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 18

Made with OpenClips.AI

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

Inspired by @KrevixAion X

Create a 10-second continuous ultra-photorealistic first-person POV transformation sequence. @image1 is a clean studio shot of the reader's vehicle - the rebuilt car must match it exactly in body shape, proportions, stance, colour, paint finish, grille, lights, glass and wheels. Ignore its background. @image2 is a storyboard sheet - a shot plan, not a scene. Read it only for framing, camera angle and lighting. NEVER reproduce its grid, panel borders, gutters or numbers. The finished video is one full-frame continuous shot. Sunny agricultural field, cloudless blue sky, bright daylight, forearms and matte-black work gloves visible throughout. One continuous shot, no cuts. 18-20mm ultra-wide lens, aggressive speed ramps, realistic physics, blockbuster VFX. 0:00-0:01 Camera snaps upward. A gigantic rusted mud-caked wreck falls from the sky toward the POV, violently rotating, filling the frame. 0:01-0:02 Both gloved hands thrust forward. The wreck STOPS one metre from the lens. Hard cut from extreme speed to bullet-time stillness. Dust and dry grass freeze in mid-air around it. 0:02-0:03 Right hand clenches into a fist. The wreck disassembles - NOT an explosion into rubble. Around twenty large intact components separate and hang suspended around the POV in a 3D exploded view. 0:03-0:04 Left hand sweeps sideways. The rusted parts disintegrate into metallic dust and blow away across the field. The bare chassis stays floating in bullet time. 0:04-0:05.4 Both hands spread apart. Speed ramp. Brand-new components in the exact colour and finish of the vehicle from @image1 fly in from behind the camera and from all directions, passing extremely close to the lens. A huge new wheel rushes straight at the lens; one glove redirects it sideways at the last second and it slams onto the hub. An engine drops from above and locks in. 0:05.4-0:06 Assembly accelerates. Wheels, glass, lights and body panels converge and magnetically lock into place. The final bonnet flies over the POV camera by centimetres and snaps into position. 0:06-0:10 HERO REVEAL. All movement stops. Directly ahead stands the fully assembled vehicle from @image1, pristine, hard sunlight raking across it. The hands lower toward the bottom of frame. Dust settles through the light while the camera makes a slow controlled push toward it. Hold to the end. Continuity: same POV, same hands, same field, same lighting. The wreck transforms spatially into the new vehicle without teleportation. The vehicle keeps exactly the badges, grille emblem and lettering it has in @image1, and nothing is added. Audio: wind across the field, the roar of the falling wreck, a hard low impact as it stops dead, metallic groans during disassembly, a rush of air as parts fly in, heavy clunks as components lock together, then settling silence with birdsong. No music, no dialogue. No extra people, no added text, no grid, no numbers, no logos other than the vehicle's own, no cuts.

3 steps21.4K
Seedance 2.010s · 16:9
Inspired by im_shahid7on X

Generate a short animated video of two people, one enormous wardrobe, and a total disagreement about whether it contains anything to wear.

4 steps25134
Seedance 2.015s · 16:9
Inspired by ivanka_humeniukon X

PLAYFUL OUTFIT CHOICES → QUICK GETTING-READY MONTAGE → CLOTHES APPEAR THROUGH CLEAN EDITS → COMPLETE STYLED LOOK → LIVELY FINAL TURN SHOT STRUCTURE: exactly 10 shots, exactly as listed, filling the full 20 seconds with the timing given in each shot heading. REFS: @image1 = character sheet. The left portrait controls facial geometry, features, skin texture and expression range inside the hairline. The right full-body panel controls height, body proportions and the casual home clothes. Every shot uses the same face, body and hair from @image1, with no drift or reinterpretation in any shot. Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 = exact wardrobe reference. Controls the design, colour and materials of the moss-olive sweater, olive satin lace mini skirt (or shorts), brown belt with gold buckle, chocolate leather boots, structured tote and gold jewellery. Wherever this prompt says "skirt", it means this satin-and-lace bottom exactly as shown in @image2 — a mini skirt or tailored mini shorts; if a skirt would not suit their gender presentation as shown in @image1, render the same satin-and-lace piece as tailored mini shorts. The gold hoop earrings are worn only if @image1 shows them wearing earrings. @image3 = exact environment reference. Controls the dressing room, doorway framing, mirror, vanity, sconces and camera geometry. ACTIVE REFERENCES: @image1 strict character identity · @image2 strict wardrobe design · @image3 strict environment. CAMERA AND EDITING LOCK: • One physical vertical phone camera remains firmly locked to the same tripod head in the doorway for the entire clip. • The camera position, tripod height, frontal 0° angle, 47° field of view, focus, exposure and lens character remain identical throughout. • The doorway edges, mirror, vanity and wall sconces keep the same size, perspective and alignment in every shot, exactly as in @image3. • Every shot boundary is a one-frame instantaneous straight HARD CUT. • Shot changes happen exclusively through editing. • Each new shot begins after the subject has already reached their new distance or completed the hidden wardrobe change. • Every garment, bag and accessory remains fully visible at the final frame of its shot, with room visible around its edges. • The camera records only the action inside each listed shot. The spatial repositioning between shots happens during the omitted edit interval. • Character, wardrobe and environment remain consistent across all ten shots. GLOBAL STYLE NOTES: • look: photorealistic live-action fashion-blogger reel, realistic skin and hair, detailed knit fibres, natural satin reflections, soft lace movement and weighted leather; warm light from two matching wall sconces; natural phone-camera exposure • starting look: the casual home clothes from @image1, bare feet • sweater proportion: slightly longer and fuller than a regular oversized sweater, with thick chunky knit, dropped shoulders, generous torso volume, balloon sleeves and a ribbed hem reaching the upper hips when loose • final styling: the satin skirt is worn high at the natural waist, approximately 2 centimetres above the navel; the lace edge ends high on the upper thighs. A centred 18–20 centimetre section of the sweater is tucked into the front waistband beneath the brown belt. The front forms a soft blouse above the gold buckle; the sides and back remain loose and voluminous over the hips. The complete lace hem stays visible. • performance: they treat the lens like a friend watching them get ready. Their eyes move naturally between each item and the viewer. Small smiles build and fade, their shoulders stay loose, and their body keeps a light rhythmic energy. • acting — Subject: scene direction: share the fun of assembling the outfit and save the complete silhouette for the final cut fuel: they enjoy showing the viewer how the separate pieces come together goal: reveal a short high-waisted silhouette while preserving the sweater's relaxed volume obstacle: the loose sweater initially conceals the waist tactic: tease individual pieces, dress through jump cuts, then reveal the completed waist styling channel: garment presentation, dressing, skirt adjustment, perfume, jewellery and final turn gaze always engaged with the item or the viewer, natural blink cadence TIMELINE (20 s): 0–3s: shots 1 and 2 — they present the satin-and-lace skirt or shorts, then the sweater, to the lens. 3–6s: shots 3 and 4 — the belt held close with the gold buckle centred, then one hair flip. 6–10s: shots 5 and 6 — the tote presentation, then they pull the sweater on in one continuous action. 10–15s: shots 7 to 9 — the perfume spray, the high-waisted satin piece appearing under the loose sweater, then the jewellery. 15–20s: shot 10 — the complete outfit from @image2, the turn in place and the smiling over-shoulder pose held to the final frame at 20s. SEQUENCE LIST: SHOT 1 HOOK (0–1.5s) — skirt presentation • first_frame: the subject stands centred at the presentation distance, framed from crown to mid-thigh, wearing the casual home clothes from @image1. They hold the olive satin lace mini skirt by both ends of its waistband against their waist. • camera: fixed tripod camera, frontal 0°, eye level, 47° field of view • action_visual: they lift the skirt once, lightly shift their hips and let the satin and lace sway naturally • acting: they check the skirt against their body, look into the lens and give a brief bright smile • exit: they hold the complete skirt still and fully visible (INSTANT STRAIGHT HARD CUT TO) SHOT 2 SETUP (1.5–3s) — sweater presentation • camera: the exact same locked camera • action_visual: they hold the moss-olive sweater against their torso by both shoulder seams. The sweater appears slightly long and generously oversized, with the ribbed hem reaching their upper hips and both balloon sleeves hanging with realistic knit weight. • acting: they glance down at the sweater, give it one light bounce and reconnect with the viewer through a small smile • exit: they hold the complete sweater still in front of them (INSTANT STRAIGHT HARD CUT TO) SHOT 3 SIGNATURE (3–4.5s) — belt detail • camera: the exact same locked camera; the subject is already standing closer when the shot begins • action_visual: they hold the brown leather belt horizontally between both hands, with the gold buckle centred close to the lens. The belt stays fully visible and their eyes remain visible above it. • acting: they align the buckle, look over its top edge at the viewer and let one corner of their mouth rise • exit: the belt remains steady at the same distance (INSTANT STRAIGHT HARD CUT TO) SHOT 4 RHYTHM (4.5–6s) — hair flip • camera: the exact same locked camera; they are already back at the presentation distance • action_visual: they turn their head once and flip their hair over one shoulder. The hair moves with natural weight and settles back into its own style. • acting: they return their gaze to the lens with a quick spontaneous grin • exit: their hair finishes settling (INSTANT STRAIGHT HARD CUT TO) SHOT 5 RISING (6–7.5s) — tote presentation • camera: the exact same locked camera; they are already standing closer when the shot begins • action_visual: they hold the structured chocolate-brown tote in front of their chest. The complete bag and both handles stay inside the frame, and their face is visible naturally between the handles. • acting: they tilt their head slightly, check the viewer through the handles and smile • exit: they hold the tote level and fully visible (INSTANT STRAIGHT HARD CUT TO) SHOT 6 RISING (7.5–10s) — putting on the sweater • camera: the exact same locked camera; they are already back at the presentation distance • action_visual: the shot begins with the moss-olive sweater already above their head. ONE CONTINUOUS UNCUT ACTION — they pull it down, guide both arms through the balloon sleeves and let the thick ribbed hem settle at their upper hips. The sweater hangs slightly long, soft and voluminous around their torso. Their hair emerges from the collar and falls back into the same style. • acting: their eyes immediately find the lens when their head clears the neckline; they exhale through a small smile and lightly shake their hair free • reaction: the loose sweater temporarily hides the waist • exit: both hands release the hem and the garment settles (INSTANT STRAIGHT HARD CUT TO) SHOT 7 SIGNATURE (10–11.5s) — perfume • camera: the exact same locked camera; they are already standing closer when the shot begins • action_visual: wearing the sweater, they hold a small clear perfume bottle beside their neck, lift their chin and press the atomiser once. A fine realistic mist appears beside their neck and disperses. • acting: they close their eyes during the spray, lower their chin with a soft smile and look back toward the viewer • exit: the perfume bottle remains in their hand while the mist dissipates (INSTANT STRAIGHT HARD CUT TO) SHOT 8 TWIST (11.5–13.5s) — high-waisted skirt appears • camera: the exact same locked camera; they are already standing farther back when the shot begins, framed from crown to upper thighs • action_visual: after the cut they already wear the olive satin lace mini skirt beneath the loose sweater. The waistband sits 2 centimetres above the navel and the lace edge ends high on the upper thighs. They grip both side seams, make one small upward adjustment and release the waistband. The sweater remains loose over the waist. • acting: they check the short leg line, shift their weight lightly onto one hip and look up with a pleased smile • reaction: the high waistband and short lace hem lengthen the visible leg line • exit: both hands rest naturally beside their hips (INSTANT STRAIGHT HARD CUT TO) SHOT 9 SIGNATURE (13.5–15s) — jewellery • camera: the exact same locked camera; they are already standing closer when the shot begins • action_visual: the gold collar necklace, ring and bangle are already in place. They close one chunky gold hoop earring with both hands — or, if @image1 shows no earrings, straighten the gold collar necklace — then lower their fingers. • acting: they use the lens like a mirror, tilt their head to check the jewellery and give the viewer a quick playful smile • exit: their hands lower completely and their face remains centred (INSTANT STRAIGHT HARD CUT TO) SHOT 10 RESOLUTION (15–20s) — complete outfit reveal • first_frame: the subject is already standing at the full-body reveal distance, centred from styled hair to both boot soles. They wear the complete exact outfit from @image2: slightly long voluminous moss-olive sweater, very short high-waisted olive satin lace skirt, centred brown belt, chocolate knee-high slouch boots and all gold jewellery (earrings only if @image1 shows them). The centred front section of the sweater is tucked beneath the belt; the sides and back stay loose. They hold the brown tote in their left hand. • camera: the exact same tripod position, frontal 0°, eye level, fixed 47° field of view; the background geometry matches every previous shot exactly • action_visual: they hold the frontal outfit view for half a beat, shift their weight with a small rhythmic bounce and turn in place through a side view into a back three-quarter view. The skirt and lace respond with light delayed movement, the sweater keeps its soft volume, the boots crease naturally and the tote swings with realistic weight. They finish by turning their head over their shoulder toward the lens. • acting: they reconnect with the viewer during the turn; their cheeks lift and a warm natural smile grows as they reach the final pose • reaction: the loose sweater now frames the high waist through the precise front tuck, completing the silhouette • exit: they hold the smiling over-shoulder pose to the final frame at 20s AUDIO: one continuous upbeat instrumental fashion track. Every instantaneous straight cut lands exactly on a musical beat. Layer fabric movement, one perfume spray, a jewellery click, grounded boot sounds and the weighted movement of the tote.

