes a freeze / bicep pose. @image2 hits a cool stance and acknowledges the operator. Fast. 4-7 seconds Low fisheye on the cement: they break. Windmill, flare, freeze, kip-up energy — real breakdance power moves, not slow-mo. Sneakers scrape. Motorcycle still in the background. Camera stays with them, never a black void. 7-9 seconds They cut across the painted pedestrian crossing, still dancing — a short six-step into a walk. Relaxed handheld reverse tracking deeper into the garage. 9-12 seconds They pivot and stride at the operator; the fisheye magnifies faces, hands, clothes. They drop back into the opening crouch beside the motorcycle — matching the first composition, an invisible loop. End. Negative: a third person, split-screen, editorial flash-cuts of a different face, studio portrait as frame 1, readable text, slow motion.

1 step441.5K
Seedance 2.512s · 16:9
Inspired by Dyyaiworkeron X

IDENTITY: @image1 and @image2 are two different people. Photocopy each face from its tag for the whole 30s. Do not morph. Do not describe them. They/them. @image1 and @image2 are face/identity only, not studio clothes. Surfwear. No other humans. 30 seconds, 16:9. Painterly semi-realistic animation (not live-action photo, not game CG). Deep blue / turquoise water, bright white spray, clear sky, strong sun. NO ON-SCREEN TEXT, captions, titles, logos. Prop: one red-and-white shortboard for @image1. If @image2 rides, a second board of the same family. Leash on the rear ankle, connected to the tail. OPENING: already on the water. Never a studio portrait as frame 0. 0–3s. Ultra-low, almost on the water, looking back from the nose. The red-white board cuts dark blue water. @image1 barefoot on the deck, one foot forward, knees bent. Spray. Camera tracks with the board. 3–6s. Pull back. First full view of @image1 and the forming wave. They drop along the steep face. @image2 is also in the lineup / on a board in the same wave system — readable, same face as the tag. 6–9s. Wide side follow. Huge teal wall. @image1 at the base, high speed. Peak curling, sun through the lip. 9–12s. Closer side. @image1 lowers for the tube. Hair and spray back. Hands for balance. 12–15s. Inside the barrel. Camera in the tube, shooting back. @image1 crouched, sliding the wall. Circular blue cave, sky in the exit. 15–18s. Track backward down the tube center. @image1 stays centered. Water tunnel. Small steering. Rim light. 18–21s. Low hero close on @image1. One hand toward camera. Barrel frames them. Tiny slow-mo ~1s, then normal speed. 21–24s. They exit the foam into sun. Small carve. Real weight and inertia. 24–27s. Wave flattens. @image1 stands taller, still slightly bent, glides the shoulder. Pull back. @image2 visible on the same clean water. No rocks. 27–30s. Camera rises and pulls to a wide aerial. Both of them small on a wide blue sea. Trails of white foam. Ending is CLEAN BEACH SAND — pale sand, no dark cliffs, no reef rocks. They keep gliding. Hold. Cut. PHYSICS: boards stay on the water. Feet do not clip through the deck. Wave rolls forward and tubes. Gravity on spray. SOUND: diegetic water, board, wind. No speech. NEGATIVE: rock cliffs, reef, extra third person, face morph, studio still, photoreal live-action, text, polo shirt, black knit top.

2 steps913.2K
Seedance 2.530s · 16:9
Inspired by aimikodaon X

30-second 16:9 Seedance clip. Identity and costume come ONLY from the attached images: @image2 is the face, @image1 is the full character (body, techwear, palette, katana, scabbard). Photocopy those. Do not describe the character. Do not invent a different face, outfit, or sword. Setting: a vast sci-fi spaceship — stacked hangar decks, grated catwalks, a cargo pit instead of a ravine. Same fight beats as an uphill battle, mapped onto ship architecture. Dozens of enemies on the lower hangar floor, mid catwalk terrace, and upper switchback ramp. Spearmen with energy shafts, swordsmen, riot shields. Survivors pursue upward through the decks. Graphic sci-fi action, strong silhouettes. White-hot blade arcs, crimson contact, cyan trails. Hits have immediate local results; defeated bodies stay down. No energy web, no remote mass-kill. Camera coupled to sword momentum: blade-height whip tracking, orbits, snap zooms. 0–7s SHOT 1: Low wide tracking beside the legs on the hangar floor. Spearmen surge down the ramp, swordsmen through gaps. Iaijutsu draw beats a spear aside, kills the exposed swordsman, ducks an overhead. Neighbor countercuts; snap-zoom on crossed blades, whip upward to the next deck. A shield drives from above; pivot around its edge, cut the wielder, spring past into the blade trail. 7–15s SHOT 2: Rising half-orbit outside the mid catwalk, cargo pit plunging below. Kick off a bulkhead into an aerial spin. Spearman tracks the landing; deflect, reverse-grip in midair, kill a second attacker on descent. Rebound into a rising countercut. Ride a cyan arc into the next shot. 15–22s SHOT 3: Slingshot along the upper switchback ramp, camera retreating just beyond the blade. Shielded reinforcements charge down. Spinning cuts, resheath-and-draw. A shield shoves toward the pit; plant at the edge, cut the wielder. Duck a countercut, gain the next step. Rising white-hot arc eclipses the lens. 22–30s SHOT 4: Burst onto the upper approach. One uninterrupted combination through the remaining force: iaijutsu, reverse-grip, aerial spins. Each kill is blade contact. Last cut onto the upper lip, low finishing stance, blade extended. Wide three-quarter: enemies motionless along the decks. AUDIO: steel, ship hum, impacts. No voiceover. No on-screen text. NEGATIVE: no mountain, no traditional robes, no character redesign, no captions.

2 steps19688
Seedance 2.530s · 16:9
Golden Hour Blush

@image1 is the product only — a makeup stick. Copy its colour, shape, finish and size exactly. Do not name a brand. Do not invent a second unit. @image2 is identity only: face, hair colour and length, skin, eye colour. Preserve their gender presentation exactly as shown. Use they / their / them only. Do not copy wardrobe, background, pose, framing or lighting from @image2. SCENE Golden-hour outdoor selfie, close on the face. Warm low sun from one side. A phone is used as a mirror at the edge of frame. One person only. Handheld, slightly alive, never a studio lock-off. WARDROBE Plain light top. No logos. 0:00-0:03 Already in the shot, looking into the phone. @image1 is in hand. They apply @image1 to their lips, one slow pass. 0:03-0:07 They look into the lens, lips together, then speak one short natural line while holding @image1 near the mouth. Mouth moves only while speaking. 0:07-0:11 They dab @image1 onto the apple of one cheek, then blend with a fingertip. @image1 stays the same object. 0:11-0:16 They lower @image1 toward the bottom of frame so the stick is readable, smile at the lens, and hold. No new product. No on-screen text. LOCKS Same face as @image2 first frame to last. Same @image1 first frame to last, correct one-hand scale, colour unchanged. Exactly one person. No captions, no subtitles, no logos other than the product itself. AUDIO Natural outdoor air and the voice. No music.