4 steps642.4K
Seedance 2.520s · 9:16
Inspired by Urwa_345on X

Create an ultra-realistic premium commercial advertisement using the provided product image only as the exact visual reference for the product’s identity and appearance.

2 steps30042.6K
MiniMax H310s · 9:16
Inspired by airina_xyzon X

Botanical watercolour illustration with refined ink linework throughout: visible paper tooth, granulating washes that dry darker at their edges, a fine ink line that varies in weight and breaks where forms turn away, soft natural colours, luminous humid atmosphere, richly detailed foliage and glass architecture, and expressive but subtle facial acting. No text, no logos, no captions, no watermark. @image1 is an absolute identity lock for the keeper: face, body, hair, apron, tunic, trousers, shoes, tool loop, materials and colours are taken from it exactly, with no drift and no reinterpretation in any shot. @image2 is an absolute identity lock for the visitor, on the same terms: face, body, hair, cardigan, knit top, trousers, shoes and shoulder satchel exactly as shown. @image3 is the location. All architecture, planting, materials, lamp positions, canopy and lighting direction come from it, and every shot stays inside that one hall. Eight shots in sequence, in this order, each running about as long as the others. TIMELINE (30 s): 0–4s: Shot 1. The keeper stands at one side of the long planting table. Directly across from them, on the far side of the table, stands the visitor. Between the two of them sits the small closed ceramic pot. Both lean in over it at the same moment, eyes on the lid, as if something inside has just stirred. 4–8s: Shot 2. The keeper places one hand lightly on the lid of the pot and looks up at the visitor, as if inviting their attention. The visitor leans forward slightly, hands resting on the table edge, eyes fixed on the pot. 8–11s: Shot 3. The keeper slowly lifts the lid with one hand. The visitor stays opposite them and leans in a little further. Both direct all of their attention into the opening pot, faces showing anticipation. 11–15s: Shot 4. Inside the pot is a tiny glowing seedling. The visitor's eyes widen and their lips part in amazement. The keeper smiles softly, pleased by the reaction. Light catches on the glazing overhead and on the leaves around them. 15–19s: Shot 5. The keeper gently turns the pot with both hands so the visitor can see the seedling better from the front. The visitor keeps both hands on the table and follows the movement carefully with their eyes. The relationship stays clear: the keeper is presenting, the visitor is observing. 19–22s: Shot 6. The visitor slowly lifts one hand, palm open, and holds it near the glowing seedling without touching it. The keeper watches that hand attentively, standing still, as if making sure they are gentle. The glow softly lights both faces from below. 22–26s: Shot 7. A small butterfly settles on the rim of the ceramic pot. The visitor smiles with delighted surprise and turns their eyes toward it. The keeper shifts their gaze to the butterfly as well, sharing the quiet moment. 26–30s: Shot 8. The keeper and the visitor now stand side by side at the end of the table, facing down the lush aisle of planting, the glowing pot resting on the table beside them. The camera pulls slowly back to reveal the full hall, ending on that wide at the final frame at 30s. CAMERA Calm, still, observational framing, held at standing eye level. Each shot carries at most one slow simple move. No handheld shake, no whips, no zooms, no punch-ins, no orbiting or arcing around the table, no speed changes. The only camera move in the piece is the slow pull back in the final shot. LIGHTING Warm horticultural lamplight from overhead through the leaves and cooler pale light down through the hazed canopy, exactly as established in @image3, constant from first frame to last. The seedling's own glow is the single soft light that grows in the frame once the lid is off, lighting hands and faces from below. AUDIO Quiet diegetic room atmosphere only: a faint ventilation hum far off, water moving somewhere in the beds, the small scrape of the lid lifting, the ceramic base turning against the table, leaves shifting, and one soft flutter as the butterfly lands. No music, no voices, no narration, no sound effects beyond these. HARD RULES The keeper is locked to @image1 and the visitor to @image2 in every frame either appears in. No drift, no reinterpretation, no substitution, and never a third person in frame. The keeper and the visitor stay on opposite sides of the planting table for the first seven shots and only come to the same side in the final shot. Every movement has a visible beginning, middle and end inside its shot: the lid is lifted by lifting it, the pot is turned by turning it, the hand is raised by raising it. Nothing is already done and nothing appears mid motion. Neither of them ever touches the seedling. The pot stays on the table at all times and is never picked up or carried. The glow belongs to the seedling only. Nothing else in the hall glows, and no plant is luminous. The light in the hall never changes level or direction; the only change in the frame is the seedling's glow arriving when the lid comes off. The butterfly appears in the seventh shot and not before, arrives by flying in and landing, and stays small and ordinary. No screens, no instrumentation, no control panels, no uniforms, no insignia, no spacecraft exteriors, no visible technology beyond the lamps and the canopy structure already in @image3. No text, no captions, no subtitles, no titles, no logos, no watermark anywhere in frame.

4 steps251
Seedance 2.530s · 16:9
Inspired by ZephyraLeighon X

A 20-second 16:9 1909 London archive film. Sound on. PHYSICS — MANDATORY: @product is a real solid object. Gravity. It NEVER floats, hovers, orbits, or magically rotates by itself. On the cobbles it stays STILL until a hand lifts it. It only turns if fingers physically turn it. No 360 product spin. No CGI turntable. No levitation into anyone's palm. STORY: Foggy London street, horses and carriages only, no buses. @product lies still in the MIDDLE of the street. A passer-by in a long Edwardian coat sees it, kneels, picks it up with gloved hands (the phone does not jump into their hand). Others reach to touch it. A gathering forms. 15–18s: The passer-by holds it still and accidentally taps; selfie on the screen. The phone stays in their grip. 18–20s: TWO bystanders panic and RUN AWAY. The passer-by keeps holding @product or drops it — it does not spin in the air. PRODUCT LOCK: exact product from the attached stills. Same shape, colour and camera layout as the stills, same markings. Do not redesign. AUDIO: projector, hooves, shutter, running feet. No dialogue. 20s 16:9.

2 steps502.2K
Seedance 2.520s · 16:9
Inspired by @ZephyraLeighon X

Generate a royal fashion film in a palace, wearing an outfit you choose.

2 steps14213.3K
Seedance 2.515s · 9:16
Inspired by azed_aion 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 15-second photoreal 16:9 urban time-lapse. Night. Locked camera. No on-screen text, no subtitles, no logos, no watermarks. The mural face is exactly the person in @image1: same facial identity, structure, eyes, brows, nose, mouth, skin, hairline and hair. Do not beautify, slim, de-age or invent a different face. No other people. No painter. No extra spray cans. No paint bucket. Setting: a narrow city alley at night. Left: a long brick wall, two-tone brown over peeling white, rusted electrical boxes, a downpipe. Right: a wet sidewalk and a live street. Warm sodium streetlight. Fixed wide shot, same framing the whole clip. THE CAN: from frame 1, exactly one spray-paint can stands on the sidewalk at the base of the wall. It is the only prop. That single can sprays by itself — it tips, hisses, and paints the mural. No hand holds it. No second can. TRAFFIC: cars drive past on the street to the right. Headlights can sweep the lens and briefly flare the frame. AUDIO — required: night traffic, one spray-can hiss and rattle, no dialogue, no lyrics. 0-3 seconds Already in the scene: empty wall, boxes, wet pavement, one spray can standing on the sidewalk. The can starts to spray. A car may pass. 3-8 seconds The lone can sprays in time-lapse: cyan, magenta, yellow and violet hit the wall, then the outline of @image1's face in graffiti style. Still only one can. 8-12 seconds The portrait fills in: @image1's face as a large mural, photoreal identity under bold graffiti colour-blocking, tropical flowers and birds. The same single can keeps spraying. 12-15 seconds Hold the finished mural. The one can rests on the sidewalk. Night traffic. End. Negative: extra cans, a paint bucket, a visible person or painter, a second face, MiniMax or Hailuo logos, subtitles, studio portrait as frame 1.