1 step
Seedance 2.516s · 9:16
Lovers Quarrel

CHARACTER LOCK — HIGHEST PRIORITY: The two people in every frame are exactly @avatar1 and @avatar2. Preserve their facial identity, structure, eye shape, skin tone, hairline, hair colour, any freckles or distinctive marks exactly as shown, apparent age, build and body proportions — identically throughout. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, de-age or restyle them. Use they/them pronouns throughout. The attached avatars outrank every word below: wherever an attached avatar and this text disagree, follow the avatar. Detailed hands with five fingers visible in every action: punch, kick, kiss, grab, gun handling, tray deflection. No changes to hands across the performance. ASSET MAP: @image1 — Storyboard showing both characters in the lovers quarrel sequence. --- 20-second action-comedy lovers quarrel video. Two characters fighting, kissing, and performing real martial arts choreography with John Wick style flow. LOCATION: Rustic countryside house interior. Wooden beams. Large windows showing green fields beyond. Golden warm daylight streaming through windows. Consistent lighting throughout. TIMELINE (20 s): 0–3s: Wide shot both characters visible. One character attacks with high kicks, right hook, left swing, spinning back kick. Other character evades with sidesteps and lateral slides. Camera tracking both, handheld feel, fast movement. 3–5s: Attacking character drives combo, other character catches momentum and pulls them close. Kiss on right cheek. Slow-motion close-up of the moment. Camera smooth push-in then pull-back. Characters pull apart. Attacking character speaks voice: "DON'T YOU DARE" then immediately attacks again. 5–8s: Attacking character escalates with spinning elbow, knee strikes, rapid punches. Other character evades, redirects, slides along wall. Both characters fully visible. Fast movement across room showing furniture and windows. 8–10s: Attacking character leaping kick, other character ducks, lands with momentum. Kiss on left cheek. Slow-motion close-up. Camera pull-back to wide. Other character speaks voice with calm confidence: "YOU MISSED" then attacking character launches back into attack. 10–13s: Maximum choreography — high kicks, spinning kicks, elbow combos, knee strikes, all connected with no pauses. John Wick style martial arts flow. Both characters move past furniture. 360-degree physical camera orbit around both characters fighting — camera moves full circle in 3D space showing interior details, beams, furniture, and fields outside. 13–15s: Attacking character drives combo, other character catches and spins them smoothly. Kiss on cheek, longer and more tender moment. Slow-motion close-up. Camera pull-back. Characters pull apart. Breathing heavy. Tension building. 15–17s: Both breathing heavy, standing apart. One character relaxed at rest, hands at sides. Other character looks around, spots metal pistol on side table. Walks to it deliberately. Picks it up. Raises it. Points directly at other character. Medium shot both visible. Character speaks voice, sharp and intentional: "NOW THIS GETS INTERESTING" FIRES the pistol. 17–20s: SLOW-MOTION — bullet traveling from barrel. 360-degree physical camera orbit around bullet mid-flight — camera moves full circle in 3D space around trajectory. Other character visible reaching toward nearby table. Orbit completes. RAMP back to full speed. Other character snatches metal serving tray from table. RAISES it in front naturally. Bullet CONNECTS tray — CLANG loud metallic sound. SPARKS EXPLODING around impact. Other character slowly lowers tray. Looks at attacking character. Long beat of eye contact. Then calm smile. Speaks voice confident and steady: "NICE TRY" HARD CUT TO BLACK. AUDIO: Foley only — footsteps on wooden floor, fabric movement, punch impacts, kick whoosh sounds, heavy breathing, natural kiss sounds, gunshot, metal tray clang, spark explosion. NO MUSIC. Professional commercial quality. PERFORMANCE: Both characters move with real weight and inertia. Real breathing. Real martial arts choreography. Photorealistic. No cartoon or stylized. DURATION: Exactly 20 seconds. Hard cut to black at end.

2 steps
Seedance 2.520s · 9:16
Inspired by @Artedeingenioon X

subject_definitions: @image_1 is the first performer. Gender, face, hair, skin and body proportions come entirely from @image_1 and not from this text. @image_1 defines identity only - its clothing, pose, framing, background and lighting are ignored. @image_2 is the second performer. Gender, face, hair, skin and body proportions come entirely from @image_2 and not from this text. @image_2 defines identity only - its clothing, pose, framing, background and lighting are ignored. summary: [reference generation] The target video is a 15-second 16:9 opening title sequence in which @image_1 and @image_2 live separate nights in the same city, never meet, and are connected only by one small yellow paper ticket, cut together as a punk editorial collage and ending on a single title card and a two-face poster frame. retention_analysis: @image_1 (appears in [Shot 1], [Shot 2], [Shot 5], [Shot 6], [Shot 8]): fully_preserved - gender, face, hair, skin and body proportions stay exactly as in @image_1 in every shot. @image_2 (appears in [Shot 1], [Shot 3], [Shot 5], [Shot 6], [Shot 8]): fully_preserved - gender, face, hair, skin and body proportions stay exactly as in @image_2 in every shot. detailed_description: The target video is live-action and photographic, cut and printed like an underground magazine: real people and real rooms, then torn paper edges, xerox grain, rough halftone and offset misprint laid over them. The palette is restrained and graphic - deep black, dirty white, cobalt blue and one sharp yellow. Light comes from fluorescent tubes and street lamps only, never from glow effects. @image_1 wears simple plain clothes in dark and pale tones; @image_2 wears simple plain clothes in dark and pale tones. Both outfits are fixed in cut and colour and only their drape adapts to the body; the gender, face, hair and skin of each performer come from their own reference and never from this text. The two performers never share a room and never touch. [Shot 1] A split composition holds two panes of glass side by side. On the left @image_1 stands inside a late-night laundromat behind its window; on the right @image_2 stands behind the window of a passing tram. Reflections of buildings slide across both faces at the same speed, so the two panes read as one continuous street. The camera holds a static shot. [Shot 2] At 00:02.000, the shot cuts to a close shot of @image_1's hands lifting a folded shirt from a machine, and a small yellow paper ticket falls out of it onto the metal counter. The camera pushes in slowly onto the ticket. [Shot 3] At 00:03.800, the shot cuts to an identical yellow paper ticket held between @image_2's fingers against the tram window, matched in size, angle and position to the previous frame. The camera holds a static shot. [Shot 4] At 00:05.600, the shot cuts to a fast burst of fragments printed as torn magazine panels: an eye, a hand on a rail, two pairs of shoes walking in opposite directions, tram doors closing, a washing drum spinning, overhead wires against a black sky. Photocopied city maps and rough black marker strokes slide between them. The camera shakes slightly at fast speed. [Shot 5] At 00:08.000, the shot cuts to @image_1 and @image_2 standing in the same frame but in separate torn panels. Each figure breaks apart into xerox slices and offset print layers, then reassembles in the opposite corner of the frame. Both faces stay whole and readable while everything around them fragments. [Shot 6] At 00:10.000, the shot cuts to a wide street view as the tram passes directly in front of the laundromat window. For one instant @image_1 and @image_2 are aligned on opposite sides of the glass, both in profile, looking past each other. The camera trucks left with large amplitude at fast speed. [Shot 7] At 00:11.800, the image freezes and the surrounding paper fragments, maps and marker strokes collapse inward and assemble into a single title card. Cut and pasted letters spell "NIGHT SHIFT" across the middle of the frame in dirty white with the second word in sharp yellow. This is the only text in the entire video. [Shot 8] At 00:13.400, the shot cuts to a final poster frame: @image_1 on the left and @image_2 on the right, both turned to face the camera straight on, evenly lit, faces clean and unfragmented and filling the frame, the pane of glass between them and the small yellow ticket centred on it. The camera holds a static shot through the final frame. overall_soundscape: A late city night: a washing machine drum turning and stopping, tram wheels on rail joints, doors hissing shut, a fluorescent tube buzzing, footsteps on wet pavement, paper tearing and the flat snap of a photocopier. non_diegetic_music: A driving instrumental built on a dry drum machine, a single distorted bass line and one repeating minor piano figure at 118 BPM. The arrangement stays at one even, moderate level from start to finish, with hits landing on the ticket falling, the fragment burst, the tram passing and the title card assembling.