1 step14488
MiniMax H315s · 16:9
Inspired by @KrevixAion X

A dark-fantasy luxury product reveal. A muscular blue-skinned genie bursts out of an ornate bronze lamp in a swirl of magical smoke, lunges straight at the camera for an intense close-up, then floats back and conjures a glowing vortex of energy between their hands. Out of that vortex, a luxury wristwatch slowly takes shape — case, crystal, hands and strap or bracelet of your own watch all materializing piece by piece — before the genie presents it and dissolves back into the lamp, which then vanishes entirely, leaving only the watch glowing in the dark.

1 step17761
Seedance 2.510s · 16:9
Inspired by @Weeleey6on X

Subjects: @image_1 is the first frame of this video and the only reference. The two performers in @image_1 are the whole band - the one holding the pastel-pink guitar is the guitarist, the one holding the baby-blue bass is the bassist. Identity: both performers in every shot are exactly the two people in @image_1 - faces, skin tone and gender presentation unchanged, never masculinized or feminized, never merged, swapped or duplicated, and the guitarist always keeps the guitar while the bassist always keeps the bass. The hair of each keeps exactly the length, texture and colour shown in @image_1: never lengthened, never restyled, and long hair is never added to a short haircut. Wardrobe and set: the matching pink school-uniform sets, the accessories, the instruments, the pastel practice room, the pink amplifier and the whole colour palette come from @image_1 and stay unchanged for the whole video. Style: high-key candy-coloured pop promo - soft bloom, gentle film halation, glitter specks in the light beams, saturated pastels with no muddy shadows. Vertical framing, one camera move per shot, hard cuts and no dissolves. Shot 1: The video starts exactly on @image_1 and the camera pushes in. Both performers hit the first chord on the downbeat and the tulle curtain lifts behind. <a big clean electric chord, the amplifier humming> (bubblegum pop at about one hundred forty beats per minute lands on the downbeat) Shot 2: A close shot travels up the neck of the pink guitar to the face of the guitarist, a fast bright riff, then a grin straight down the lens. <fast picking on wound strings, a pick scraping once> (the guitar line carries the melody) Shot 3: A low tracking shot passes the bassist, who leans into the microphone for a wordless harmony and turns once on the spot as the first pale pink confetti falls. <a round warm bass line, an airy wordless harmony, confetti fluttering> (drums come in punchy underneath) Shot 4: The camera arcs around both performers, back to back at the centre of the room with heads tipped back, confetti settling in the hair of each. <guitar and bass locked together, a shared laugh> (the chorus opens up wide) Shot 5: A rooftop at dusk under a cotton-candy sky. Both stand at the railing seen from behind with the cases on the ground and bump shoulders once as the city lights come up, the two figures small in the lower third and the sky filling the rest. <open wind, distant city hum, a last cymbal ring> (the song lands on its final beat and stops clean) Continuity: only the two people from @image_1 exist in this entire video and no additional figure is ever visible, not even in the distance. Same uniforms, accessories, hair length and instruments from the first shot to the last, five fingers on every hand. There are no lyrics and no words in any language anywhere in the audio - wordless harmonies only. Constraints: Keep it subtitle-free and avoid generating any text or subtitles anywhere. Do not generate a logo. Do not generate a watermark. Do not generate duplicate performers or a twin effect.

2 steps
Seedance 2.015s · 1:1
@rovvmut_made this on OpenClips

ONE HANDHELD SELFIE-STYLE UGC VIDEO. VERTICAL. 20 SECONDS. ONE PERSON ONLY. ONE CONTINUOUS TAKE. ASSET MAP - every reference is bound here and cited by tag below: @avatar - the person. This is who is on camera; face, hair, skin and body come entirely from @avatar and never from this text. @image_1 - the reference sheet. It shows the same one device twice: closed on the left, and opened out flat on the right. The device in this film is that device, in those two states. CHARACTER LOCK - HIGHEST PRIORITY: the person in every frame is exactly the person in @avatar. 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 from the first frame to the last. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. Use they / their / them only. No face changes, no identity drift, and no other people anywhere in frame. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached references outrank every word written below them. Wherever a reference and this text disagree, follow the reference. DEVICE LOCK: the object in their hands is exactly the device in @image_1 - closed as it is shown on the left of that sheet, open as it is shown on the right. Its shape, proportions, thickness, materials, finish, colours and every printed and engraved detail come entirely from those two references and never from this text. Closed, it is visibly thicker and wider than an ordinary single-screen phone, exactly as thick and as wide as it is on the left of @image_1. Its two halves are stacked face to face like a shut book standing on its end, and the hinge spine runs vertically down one long side. Open, it is one single wide screen that fills both hands, with a faint crease running down the middle of the glass, exactly as on the right of @image_1. Never redesign it, never re-letter it, never recolour it, never add a logo, badge, label, sticker, lettering or symbol that is not already on the references, and never remove one that is. There is only one device in the whole video. THE TWO OUTER FACES ARE NOT THE SAME - this matters: when the device is closed it has two different outer faces. One outer face is the back: the camera module and any mark it carries, exactly as on the left of @image_1. The opposite outer face is the cover display: a lit glass screen showing a wallpaper, with no camera module and no logo on it at all. The camera module exists on one face only. Never repeat or mirror the camera module onto both faces, never put a mark on both faces, and never let the closed device look identical from both sides. When it is turned over in the hand, the camera side and the screen side must read as clearly different. HOW IT OPENS - READ THIS CAREFULLY: the hinge is a single vertical spine running down one long side, and the device opens sideways like a book. Closed, the spine is on one side and the free opening edge is on the other. To open it, a thumb goes on the front of the free half and the fingers go behind it, and that half swings outward to the side, away from the spine, until both halves are flat and side by side. The finished open device is one wide screen with the crease standing vertically down the middle. It never opens from the bottom edge, never opens from the top edge, never unfolds top over bottom, and is never handled as a clamshell flip phone. No half ever slides, peels, hinges horizontally or swings downward. The spine stays on the same side for the whole clip. HANDS: both hands stay in frame while the device is handled. Exactly five fingers on each hand, correct joints, correct thumb placement, natural grip pressure. No extra fingers, no fused fingers, no missing fingers, no bent or rubbery hands, and the device never floats, clips through a hand or changes size at any point. WARDROBE (from this text, never from @avatar): plain everyday indoor clothing with no logos, no lettering and no visible branding. Unisex cut. The reference shows their face and build, not this outfit - fit it to their body naturally without changing its cut, proportions or colour. LOOK: shot on a phone front camera at arm's length, held by the person themselves. Slightly unsteady handheld framing that drifts and corrects, natural indoor daylight from a window off to one side, an ordinary lived-in room softly out of focus behind them, plain phone-camera colour with no grading and no cinematic lighting. Real skin texture, real pores, no beauty filter, no ring light, no studio look. It must read as a clip somebody actually filmed for social, not as an advertisement. The person is pleased and a little smug the whole way through, like someone showing off something they got first. 0-3s: the person holds the device closed in one hand, up near their face, and starts talking straight to the lens. They turn it slowly so the camera catches its closed edge and its thickness. 3-6s: they bring the second hand in, take hold of the free long side, and swing the two halves apart sideways around the vertical spine, opening it like a book until it lies flat. Still talking, eyes flicking down to it and back to the lens. 6-13s: they hold it fully open in both hands beside their face, screen toward the lens, and slowly tilt and rotate it in the daylight. The screen is switched on the whole time and shows its own wallpaper brightly and clearly. As it tilts, the glass stays matte and readable: the room is never mirrored in it, no window, trees, ceiling or reflection of the person ever appears on the screen, and it never turns into a mirror or blows out into a white glare. They keep talking to the lens. 13-17s: they bring the open screen closer to the lens so it fills more of the frame, turning it a few degrees each way, their face still visible beside it. The screen stays lit and matte with no reflection of the room in it. 17-20s: they lower it slightly, look straight into the lens and land the last line with a small pleased grin, then hold still until the clip cuts. DIALOGUE: the person speaks in their own natural speaking voice, unhurried and conversational, in a normal indoor room, with the mouth movement matching exactly. Across the whole clip they say only this, starting at 0s and finishing by 20s: "Closed, it's a phone. Opened, it's one big screen - room for watching, gaming and doing three things at once. And it's in my hands." AUDIO: their voice close on the phone microphone, quiet room tone, the soft mechanical sound of the device opening, and light clothing movement. No music, no narration and no sound effects beyond the room. Only one person and one device exist in this entire video. Keep it subtitle-free: do not generate subtitles, captions, on-screen text, a timestamp, a recording indicator, an interface overlay, an added logo or a watermark (the device keeps its own marks exactly as shown). No second person, no reflections of another person, no extra hands, no tripod, no studio set and no exaggerated visual effects.

2 steps9115.1K
Seedance 2.520s · 1:1
Inspired by @nawalseharon X

ASSET MAP - every reference is bound here and cited by tag below: @avatar - the person the vlog follows. It defines face and identity and nothing else. CHARACTER LOCK - HIGHEST PRIORITY The person in every shot is exactly the person in @avatar. 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, from the first shot to the last. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached avatar is the person - reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached image outranks every word written below it: wherever the attached image and this text disagree, follow the image. WARDROBE LOCK The outfit comes from THIS TEXT, never from @avatar - the avatar reference shows their face and build, not this outfit, so put the outfit on them. The wardrobe of @avatar never appears. @avatar wears simple casual summer evening clothes. Unbranded, no lettering or logo. Fit each garment to the body of @avatar naturally without altering its design, cut, proportions or colour - the garment is fixed, only its drape adapts. The outfit is identical in every shot of the film. FRAME 30-second ultra-photorealistic cinematic vlog, horizontal 16:9, following @avatar through a warm summer evening at a LARGE amusement park. This is a big permanent park, not a small country fair: wide paved avenues, a towering steel roller coaster looping overhead with trains screaming past, a giant illuminated Ferris wheel, a drop tower, spinning rides throwing coloured light, neon-fronted arcades and game arcades, big food pavilions, and thousands of visitors filling the walkways. Strings of bulbs and huge lit signs run above the crowd, and the park glows brighter as the sky goes from gold to deep blue. Realistic handheld vlog cinematography: subtle natural camera movement, small imperfect reframes, natural expressions, authentic evening lighting, realistic crowd behaviour and physically accurate motion. Photo-realistic throughout - no CGI look, no animation. Hard cuts between shots, no dissolves. @avatar wears the same outfit and keeps the same face in every one. The film opens already in motion on a fully exposed frame - no fade from black and no still opening beat. TIMELINE (30 s): 0–5s: ARRIVAL @avatar walks in through the main gates of the park as the last golden light fades behind the roller coaster. The camera follows just behind and slightly to the side, then swings around to catch the face of @avatar looking up at the lit arch and the rides beyond. Crowds move past in both directions; the coaster train roars overhead. @avatar says, "Okay, this place is huge." 5–10s: THE FERRIS WHEEL Hard cut to @avatar in a Ferris wheel gondola as it climbs. The whole park opens up below - the coaster, the spinning rides, the rivers of people, the city lights beyond the fence. @avatar leans to the window, the wind moving through the gondola, and looks out and then back to the lens, smiling. 10–15s: FUNNEL CAKE Hard cut to a food pavilion counter under warm bulbs. @avatar breaks off a piece of a fresh funnel cake and shares it, powdered sugar falling like snow and dusting their fingers. Close detail on the crisp fried texture and the sugar in the air, then back to the reaction of @avatar tasting it. 15–20s: RING TOSS Hard cut to a brightly lit game booth wall stacked with prizes. @avatar takes a ring, lines up, throws - the ring spins through the air and clatters against the bottles. @avatar laughs at the miss, takes another and throws again. 20–25s: THE CROWD AND THE BAND Hard cut to @avatar wandering the main avenue among families, children with light-up toys and vendors, rides turning overhead. @avatar stops at an outdoor stage where a live band is playing to a packed crowd, and stands watching with the stage lights crossing their face. @avatar says, "This is my favourite part." 25–30s: FIREWORKS Hard cut to @avatar standing near the Ferris wheel as the first fireworks burst over the park. The camera holds on the face of @avatar lit by the flashes, then tilts up to the sky where smoke drifts across the colours, and settles back on @avatar watching. The film ends on that. AUDIO Natural amusement-park sound only: the roar and clatter of the roller coaster, ride motors, crowd chatter and children, a distant PA, the live band playing from the stage, and fireworks cracking overhead at the end. The two short lines of @avatar are spoken naturally in American English and synchronised to the lips. No narration. No subtitles. NOTES The identity of @avatar and the outfit described above stay identical in all six shots; only the location inside the park changes. Realistic crowd behaviour throughout, physically accurate ride mechanics and thrown rings, real powdered sugar and real smoke. The strongest moment - @avatar walking in under the lit gate with the coaster overhead - is present in the first shot.

1 step1383.6K
Seedance 2.530s · 16:9
Inspired by @EHuangluon X

Cinematic historical period-romance, warm painterly feature-film look, 35mm, fine grain, shallow depth of field, soft natural light. Set in a European medieval/Renaissance riverside village and market town. Two leads, identity ONLY from their references, kept identical every shot; no added physical, hair or gender description. Preserve their gender presentation exactly as shown. Use they / their / them only. Preserve each lead's hairline, hair length, texture and colour exactly as their reference shows — period styling may tuck or gather the hair but never changes its length, texture or colour. @image1 is one lead (exact face and identity from @image1), playful and warm; @image2 is the other lead (exact face and identity from @image2), quiet and brooding. WARDROBE (fixed design, adaptive fit): @image1 wears pale linen period clothing with loose sleeves, styled to suit their gender presentation as shown in @image1; @image2 wears a dark travel tunic and cloak. The references show face and build, not these clothes — fit each garment to that lead's body naturally without altering its design, cut, proportions or colour; the garment is fixed, only its drape adapts. Any other people are period townsfolk in medieval clothing, clearly different-looking, never resembling the leads. BEATS (30 s): 0–8s: OPEN ON THE FACE — begin tight on @image1's face mid-laugh, sunlight and leaf-shadow moving across it, eyes bright; the camera pulls back to reveal a sunlit clear forest stream, dappled light through leaves, @image1 kneeling at the water's edge with sleeves pushed up, trying to scoop a darting fish with bare hands, real believable splashes and ripples; @image2 crouches a few steps away on the mossy bank, watching quietly with the faintest smile. 8–12s: THEN intimate close-ups — @image2's thoughtful, watchful face; @image1 glances back over the shoulder, water droplets on the hands, a bright grin; handheld-soft cinematic framing. 12–18s: THEN MARKET — match to a bustling medieval market street, timber-framed houses, cloth awnings, hanging charms and lanterns, a lively period crowd; @image2 walks slowly through the moving crowd, camera tracking; @image1 drifts between stalls. 18–24s: THEN THE STALL — @image1 stops at a trinket-and-jewellery stall, lifts a carved hair comb and holds it up to a round polished-bronze mirror on the counter, tilting the head, trying it against the hair, delighted; a stall-keeper beside; @image2 notices from across the lane. 24–30s: FINAL BEAT THE MEETING — the two cross paths in the golden late-day light; eyes meet and hold; @image1 smiles, @image2's guarded expression softens into a warm quiet smile; a gentle push-in ends on the shared look, market life blurred warm behind them, held to the final frame at 30s. LOOK: feature-film cinematography, natural handheld micro-movement, warm earthy colour (greens and sunlight at the river, amber and cloth-tones in the market), realistic skin and fabric, believable historical props and architecture, delicate atmosphere, never staged or plastic. PHYSICS & CONSISTENCY: real water splashes and ripples with weight; locked identities and wardrobe throughout; crowd moves independently and never freezes or duplicates; believable hands; @image1 and @image2 never swap or change. SOUND: a gentle orchestral-and-folk period score plus authentic ambience — flowing stream, birdsong, market chatter, footsteps, cloth and trinket sounds; NO spoken dialogue, NO voiceover, NO invented language. Negative: any ethnic or racial description or exclusion; any change to either lead's hair length, texture or colour; opening on an empty landscape with no face in frame; on-screen text, letters or captions; brand names or logos; changing faces, hairstyles or identity; a second lookalike of either lead; distorted or extra fingers; plastic skin; watermark.

1 step
Seedance 2.530s · 16:9
Inspired by @umesh_aion X

A tense baby-monitor horror: @image1 wakes to a strange sound, looks at the monitor and sees a gaunt shape looming over the crib in the grainy night-vision feed. @image1 races down the dark hall, heart pounding, to reach the nursery — the shape is gone but something is wrong. Claustrophobic handheld, photoreal, moody low light, diegetic sound and score, no dialogue. The baby is never harmed.

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

Premium cinematic action-comedy, photorealistic, film-grade, shallow depth of field, smooth stable camera, three clean unhurried shots, rich golden-hour light. Single consistent character: @image1, an unlikely action hero - appearance and identity ONLY from @image1, wearing the exact outfit from @image2 if a second image is attached — if no second image is attached, they wear simple everyday clothes (same outfit in every shot); no physical, gender or clothing description beyond the references, identity and wardrobe locked together throughout. Preserve their gender presentation exactly as shown. Use they / their / them only. The references show face, build and garment design, not how they meet — fit the outfit to their body naturally without altering its design, cut, proportions or colour. TIMELINE (21 s): 0–6s: SHOT 1 — a slow cinematic push-in on @image1 sitting confidently in the open side door of a dark navy helicopter hovering high over a glowing city skyline at sunset, a small bag on the lap, hair and clothes rippling in the rotor wash, a calm delighted smile. 6–13s: SHOT 2 — @image1 leans out and drops; a round parachute blooms open above and @image1 glides gracefully down between tall glass skyscrapers, laughing softly, the camera tracking smoothly alongside. 13–21s: SHOT 3 — @image1 touches down lightly on a quiet, empty barricaded street, unclips the parachute, calmly lifts an oversized toy-like rocket launcher and fires at a single EMPTY parked armored truck far down the road; a big clean cinematic fireball blooms behind while @image1 strolls toward camera unbothered, grinning, the shot holding on them to the final frame at 21s. Completely harmless comedic slapstick: the target is empty and inanimate, nobody near the blast, nobody hurt. High realism, believable physics, natural anatomy and hands. SOUND: helicopter rotor wash, wind, a soft parachute flap, a gentle laugh, one big echoing boom and crackling fire, distant sirens, a light cinematic score; NO spoken words, NO voiceover. Negative: a character not matching @image1, an outfit not matching @image2 when @image2 is attached; any ethnic, age, gender or clothing description; rushed or jittery editing, too many cuts; distorted or melting faces, extra fingers or limbs; on-screen text, captions or letters; added logos (anything printed on the @image2 outfit stays exactly as it is) or watermarks; identity or outfit changing; blurry low quality; empty pilot seat; slow motion.

1 step
Seedance 2.521s · 16:9
Inspired by @HeyAbhishekon X

Generate a 15 second commercial video for a product.

3 steps26613.4K
Seedance 2.015s · 9:16
Inspired by ZetoGroovinon 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, skin, hair, age and body exactly as shown. The photo is identity only, not wardrobe. Do not keep the clothes, shoes or bag from the photo. Keep their hair exactly as in @image1. WARDROBE: a plain casual dance-ready studio outfit with sneakers. Same outfit for the full 15 seconds. SETTING: charcoal-grey seamless studio, dry floor with a faint reflection. No furniture, no crowd, no props. Soft white key from front-left, pale blue-violet rim from behind. One person only. No on-screen text. MUSIC: 128 BPM four-on-the-floor k-pop dance track already in the chorus. Heavy kick, bouncing bass, sharp claps. No intro, no fade-out, no ending hit. The clip is a mid-routine slice — they are already dancing in frame 1 and still moving in the last frame. CHOREOGRAPHY — one continuous 15s routine in four phrases. Never freeze. Never a start pose or a finish pose. Phrase 1 (0–3.75s): already weighting the left leg as arms return to the chest. Step hard right, uncross the arms out and open the chest. Weight back left, arms circle down. Two small forward steps, a sharp chest hit on the clap. Open the right foot, drop the knees, arms to the hips into a hip figure-eight. Phrase 2 (3.75–7.5s): low hip figure-eight, weight right-left-centre. Wave up from pelvis through belly to chest. Uncoil the arms as the right foot crosses in front, glance at the lens with a brief smile without stopping. Phrase 3 (7.5–11.25s): smooth stepping turn, hair lagging the spin. Land into a right side lunge, left arm high, long diagonal. Push back to centre, wave down the torso. Phrase 4 (11.25–15s): two strong hip accents. Two quick steps to centre, load the arms. Open the right foot wide, big arm unfold — not a finish, a send-off. Circle the arms down, take weight on the left, right foot already starting the next cross-step. Last frame still travelling. CAMERA (cut on the body, never reset the step): 0–3.75s full body, slight three-quarter, short lateral slide. 3.75–5.625s waist-up, hip figure-eight, locked frame. 5.625–7.5s face and shoulders, 85mm, the wave hitting the collarbone. 7.5–11.25s full body for the turn and lunge. 11.25–13.125s head to mid-thigh. 13.125–15s full body, short lateral move, no zoom-in to end. Photoreal skin, light sweat, motion blur on hair and hands. No slow-mo, no logos, no extra limbs.