1 step2415
MiniMax H315s · 1:1
Inspired by airina_xyzon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, any freckles or distinctive marks exactly as shown, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. A warm hand-painted pastoral anime sequence in a quiet apple orchard at the start of autumn. The person, in their own clothes as in @image1, walks beneath trees heavy with red apples. Golden afternoon sunlight, first hints of autumn, rich painted textures, gentle breeze, nostalgic countryside atmosphere, simple graceful actions, highly detailed. No on-screen text. Shot 1 (0–2s): Wide establishing shot, slow push-in. Rows of apple trees glow in warm autumn sunlight. Frame 1 is already in the orchard — never a studio portrait. Shot 2 (2–4s): Low-angle shot, static. Red apples hang among green leaves against a pale blue sky. Shot 3 (4–6s): Medium rear shot, gentle tracking. The person walks slowly between the trees. Shot 4 (6–8s): Close-up, static. Their legs brush softly through tall grass. Shot 5 (8–10s): Medium profile shot, static. They pause beneath one tree. Shot 6 (10–12s): Close-up, static. A ripe red apple hangs from a low branch. Shot 7 (12–14s): Medium shot, slight push-in. They reach toward the apple. Shot 8 (14–16s): Close-up, static. Their hand gently picks it from the branch. Shot 9 (16–18s): Close-up portrait, static. They look at the apple and smile. Shot 10 (18–20s): Wide side shot, slow pan. Leaves move gently around them. Shot 11 (20–22s): Medium rear shot, static. They continue walking through the orchard. Shot 12 (22–24s): Close-up, static. Sunlight flickers across fallen leaves on the grass. Shot 13 (24–26s): Low-to-high shot, gentle tilt. Branches sway overhead. Shot 14 (26–28s): Wide rear shot, slow pull back. They walk toward the far end of the orchard. Shot 15 (28–30s): Far wide shot, static. The orchard rests beneath soft golden evening light, held to the final frame. CAMERA: slow, simple, graceful. No teleporting. AUDIO: soft breeze, leaves, quiet countryside. No voiceover. NEGATIVE: no live-action photoreal, no modern objects, no text, no watermark, no extra people.

1 step459
Seedance 2.530s · 16:9
Inspired by @FutureVibesAion X

Create a 30-second late-2000s handheld flip-camera vlog. @image1 is the only person — keep @image1's exact face and identity in every frame, no other physical or gender description. Only one person. OPENING — MANDATORY: Frame 1 is already walking toward a tiny beachside meat stand, handheld flip-camera running. Do not open on a studio portrait, grey backdrop, still headshot, or @image1 as a plate. Wardrobe: relaxed beachwear fitted to @image1 — a loose linen shirt, light trousers or shorts, flip-flops and a canvas shoulder bag. Fit these clothes to @image1's body naturally. Keep @image1's hair exactly as the reference shows; wind may move it, do not restyle its length. Keep the one animal from @image2 throughout, exactly as the reference shows (species, size, coat colour and markings), the same animal every frame, natural behaviour for its species. No other people, no vendor face (the stand is self-serve: wrapped cuts of meat on ice, a cash tin, handwritten prices with no readable words). IF NO @image3 IS ATTACHED: the product is a plain unbranded wrapped pack of cooked meat treats taken from the stand's ice — no label, no logo, no text — and it takes @image3's place in every beat below. Style: genuine late-2000s handheld flip-camera vlog. Heavy camera shake, focus hunting, accidental reframing, warm faded colors, digital noise, imperfect zooms, no cinematic look. 0-8s — approach: Walking on sand toward the little beachside meat stand. @image2 starts following at their flip-flops. @image1 laughs and points the camera down. Exact lip sync: "Oh... you're coming too?" 8-16s — buy: @image1 picks up @image3 — the product exactly as shown — same shape, colour, materials, label and logo; nothing invented or redesigned — drops cash in the tin, then takes a bite-sized piece out of @image3 for @image2. @image1 crouches, smiles, exact lip sync: "This one's for you." @image2 sniffs the food. 16-24s — feed: On a small wooden stool in the sand beside the stand, @image1 sets the piece of @image3 down. @image2 eats while @image1 gently pets its head. Exact lip sync: "You were hungry." 24-30s — leave: @image1 walks along the shore carrying @image3 as the same animal @image2 keeps following beside their flip-flops. @image1 laughs at the camera, exact lip sync: "I have company now." @image2 makes a small natural sound as the recording abruptly ends. Audio: natural beach-stand ambience only — surf, wind, plastic wrap, footsteps on sand, cash tin, the animal's small natural sounds, the spoken lines. No music, subtitles, added logos, or cinematic effects. No on-screen text.