1 step34013.6K
Seedance 2.515s · 9:16
Inspired by @VeraVCreateson X

ASSET REFERENCING @image_1 — the avatar. This is the protagonist and the sole facial anchor for the whole video. It is the only attached image. ONE-SENTENCE SUMMARY 30 seconds, 16:9, a twelve-shot live-action handheld travel vlog in which @image_1 films themselves on a snowy Amsterdam canal and goes from calmly recording to being quietly overwhelmed by the view. CHARACTER LOCK ATTACHED IMAGES ARE MANDATORY AND FINAL: the person in @image_1 is the protagonist — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached image outranks every word written below it: wherever the attached image and this text disagree, follow the image. Preserve the 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 of @image_1 — identically, shot to shot. Preserve the gender presentation of @image_1 exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift, no other people in close-up. Gender, face, hair, skin tone and body proportions come entirely from @image_1 and not from this text. The speaking voice belongs to @image_1 and matches the person shown there. WARDROBE LOCK @image_1 wears a warm puffer jacket, a knitted scarf, straight-leg trousers, winter gloves and winter boots in colours that suit @image_1 — the same outfit from the first frame to the last, with no costume change. The avatar reference shows their face and build, not this outfit — put the outfit on them. Fit each garment to their body naturally without altering its design, cut, proportions or colour: the garment is fixed, only its drape adapts. CAMERA AND TEXTURE @image_1 holds a small early-generation consumer camcorder at arm's length and films themselves with it. The camcorder is the camera we are watching through and never appears inside the frame; we see only the arm holding it, and only when the frame drifts. Authentic handheld home-video texture throughout: slight shake, autofocus hunting, auto-exposure lag, mild tape noise, soft highlight bloom, and occasional snowflakes sitting on the lens. SETTING Winter in Amsterdam. A canal in the old centre: narrow seventeenth-century brick canal houses with stepped and bell gables, tall warmly lit windows, an arched stone bridge strung with small warm lights, bare elm branches along the water, houseboats moored at the quay, bicycles chained to the iron railings with snow settled on their saddles, and cobbles under fresh snow. Fine snow falls slowly the whole time. The timeline moves naturally from overcast daylight to blue-hour dusk. DETAILED PLOT [0-3s] Extreme close-up selfie, almost pressed against the face of @image_1, showing only forehead, eyes, nose tip and lips, the background blurred into a cold blue-grey sky. They look calmly into the lens and breathe out a puff of white. Something off-frame catches the edge of their vision: the pupils widen slightly, the eyelids hold for half a beat, one eyebrow lifts a fraction. No words yet, only a small sharp inhale as the gaze drifts to the right of frame. The autofocus hunts once. Then, quietly: "No way." Ambient sound only — snow landing on the jacket, footsteps somewhere behind. [3-5s] Medium close-up, still held at arm's length, the frame easing back to show the scarf and shoulders of @image_1. They turn their head slowly to the right, lips parted but not open, breathing shallower. Their free hand lifts and stops in mid-air. Softly: "Hold on. Look at this." The camera follows the turn and the snow light briefly blows out the frame. [5-8s] Point-of-view shot: the frame pans off the shoulder of @image_1 to reveal the canal — dark green water, gabled brick houses on both banks, warm yellow window light, an arched bridge in the middle distance, snow falling into the water. One natural handheld pause and one hesitant zoom. Focus pulls from the snow on the foreground railing to the far bridge. Off-frame, @image_1 lets out a quiet laugh. Distant voices, a bicycle bell, water lapping against the quay. [8-10s] Close-up selfie. The canal lights sit as small reflections in the eyes of @image_1. They blink once, as if bringing the scene into focus, then the brow relaxes and the mouth lifts from a held line into a smile. A one-second glance at the lens, then straight back to the canal, in a breathy, disbelieving tone: "I had no idea it snowed like this here." Snow keeps falling behind them. [10-13s] Extreme close-up as the frame tilts down to the open palm of @image_1. Snowflakes land on the edge of the glove and on bare fingertips and melt into tiny beads. The fingers curl in gently, then slowly spread open again, the movement careful, almost protective. Almost murmured, off-frame: "This is unreal." Close sound: fabric rustle, snow particles, faint wind. [13-15s] Medium following shot. @image_1 walks forward along the snowy quay, the camera pointing ahead from their hand and then swinging naturally back to catch their profile. Halfway through they slow down, shoulders sinking into the scarf, eyes brightening. Looking up at the snow banked along a gable, with a suppressed laugh: "Look at it. All of it, white." Warm light from the tall canal-house windows sets a real warm-cool contrast against the blue snow. [15-18s] Close-up. @image_1 stands at a canal-house doorway. Off-frame, a loose shutter knocks in the snowy wind. They look up sharply as a small slab of snow slides off the gable ledge above them, flinch back half a step with the eyes going wide, then realise there was never any danger, press their lips together and let a smile break through anyway, laughing: "Okay, that got me." The frame shakes with the step back and settles naturally. [18-20s] Medium wide shot, the frame panning slowly along the quay. A grey heron stands completely still on a mooring post across the water, keeping its natural wild distance — not approaching, not being fed. Only half the face of @image_1 sits in the corner of frame. They hold their breath, grip the camera tighter, eyes wide, voice dropping to almost nothing: "Wait. Is that a heron?" Focus starts on the falling snow and shifts to the bird. [20-23s] Extreme close-up selfie. @image_1 does not dare make a sound, keeping their lips closed for two seconds, working hard to hold the smile down, but the corners of the eyes have already creased. A quick glance toward the heron, then back to the lens, brows lifting, breath unsteady. Whispered: "I'm so glad I came." The frame dips slightly because the laugh finally wins. [23-25s] Wide point-of-view shot. The canal enters blue hour. Window lights and the small lights on the bridge come on one by one, and snowflakes catch the light as tiny bright specks in front of the lens. The frame moves slowly forward along the iron railing while people pass naturally through the edges. Off-frame, softly: "This looks like a film." No music — only water, snow, a distant bicycle bell and voices. [25-28s] Medium close-up selfie. @image_1 stops by the railing. They do not look at the lens at first, holding their gaze on the canal for two seconds, then turn back with the wonder still in their eyes and the faintest smile. They breathe out a puff of white and say quietly: "I still can't believe it." The light is softly diffused, with no romantic filter over it. [28-30s] Medium close-up selfie turning into a slow pan: @image_1 looks at the lens one last time, the widened eyes settling, and says softly: "I want to come back." Then they pan the camera off their own face across the full snowy canal — bridge lights, gabled houses, dark water — and the frame holds there for the last two seconds. ADDITIONAL NOTES The same face from @image_1 carries the entire video; the outfit, the handheld camera behaviour, the autofocus response, the exposure lag, the shake and the tape texture all stay consistent from the first frame to the last. Every shot in the film is filmed by @image_1 at arm's length; there is never a shot taken from anyone else's position and never a second person operating a camera. The route runs: canal edge at the bridge → snowy quay past the canal houses → heron across the water → the same canal at blue hour. Every cut is bridged by a gaze, a body turn, a hand movement or an ambient sound cue. Every spoken line is in English, in the same natural speaking voice, kept low and close to the microphone — never shouted or performed. The first frame is already fully lit and already in motion; there is no fade in from black, no intro card and no title. Hands are drawn correctly, with five fingers. Do not add subtitles. No on-screen text. No BGM; generate only environmental sounds, the close handheld sound of the jacket and gloves, and the spoken lines.