1 step403.8K
Seedance 2.530s · 16:9
Inspired by @ZephyraLeighon X

Photorealistic UGC-style product unboxing and review, genuine handheld/tripod footage by a creator, warm cinematic look. Single presenter @image1 (identity locked to reference), sitting at a cozy creator desk — a podcast microphone on an arm, LED-lit shelves with gear behind, a glowing monitor, soft warm accent lights. Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 = the featured product, of ANY kind (a console, a laptop, a phone, a gadget, a handbag, a jacket, a beauty item — anything), shown exactly as its reference: its packaging, shape, colour, materials and any label kept identical and clearly readable. The whole video is a clear but natural showcase of @image2. 0-4s: talking-head — @image1 holds up @image2 in its retail packaging toward the camera with both hands, smiling and explaining what it is. 4-8s: overhead top-down shot — @image1's hands open the packaging and lift @image2 out with slow, deliberate, satisfying movements; exactly two hands. 8-13s: overhead flatlay — @image1 neatly arranges @image2 and every included piece around it, narrating each piece as it is placed. 13-18s: close demonstration — @image1 shows @image2 in use / being handled; tight macro close-ups of textures and details. 18-22s: clean beauty shots of @image2 — slow push-ins and gentle rotations, soft reflections, premium look. 22-26s: talking-head wrap — @image1 seated at the desk holding @image2, giving a warm sign-off. Authentic UGC realism, believable hands (exactly two), real packaging physics. @image1 stays in the exact outfit from their reference, fully clothed and decent. If no @image2 is provided, do not invent a product — skip the product actions and keep the talking-head the same. AUDIO: pure location sound — spoken explanation, cardboard and plastic unboxing sounds, soft room tone; no music. Negative: any gendered, ethnic or racial description; nudity; the @image2 item changing shape, colour or detail; on-screen text, captions, logos or numbers except the product's own label; a third hand, extra arm, extra or missing fingers; identity drift, plastic skin, watermark.

1 step384.2K
Seedance 2.526s · 16:9
Inspired by elowen0c75kon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. A 10-second photoreal vertical 9:16 commercial. No on-screen text, no subtitles, no added logos or brand marks (keep the suitcase's own label and logo exactly as shown; add no other text), no hotel names. @image1 is the rider. Preserve their face, hair, skin, age and build exactly. Do not beautify, slim, de-age or restyle. No other people. @image2 / @product is the suitcase. Lock it exactly as shown: same shape, colour, materials, handle, wheels, proportions, label and logo; nothing invented or redesigned. One suitcase. MOTORCYCLE (shape locked, colour follows the suitcase): a compact futuristic streetfighter / naked electric bike — sharp angular nose, split LED headlamp, black front forks, black disc brake, black wheels, sculpted side panels, under-seat tail, gold-accent LED strip along the mid-body. Body-panel paint takes the dominant colour of @product (the side panels and tank take that colour, whatever it is; black mechanical parts stay black). Same bike every frame until it morphs. No manufacturer badge. Wardrobe on the rider: a simple casual riding outfit with sneakers. Fit to @image1's body. Setting: a luxury desert-resort plaza at golden hour — pale stone paving, tall palms, glass-and-timber hotel canopy, long shadows. Empty of other people. AUDIO — required: electric bike hum, tyre on stone, a mechanical folding whoosh as the bike becomes the case, suitcase wheels on stone. No dialogue, no lyrics. 0-3 seconds Already in the scene: @image1 rides the colour-matched streetfighter slowly toward camera across the plaza. Tracking three-quarter, low. Palms and hotel behind. 3-5 seconds They slow and put a foot down, still astride. Camera orbits slightly. Bike panels clearly show @product's colour. 5-7 seconds They step off. The bike compresses and folds in one continuous CGI move: wheels tuck, body panels collapse inward and become @product standing on its own wheels, handle rising. Same colour throughout. 7-8 seconds @image1 takes the telescopic handle of @product. 8-10 seconds They walk away toward the hotel entrance, pulling @product. Rear three-quarter. Empty plaza. End. Negative: extra people, crowd, BMW badge, readable signage, split-screen, a different suitcase than @image2, studio portrait as frame 1.