1 step42957
Seedance 2.530s · 16:9
Inspired by @ChillaiKalan__on X

ASSET MAP — every reference is bound here and cited by tag below: @image1 — Avatar 1. Refer to @image1 for the person in every shot: their face, identity and everything they wear. The person is exactly the person in @image1 and nobody else; read it all off @image1 and invent nothing. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. The numbering follows the order the references are attached. Day 1 — "Golden Hour Corner Shop" Create a 30-second ultra-photorealistic personal home-video capturing an ordinary summer evening in the life of the person from @image1. The footage should feel spontaneous and genuinely recorded by a friend, not like a commercial or music video. MAIN SUBJECT The person from @image1, relaxed and slightly playful, with realistic skin texture. Their hair carries natural flyaways and a few loose strands lifted by the warm evening air. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout the entire video, exactly as @image1 shows them. SETTING A quiet older residential neighborhood in Rome during a warm summer day at golden hour. Narrow cobblestone streets, small ochre and terracotta plastered buildings with weathered paint, wooden shutters half closed, potted plants and ivy on windowsills, laundry lines strung between windows, utility poles, tangled overhead cables, parked scooters and bicycles, a small worn stone fountain trickling at a corner and a modest neighborhood corner shop. The low sun sits just above the rooftops and fills the street with warm amber light and long soft shadows. The environment should feel lived-in and ordinary. Avoid famous landmarks, recognizable brands, advertisements or tourist locations. CAMERA / VISUAL AESTHETIC Raw personal footage casually recorded by a friend on a small early-2000s consumer digital camcorder. Handheld movement, imperfect framing, occasional autofocus hunting, slight exposure pumping, mild motion blur, soft digital detail, faded colors, subtle sensor noise, accidental zoom adjustments and realistic camera-handling movements. The low sun sometimes flares straight into the lens and the automatic exposure takes a moment to settle again. The camera operator should sometimes react slightly late to their movement. The camera stays handheld and unstabilized throughout — no gimbal, no drone shots, no cinematic lens effects, no polished commercial cinematography. 00–05s — LEAVING HOME They open the front door of a small apartment building and step out into the low evening sun. Warm amber light falls across the whole street. They squint slightly at the sun, push their hair back from their forehead and look toward the camera with a small amused smile. They say: "I thought it would be cooler by now." They step out onto the warm cobblestones. 05–10s — WALKING THROUGH THE GOLDEN LIGHT The camera follows beside them as they walk down the narrow cobblestone street. Their shoes scuff quietly over the uneven stones and their shadow stretches long ahead of them. They pass parked bicycles glowing in the low sunlight. A scooter moves through the background, briefly cutting through the shafts of light. They adjust a sleeve while walking. The camera briefly loses focus on them and focuses on a nearby sunlit bicycle before recovering. 10–15s — CORNER SHOP STOP They notice a small corner shop ahead. They walk inside while the camera remains just outside the entrance for a moment. The cool dim interior contrasts naturally with the glowing amber street. They come back out holding a small transparent plastic bag containing a bottled drink and a simple packaged snack. They look at the bag and smile. The bag and everything in it stays plain and unbranded. 15–20s — IN THE SHADE They stop in a patch of shade beneath a neighboring building, out of the direct sun. They set the plastic bag down briefly and push a few damp strands of hair off their forehead. The small stone fountain trickles quietly nearby. They notice a small stray cat sitting underneath a parked bicycle across the street. They crouch slightly to look at it. The cat watches them but does not approach. They smile and quietly say: "You found the shade too." The cat remains independent and natural. 20–25s — WALKING HOME The sun drops lower and the light turns deeper orange. They pick up the bag and continue walking. The camera follows from behind. Long shadows and warm reflections stretch across the cobblestones. A bicycle bell rings somewhere behind the camera. They turn briefly, then continue. Their clothes move naturally with their walking and the warm summer air. 25–30s — FINAL MOMENT They reach their apartment entrance, stop in the doorway, look back once toward the camera with a small tired smile and step inside. The camera holds on the closed door as the last of the golden light moves slowly across it. This is the last image of the film. No subtitles, no captions, no on-screen text.

1 step476.5K
Seedance 2.530s · 16:9
Inspired by @ImaStudio_aion X

Generate a tired evening skincare routine filmed on a phone, the last thing before bed.

2 steps231.7K
Seedance 2.515s · 16:9
Inspired by @HeyRu0byon X

Generate a premium macro commercial for your drink.

2 steps24630.1K
MiniMax H315s · 9:16
Inspired by @Ava_Ai__on X

subject_definitions: <Subject 1> is the product the reader adds in step 1, shown in @product. Its silhouette, its proportions, its colour, its finish and every mark printed or engraved on it come entirely from @product and not from this text. @product defines the product only; its background, framing and lighting are not carried over. summary: [reference generation] The target video is a fifteen-second vertical launch film in which <Subject 1> is shown on a seamless off-white paper backdrop across eight fast shots — a hero frame, three macro passes, two levitation frames, one demonstration and an end card — with four short lines of on-screen text written from the product itself. retention_analysis: <Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6], [Shot 7], [Shot 8]): fully_preserved - the silhouette, the proportions, the colour and the finish stay exactly as in @product in every shot, and its surface carries only the marks that exist there. detailed_description: The target video is a live-action, high-end product commercial in vertical 9:16, lit by soft daylight from the left against a seamless off-white paper backdrop, with shallow depth of field and a clean neutral grade. The objects on the paper are chosen by reading @product: two or three simple things that come from the same world as that product — the material it is made from, the thing it is used on, or the thing it is used with — and they are the only objects in the film besides <Subject 1>. They stay the same two or three objects from the first shot to the last. Four shots carry one line of on-screen text each, and each line is written by reading @product: two words in title case, at most sixteen characters, naming one quality that this particular product genuinely has. Each line sits in the vertically central zone in a bold sans-serif, the first word charcoal grey and the second word steel blue, rising into place over about fifteen pixels. One line is on screen at a time, and the other four shots carry only the image. [Shot 1] A wide frame holds <Subject 1> lying on the paper among those objects. The camera pushes in with large amplitude at fast speed until <Subject 1> fills the lower third. [Shot 2] At 00:02.000, the shot cuts to an extreme macro of the part of <Subject 1> that does its work — the edge, the tip, the opening, whichever part of this product meets what it is for. The camera trucks right with large amplitude at fast speed as a narrow specular highlight races along that part, and a line of text appears naming how well this product performs that job. [Shot 3] At 00:04.000, the camera cuts to <Subject 1> spinning in the air above the paper, those objects whipping past it. The camera holds a static shot while the product completes a full turn. [Shot 4] At 00:06.000, the shot cuts to a macro of the part of <Subject 1> a hand would take hold of. The camera trucks left with small amplitude at fast speed across that part, and a line of text appears naming how this product feels to hold. [Shot 5] At 00:08.000, the shot cuts to an extreme texture macro in which the broadest surface of <Subject 1> fills the frame. The camera pans right with large amplitude at fast speed as one band of light sweeps over it. [Shot 6] At 00:10.000, the shot cuts to a slow-motion side view of one demonstration: the simplest action that shows what <Subject 1> is for, performed on it with one of the objects from the paper. The camera holds a static shot. [Shot 7] At 00:12.000, the shot cuts to a levitation frame in which <Subject 1> and those objects hang at different heights above the paper and rotate together, each casting its own shadow on the paper below. The camera pulls out with small amplitude at fast speed, and a line of text appears naming what this product does for the person using it. [Shot 8] At 00:13.500, the shot cuts to the end card: <Subject 1> rests on the paper among those objects, nothing moving. The camera holds a static shot, and a line of text appears naming what this product is made of, and it remains to the final frame. overall_soundscape: A quiet room tone runs under the whole video at a low, even level. Each cut carries one short, soft sound made by the material of the product in @product itself, and each of those sounds sits just above the room tone. non_diegetic_music: A steady electronic pulse at about 128 beats per minute with a soft kick and clipped hats, held at one even, moderate level from the first frame to the last, ending on a single short tail.

2 steps510.3K
MiniMax H315s · 1:1
Inspired by codewithhajraon X

Style: luxury skincare commercial, minimal, clean, soft ivory palette with accents taken from @product's own colours, premium CGI, glossy liquid physics, elegant editorial beauty, photorealistic, slow motion. Product lock: @product is the only hero. Match the reference photo exactly — bottle shape, proportions, cap, label, typography, colors, fill level, packaging. No redesign, no extra products, no on-screen text, no captions, no typography overlays. Liquid: the product's own liquid — its colour, clarity and texture exactly as @product shows them. Eight beats in one continuous 10-second spot, 9:16. Beat 1. @product slowly descends against a pristine ivory-white field with a faint warm gradient in @product's accent colour. Fine water droplets float around the bottle and catch the light. Camera: slow cinematic push-in. Lighting: soft diffused studio, delicate glossy reflections. Beat 2. The bottle settles into crystal-clear water. An elegant splash rises around the base in slow motion. Soft caustics in @product's accent colour shimmer through the liquid. Camera: high-speed macro. Details: realistic water physics, fine droplets, glass-like refraction. Beat 3. The bottle rotates a full turn just above reflective water. Tiny droplets orbit it. The background eases from ivory into an ultra-soft tint of @product's accent colour. Camera: smooth product orbit. Details: sharp product focus, shallow depth of field, realistic reflections. Beat 4. Extreme macro of the product's own liquid dispensing from the bottle. A silky drop of it forms and falls. Camera: macro tracking the drop. Details: realistic viscosity, glossy surface tension, soft highlights. Beat 5. The drop lands on calm water. Concentric ripples, micro-bubbles, light sliding across the surface. Camera: slow-motion macro at water level. Mood: calm, fresh, hydrating. Beat 6. Extreme macro of the product's own liquid spreading across pristine glass. Silky, lightweight, luminous, with delicate waves and tiny air bubbles. Lighting: soft beauty-editorial, glossy highlights. Camera: slow macro track. Beat 7. One hand lifts @product. Soft side sunlight, highlights along the bottle and cap. Camera: slow rotation around the hand and product. Background: minimal warm-white studio, faint gradient in @product's accent colour. No other people. Beat 8. @product stands centered on a glossy reflective water surface. Soft mist tinted with @product's accent colour, a few floating droplets, a premium finishing sparkle. Camera: very slow push-in toward the label. Lighting: soft diffused luxury studio, realistic reflections, cinematic depth of field. Final look: high-end skincare campaign, photorealistic product CGI, elegant, minimal, ivory with @product's accent colour, realistic water and liquid physics, no distortion, no extra products, no altered packaging, no on-screen text.

2 steps685.9K
Seedance 2.510s · 9:16
Inspired by @FutureVibesAion X

@avatar is the person filming and appearing in the vlog - it defines face and identity only. Preserve their facial identity, skin tone, hairline, hair, apparent age, build and gender presentation exactly as shown, in every frame; never invent a different face. The attached image outranks this text wherever they disagree. Wardrobe comes from this text, never from @avatar: simple plain casual clothes, a rain jacket, sandals and a canvas crossbody bag. Same outfit, soaked the same way, in every second. 30-second authentic late-2000s flip-camera vlog, 16:9. Heavy handheld shake, autofocus hunting, accidental crops, raindrops on the lens, warm faded colours, low-quality home-video compression. NOT cinematic - no grading, no stabilisation, no slow motion. The camera is a cheap flip camcorder and is never visible in frame. A New York street corner in a heavy downpour, late afternoon: a glass bus shelter with a metal bench, brick buildings with fire escapes, a bodega with a lit awning, a halal cart under a big umbrella, yellow cabs throwing spray, steam off a manhole. Pedestrians hurry past without stopping. TIMELINE (30 s): 0–5s: @avatar runs through the rain to the shelter, laughing - "Ahh! It's pouring!" 5–10s: Under the shelter they hear a thin meow; the camera tilts down and hunts for focus under the bench, finding a tiny soaked grey-and-white kitten - "Oh no... you're all wet." 10–15s: @avatar dries it with a cloth from the bag. 15–20s: They dash to the halal cart for a plate of vegetarian rice and grab a packet of kitten food from the bodega. 20–25s: Back on the bench they tip the food onto the lid and both eat, the rain easing. 25–30s: @avatar turns the camera on themselves, laughing - "Looks like we ended up having lunch together." The kitten meows, rubs against their sandal, and the recording cuts off mid-motion. Diegetic sound only from a cheap camcorder mic: hammering rain, tyres hissing through water, a passing bus, distant horns, the kitten, plastic packaging, and the voice close to the mic. Three short lines in American English, synchronised to the lips. No BGM; generate only environmental sounds and action sounds. No subtitles. Only one kitten and no other animal.