2 steps15143
MiniMax H310s · 9:16
OCT pipeline

Exactly 15 seconds, 16:9. THIS IS A VIDEO GAME, not live-action, not a real camera, not a real person on a real street. Look: modern open-world crime-game cinematics. Pre-rendered game engine. Stylized PBR, slight subsurface on skin but clearly CGI characters, game anti-aliasing, in-game depth of field, game lighting, no film grain, no documentary shake. Think third-person console gameplay trailer — never photoreal street photography. @image1 is the playable character's FACE only — lock that face on a game-character body. Do not turn them into a real-world pedestrian. Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 is the jacket they wear as in-game armor/clothing. Fit that exact jacket onto the game body. Do not change the jacket design, cut, colours or graphics. Only the drape. Frame 1 is already in-game, third-person camera behind the character on a New York–like city street. Never a studio portrait. Never a real iPhone clip. Camera: locked third-person follow, over-the-shoulder, typical game camera boom, slight analog stick drift, no handheld documentary. City: game-NYC — yellow taxi models, sidewalks, steam vents, crowds as NPCs (no readable faces), traffic AI, shopfronts, skybox. Optional simple game HUD: tiny minimap corner, no brand names, no titles. 0-4s — already walking. Game camera behind. Jacket fully visible. NPC traffic. 4-8s — cross the street on a walk light. Camera holds third-person. Jacket reads front and back. 8-12s — turn onto a wider avenue. Game sun, specular on the jacket. Same face, same jacket. 12-15s — keep walking. Half-orbit game camera, then settle behind. Abrupt end. Audio: game-mix city bed, footsteps, engines. No music, no subtitles, no added logos beyond the jacket's own, no real-world film tone. No on-screen text except a tiny generic minimap. Duration: exactly 15 seconds. Aspect ratio: 16:9.

1 step
Seedance 2.515s · 16:9
Inspired by itsSaira_1on X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. Create a 30-second 16:9 2D hand-painted storybook animation — not photoreal, not live-action, not 3D CGI. Visible brush, soft painted edges, night-forest colour. The person in the attached reference is the only person. They are a fairy in this scene: same face as @image1, plus delicate translucent wings. OPENING — MANDATORY: Frame 1 is already a close-up of a hanging bell-shaped glowing flower on a mossy log, bare feet stepping into frame. Handheld-feeling but painted. Do not open on a studio portrait, grey backdrop, still headshot, or the attached image as a plate. Wardrobe, locked, gender-neutral: hand-knitted blue tunic, loose dark trousers, plain blue wool cap, small brown leather pouch on a strap, barefoot, translucent fairy wings. Fit these clothes and the wings to the attached person's body. No dress, no skirt, no gown. Hair stays as in the attached reference — mist can dampen it, do not recut or recolour it. Setting: enchanted night forest. Deep blue trees, mossy log, many hanging bell-shaped flowers on thin vines, floating pink purple and blue glow-lights, fog, tiny sparkles. One person only. 0-6s — hook: Bare feet on wet moss. A large pale-lilac bell flower hangs in the foreground, glowing softly. They step along the log toward it. Wings flutter. 6-14s — approach: They walk the log in the knitted tunic, trousers and cap, pouch at their side. Painted bokeh lights behind. Slow move toward the hanging flower. 14-22s — the key: They crouch, open the pouch, take out a small ornate golden key. Look at the flower. Reach toward it. 22-30s — glow: They touch the flower with the key. The bell lights from inside, sways, brighter. Hold on the glowing flower as they watch. No on-screen text. Cut. Diegetic forest night only: soft wing flutter, faint chime when the flower lights, breeze. No music, no speech, no subtitles, no logos, no watermark. Duration: exactly 30 seconds. Aspect ratio: 16:9.

1 step931.1K
Seedance 2.530s · 16:9
Inspired by TaliaAarizon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image2. 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, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. Use they/them throughout. No other people. @image2 is face and identity only, not the outfit. @image3 shows the garment only: if anyone is wearing the garment in @image3, that wearer is not in this film — never take a face, hair colour, hairstyle, skin tone or body from @image3. The only person in the film is @image2. @image3 is the product at the START, in the original colour and material of the member's garment. @image1 is the product at the END (purple flowers). Address references only as @image2, @image3, @image1. Do not describe the person. Do not name the product. HANDS: both hands visible in every shot. Arms in frame, not hidden in the gown, not cropped, not missing. Fingers readable. 20 seconds, 16:9. Surreal ultra-realistic haute couture fashion film. Bright minimalist white studio. Giant purple peony halo behind them. 0–4s. Wide: @image2 stands full-body, both hands visible. They wear the product exactly as @image3 — still in its original colour and material. The giant purple peony halo forms behind them. 4–12s. The product transforms from the hem upward: purple flowers grow from the bottom of the gown toward the bodice, replacing the original fabric. Transformation is only bottom-to-top. Hands stay visible. Slow push-in. 12–16s. The product is now fully the floral form in @image1. Sculptural purple-flower formations (heart, wings) move around them. Both hands still in frame. 16–20s. Final wide hero: @image2, fully floral product from @image1, giant purple peony halo, both hands visible, white studio. Hold. CAMERA: slow push-ins, full-body so hands and hem stay in frame. NO ON-SCREEN TEXT. NEGATIVE: missing hands, hidden arms, flowers from frame 1, top-down transform, extra people, feathers that are not on @image3, added text, face morphing. Sound: studio ambience, soft petal motion, quiet luxury finish. No lyrics.

2 steps1593.9K
Seedance 2.520s · 16:9
Inspired by @Strength04_Xon X

CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or reinterpret it. Do not beautify, slim, de-age or restyle them. Use they/them throughout. No other humans. @image1 is face and identity only, not the outfit. Dress them for a cold night at a station. Do not describe their face, hair, body, or the clothes beyond that. Address the reference only as @image1. 30 seconds, 16:9. Photoreal cinematic science-fantasy becoming high fantasy. No on-screen text, captions, logos, or watermarks. 0–5s. An abandoned underground railway station, empty at midnight. Dust in flickering lights. @image1 waits alone on the platform. An old train arrives without sound. Its windows show a glowing magical forest instead of passengers. 5–10s. Doors open by themselves. @image1 steps inside. Camera follows behind as the doors close. The train accelerates through the dark tunnel. Tunnel walls transform into living roots, floating lights, and deep forest. 10–16s. The train bursts out of the tunnel onto tracks running through a vast mythical forest. Giant ancient trees, bioluminescent moss, fairies in the air, mythical creatures moving beside the rails. @image1 looks through the window. 16–22s. Deeper into the fantasy world: more creatures and fairies along the route, impossible bridges of light through the canopy, the forest opening into a hidden realm. Camera beside the train. 22–27s. The train slows and stops in a starlit forest glade. @image1 steps out. In front of them a living arch of trees slowly opens, warm gold light pouring through onto their face. Fairies drift in the beam. No other humans. 27–30s. Camera pulls rapidly back from the glade → the whole enchanted forest comes into view → the train leaves along its glowing track → final shot: the tiny glowing train crossing the magical forest beneath a vast starry sky. CAMERA: slow suspenseful opening, smooth tracking, dynamic acceleration at the tunnel-to-forest transition, wide shots of the forest, controlled final pullback. NEGATIVE: cartoon, anime, low-quality CGI, face morphing, identity drift, extra humans, text, subtitles, logos, watermark, moon-base, outer space, lunar station.

1 step521.6K
Seedance 2.530s · 16:9
Clips on this page (40)