1 step24932
Seedance 2.530s · 16:9
Inspired by FutureVibesAion 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 late-2000s handheld flip-camera vlog. 16:9. The person in the attached reference keeps their own age and gender presentation in every frame. They are the only 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 the attached image as a plate. Wardrobe, locked: a simple casual beach outfit with flip-flops and a shoulder bag. Fit these clothes to the attached person's body. Hair exactly as in @image1; wind may move it, never restyle it. Keep one tiny all-black kitten throughout, same kitten every frame, natural cat behavior. No other people, no vendor face (the stand is self-serve: wrapped cuts on ice, a cash tin, handwritten prices with no readable words). 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. The all-black kitten starts following at their flip-flops. They laugh and point the camera down. Exact lip sync: "Oh... you're coming too?" 8-16s — buy: They pick up a small wrapped cut of meat for themselves, drop cash in the tin, then tear off a piece for the kitten. They crouch, smile, exact lip sync: "This one's for you." The kitten sniffs the meat. 16-24s — feed: On a small wooden stool in the sand beside the stand, they set the piece down. The kitten eats while they gently pet its head. Exact lip sync: "You were hungry." 24-30s — leave: They walk along the shore carrying the remaining wrapped meat as the same black kitten keeps following beside their flip-flops. They laugh at the camera, exact lip sync: "I have company now." The kitten meows as the recording abruptly ends. Audio: natural beach-stand ambience only — surf, wind, plastic wrap, footsteps on sand, cash tin, kitten meows, the spoken lines. No music, subtitles, logos, or cinematic effects. No on-screen text. Duration: exactly 30 seconds. Aspect ratio: 16:9.

1 step373.3K
Seedance 2.530s · 16:9
Inspired by @ZephyraLeighon X

Create a 15-second video that looks like authentic 1890 hand-cranked black-and-white film, filmed by the person holding the camera themselves. **@avatar — THE PERSON.** Preserve their exact face, identity, facial structure, eyes, hair, age, build and proportions throughout. No identity drift, beautification, de-aging or restyling. Ignore the reference background. **WARDROBE:** Wet 1890 London clothing: dark heavy wool overcoat buttoned high, collarless shirt, worn leather boots, soft flat cap, canvas satchel. Damp hair. Outfit never changes. **STYLE:** Authentic early cinema, ~16fps, slightly fast and jerky movement, constant flicker, heavy film grain, dust, hairs, vertical scratches, soft vignette, occasional frame jumps, rain on lens and strong handheld shake. Bad framing is intentional — cropped heads, drifting subject and sudden camera movements. Absolutely no modern cinematic stabilization. **SETTING:** Narrow rainy London street, wet cobblestones, gas lamps, soot-stained brick, market stalls with dripping canvas awnings, horse-drawn carts and pedestrians with umbrellas. The stallholders, the fishmonger and the pedestrians are generated background extras, never a second lead. **00:00–00:04:** They run through heavy rain toward a market awning, laughing, holding the camera at arm's length as it swings wildly. They shake water from their cap. **00:04–00:08:** They hear something and swing the camera down, searching under a wooden crate. They find a tiny soaked grey-and-white kitten. They crouch down, face filling the frame at an awkward angle. **00:08–00:12:** They dry the kitten with their coat, then buy roasted chestnuts for themselves and a scrap of fish for the kitten. **00:12–00:15:** Sitting on a crate under the awning, they eat together as the rain eases. They laugh into the lens and shrug. The kitten rubs against their boot. The frame stutters, flares white and the film runs out. **AUDIO:** No dialogue, voiceover or music. Only rain, canvas, hooves, cart wheels, distant voices and one small mew. **AVOID:** text, intertitles, subtitles, logos, watermark, color, modern objects/clothing/vehicles/signage, stabilization, cinematic camera work, second person in close-up, face changes or costume changes.

1 step271.1K
Seedance 2.515s · 4:3
Inspired by @aimikodaon X

15-second experimental anime fashion film. Use @avatar for the @avatar’s exact identity, outfit and rendering style. A pristine, uniform lemon-yellow cyclorama with a seamless matte floor. Flat, clean yellow throughout, free of grain, gradients and set dressing. No text or logos. The @avatar performs one fast, unconventional dance phrase: ankles weave while the torso stays suspended, a wrist flick ripples through both elbows into a chest pop, knees fold into a low corkscrew pivot, then a heel swivel unwinds the body into an off-balance editorial pose. Continue through asymmetric shoulder rolls, angular arm threading around the face and a sideways glide with the head counter-rotating toward the lens. Every sharp lock immediately releases into another surprising movement. Convincing weight, precise foot contact and expressive follow-through. Electric cyan and hot pink dominate the motion effects. Bold, opaque silhouette afterimages peel away from opposite sides of the body, replay the previous gesture a fraction late and slam back into alignment on each pose. Arm sweeps stretch them into broad curved ribbons; crossing steps weave pink and cyan trails around the ankles; rapid turns fan out overlapping screen-print impressions. At the strongest accents, oversized cyan and pink cutouts of the current pose slide across the foreground, briefly masking the lens. Keep the real character crisp and recognizable, with clean yellow visible between effect bursts. The camera dances in counterpoint: skim backward at ankle height through advancing footwork, whip upward around an outstretched wrist into an extreme face close-up, then use the passing forearm to cut into a rotating overhead view of the low pivot. Dive to a tilted low-angle full-body composition as the character rises. Orbit opposite the sideways glide, exaggerating hands and feet near the wide lens.

1 step58227.3K
MiniMax H315s · 16:9
Inspired by @ZaraIrahhon X

A dreamy golden-hour beach scene with @image1, where the earrings from @image2 catch the low sun as the sea breeze moves and waves roll in. Soft cinematic close-ups, a brief sparkle on the earrings, and a warm calm mood. Editorial and understated, photoreal, natural ocean sound and a light music bed, no dialogue.

1 step
Seedance 2.56s · 9:16
Inspired by bmx_ai13on X

Generate a phone-selfie UGC video, for a product.

2 steps41789
Seedance 2.015s · 9:16
Inspired by ivanka_humeniukon 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, skin, hair, age and body exactly as shown. The photo is identity only, not wardrobe. Do not keep any clothing, bags or accessories from the photo. Start look (shots 1–5): white cropped tank and short white fitted shorts. Barefoot until the final reveal. Final outfit (from the source film, not the photo): oversized moss-olive mohair sweater with balloon sleeves; olive satin bottom with a floral lace hem — a mini skirt or tailored shorts/trousers, whichever suits their gender presentation as shown in @image1, the same piece in every shot; dark chocolate leather boots, knee-high slouch or ankle height, whichever suits them; dark brown leather belt with a gold buckle, front of the sweater tucked into the belt; structured dark chocolate-brown leather tote; warm gold jewellery that suits them: a collar necklace or chain, a ring and a bangle, plus hoop earrings only if they wear earrings in @image1. SETTING: cream Paris hallway, gold rococo mirror, two wall sconces, marble console, open shopping boxes on the floor. Warm lamp light. No other people. No on-screen text. No bottom reference panels, no collage, no character sheet, no flat-lay. CAMERA: one locked tripod in the doorway, frontal, eye level. Hard cuts on the beat. 9:16, 20 seconds. Frame 1 is already in the hallway — never a studio portrait plate. SHOT 1 (0–1.7s) They hold the olive satin lace-hem bottom by the waistband against their waist, lift it once so the satin sways, look into the lens and smile. SHOT 2 (1.7–3.4s) Same camera. They hold the moss-olive sweater against their torso by both shoulder seams, bounce it once, glance down, then smile at the lens. SHOT 3 (3.4–5.0s) They hold the brown leather belt horizontally, gold buckle centred close to the lens, eyes visible above it, a small smile. SHOT 4 (5.0–5.8s) They toss their hair (or run a hand through it if it is short) and grin at the lens. SHOT 5 (5.8–7.5s) They hold the chocolate-brown tote in front of their chest; face visible between the handles; head tilt and smile. SHOT 6 (7.5–10.2s) Sweater already above their head. One uncut action: they pull it down, arms through the balloon sleeves, hem settles at the hips, hair falls back. Eyes find the lens. Smile. SHOT 7 (10.2–11.7s) Wearing the sweater, they spray perfume beside their neck once, eyes close, then look back at the viewer. SHOT 8 (11.7–14.0s) Wider. They already wear the olive lace-hem bottom under the sweater. They adjust the high waistband once, shift onto one hip, pleased smile. SHOT 9 (14.0–15.7s) Closer. Gold jewellery already on. They fasten one gold piece with both hands (a hoop earring if they wear earrings in @image1, otherwise the bangle), check it in the lens, playful smile. SHOT 10 (15.7–20.0s) Full length, hair to boot soles. Complete outfit, tote in the left hand. Hold, small bounce, turn through a side view to a back three-quarter, then look over the shoulder at the lens and hold the smile to 20s. AUDIO: one upbeat instrumental fashion track. Cuts on the beat. Fabric, one spray, jewellery click, boots, tote.

1 step13532
Seedance 2.520s · 9:16
Taken by the Light

FOUR SHOTS. VERTICAL. ONE PERSON ONLY. ULTRA-REALISTIC CINEMATIC SCI-FI. ASSET MAP - every reference is bound here and cited by tag below: @avatar - the person. This is who is on camera; face, hair, skin and body come entirely from @avatar and never from this text. CHARACTER LOCK - HIGHEST PRIORITY: the person in every shot is exactly the person in @avatar. 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 from the first frame to the last. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift, and no other people anywhere in frame. ATTACHED IMAGES ARE MANDATORY AND FINAL: if a reference is attached, that is the person - reproduce them exactly, in every frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached reference outranks every word written below it. WARDROBE (from this text, never from @avatar): a pale floor-length robe of lightweight loosely woven fabric - long sleeves, an open front, a soft sash tied at the waist, and a long hem that trails on the ground, worn over matching loose full-length trousers in the same pale fabric. This is a unisex ceremonial robe, cut identically for any body: no logos, no lettering, no visible branding. The collar and shoulders of this robe are visible in every single shot, including the closest one - never a t-shirt, never a plain top, never bare shoulders. The reference shows their face and build, not this outfit - fit it to their body naturally without altering its cut, length, proportions or colour. The robe never changes the person: their hair length, hairstyle and gender presentation stay exactly as in @avatar. WORLD: an enormous, almost silent futuristic city at night. Glass towers climb out of frame, their windows glowing, thin neon lines running up their edges. The street is wet from recent rain and mirrors every light. Light mist and soft atmospheric fog. Above the rooftops there is no sky at all - the gap between the towers opens straight into the heart of a galaxy: dense drifting starfields and vast clouds of coloured nebula, close enough that they visibly move. Living inside that galaxy, an enormous creature glides slowly above the city like a whale through water. It has a solid rounded body with real volume - visible skin texture lit from within, soft shadow along its underside and flanks, slow rippling fins and a wide tail that flexes as it moves. It is a living animal made of light, not a flat glowing outline and not a drawing. Shot 1 (about 4 seconds): a tracking shot from behind at walking height. The person walks slowly away down the middle of the wet street in the long pale robe, its hem trailing behind them, their steps sending small rings across the shallow water. Far above and ahead, the enormous creature slides across the gap between the towers. They slow to a stop and begin to tilt their head back. Shot 2 (about 3 seconds): cut to a close shot of the person from the front, framed from the chest up so the collar and shoulders of the pale robe are clearly in frame. Their face is clearly lit and readable, head tilted back, looking up in silent amazement, eyes wide, lips slightly parted. Nebula light in soft blues and warm pinks moves across their face. Shot 3 (about 3 seconds): cut wider. The enormous creature descends into the canyon between the towers until its body fills the whole gap directly above the person, so close its lit underside washes the whole street. The person stands small and alone in the middle of the wet road, head back, arms loose at their sides, the long hem beginning to lift around their ankles. Shot 4 (about 5 seconds): THIS IS THE FINAL SHOT AND THE LONGEST SHOT OF THE FILM - it runs to the very end and the film closes on it. Cut to a low angle close on the person. The light closes around them and they rise: their feet lift cleanly off the wet street, the long hem and sleeves and their hair all stream downward as they climb, and water lifts off the road beneath them in slow threads. Their face stays turned upward, calm and amazed rather than frightened, clearly lit and clearly the same person. The camera stays with them and tilts up as they go, holding them in frame the whole way while the street falls away below and the creature's lit body grows above them, until they rise out of the top of the frame into the light. Stay on the person for this entire shot and end the film here. AUDIO: the deep quiet room tone of an empty city, faint water dripping and running, a low distant hum, one long low resonant call from the creature, and a soft rising swell of air as the person leaves the ground. Only one person exists in this entire video. No music, no narration, no dialogue and no voices. Do not generate subtitles, captions, on-screen text, a timestamp, a recording indicator, an interface overlay, a logo or a watermark. No second person, no crowd, no readable signage, no spacecraft, no tentacles, no grabbing or gripping of the body, no creature with a face or limbs, no final wide city shot without the person in it, and nothing that reads as a map or as lettering.

1 step947.7K
Seedance 2.015s · 1:1
Inspired by @Strength04_Xon X

Generate a 10 second soft luxury commercial for your product.

3 steps1112.7K
MiniMax H310s · 9:16
Inspired by @Soaima_Aion X

Generate a commercial like video for the dairy product.

2 steps481.3K
MiniMax H315s · 9:16
Inspired by @IsabelWhite24on X

Generate a video of an ocean floating above an ancient city with whales swimming in it.

1 step957.7K
Seedance 2.510s · 16:9
Inspired by Kel_vinlevenon 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. PRODUCT LOCK — HIGHEST PRIORITY AFTER THE PERSON: @image2 is the hero bag. It is the only bag. Preserve its exact colour, material, shape, strap, hardware, charms and proportions as @image2 shows them. No other bag, no tote, no redesign. The bag is in every shot with the person — worn on the shoulder, held in the hand, or sitting against them on the floor. Never leave the bag out of frame. WARDROBE: keep the outfit worn in @image1; if @image1 shows only head and shoulders, plain, neutral everyday clothes in the same register and colour family as the garment @image1 does show. SETTING: a clean luxury fashion studio, seamless cyclorama, warm ivory-beige walls, glossy pale floor with soft reflections, hard directional sunlight from one side. No crew, no photographer, no other people, no on-screen text, no captions. STYLE: high-fashion bag commercial, 9:16, 15 seconds. Copy this studio-fashion movement and camera language: full-body hero, overhead floor sit, over-shoulder look, walk with the bag, seated pose, squat, walk-away look-back. Slow editorial pacing, photoreal, shallow depth, commercial lighting. Frame 1 is already in the scene — never a studio portrait plate of the attached still. Beat 1 (0-2s). Full-body hero. They stand in the cyclorama, weight on one leg, the bag on the shoulder exactly as in the product photo. Slow push-in. Bag fully visible. Beat 2 (2-4s). Overhead. They sit on the glossy floor, knees folded, one hand on the bag beside them. Bag fills a clear part of the frame. Camera high above. Beat 3 (4-6s). Medium. They turn, look back over the shoulder at camera. Bag in the hand at their side, its silhouette readable. Beat 4 (6-8s). Product insert. Close-up of the bag in their hand: its own texture, hardware and details as @image2 shows them. They do not leave the shot — fingers and forearm stay in frame. Slow orbit. Beat 5 (8-10s). Walk. They walk across the cyclorama carrying the bag by the strap, a natural swing. Full-body, floor reflection. Bag never hidden by the body. Beat 6 (10-12s). Floor sit. They sit with one leg extended, the bag standing or held against the hip, facing camera. Plenty of negative space above. Beat 7 (12-13s). Low squat, facing camera, bag on the shoulder. Still, then a small weight shift. Beat 8 (13-15s). They walk away and look back over the shoulder, bag in hand. Hold on the look. Slow push-in. End. No extra products, no logos invented, no on-screen type.

2 steps391.8K
Seedance 2.515s · 9:16
Inspired by @Zyrellixon X

Photorealistic live-action comedic short, cinematic quality, warm dimly lit bedroom-study at night — bookshelves, a warm desk lamp, curtained window. Single character @image1 (identity locked to reference). Preserve their gender presentation exactly as shown. Use they / their / them only. Humor comes from the absurd mismatch of scale: a huge overreaction to a tiny annoyance wrecks the room. PRODUCT IS OPTIONAL AND CAN BE ANY ITEM: @image2 = any single product or item the user plugs in — a handbag, a watch, a gadget, a snack pack, a cosmetic, anything — shown exactly as its reference, keeping its shape, colour, materials and any label or detail identical and clearly visible. If an @image2 reference IS provided, include the "showing the item" action and keep it clearly visible as written. If NO @image2 is provided, SKIP every product action and reference — do not invent, add or imagine any item — and keep the rest of the video exactly the same; in that case @image1 is just relaxing empty-handed before the fly lands. 0-5s: intimate close-up of @image1 sitting on the floor of the cozy room. IF @image2 is provided: @image1 casually holds and shows the item from @image2, turning it in their hands and angling it toward the camera so it is clearly visible, relaxed and pleased with it. IF NOT: @image1 simply sits relaxed, hands empty. Then a single fly lands on @image1's forehead; @image1 slaps their own forehead hard to catch it, but the fly darts away unharmed and @image1 winces in real pain from the smack. 5-9s: irritated, @image1 rises, eyes narrowing at the buzzing fly. The air tightens and begins to swirl; @image1 raises both hands and powers up — hair lifts and blazes with a glowing neon-orange aura, keeping its own colour and length, fine particles and energy spiralling up from their hands, fabric and hair rippling in the rising wind. Books and papers start to flutter. 9-14s: in full power state, wrapped in a neon-orange aura, @image1 throws fast, believable martial-arts strikes and stances around the room, chasing the tiny fly with deadly seriousness. IF @image2 is provided: the item @image2 is knocked from their grip and tumbles and spins through the air in the swirling energy with believable object physics, landing somewhere in the room, still intact and matching its reference. Real momentum and body weight. 14-20s: @image1 unleashes a burst of brilliant white-blue energy FROM THEIR HANDS (never from the mouth or head). The ceiling cracks and tears open into a huge hole revealing the dark night sky, walls fracture, the desk lamp topples, books and furniture are thrown across the room in a storm of dust. The entire rented room is accidentally destroyed. 20-25s: the energy dies down. @image1, their hair still glowing with the aura, freezes and slowly looks around the wrecked room, shocked and breathing heavily, realizing what they just did. The tiny fly calmly buzzes past, completely unharmed. 25-30s: a gigantic furious English bulldog looms up out of the wreckage — the landlord — unnaturally large, heavy and wrinkled, with glowing eyes and an intimidating presence. In a dramatic slow-motion extreme close-up, the giant bulldog's paw smacks squarely into @image1's face, squishing their cheek and knocking them sideways; @image1's shocked expression and flying, still-glowing hair captured in crisp slow motion. Hard cut to black. Realistic physics and biomechanics throughout — correct body weight, inertia, momentum, real debris and dust, believable destruction, exactly two hands on @image1 at all times. Handheld-but-controlled cinematic camera, shallow depth of field, warm interior light with cool blue from the sky through the broken ceiling, volumetric dust, dramatic shadows, film-quality color grading, photorealistic skin and hair. @image1 stays fully and modestly clothed at all times, no nudity. The transformation adds only a glow around their hair — hair colour, length, face and identity stay identical to the reference before and after. Diegetic sound and an orchestral swell only; no spoken dialogue, no invented language. Negative: no beam, laser or light from the mouth or head (energy comes only from the hands); when no product is provided, any invented item, product, box or package on screen; the @image2 item changing shape, colour or detail, breaking or duplicating; any gendered, ethnic or racial description of the character; nudity; letters, words, on-screen text, captions, logos or numbers (except a label that is part of the @image2 item itself when provided); resemblance to any known or published character design; identity drift, deformed or changing face, extra fingers, a third hand or extra arm, plastic skin, cartoon physics, watermark.

1 step
Seedance 2.530s · 16:9
Inspired by IqrasaifiAIon X

An 8-second vertical 9:16 hyper-realistic CGI product advertisement. Sleek, powerful, sophisticated. No on-screen text, no subtitles, no added logos or brand names; any badge or lettering already on @product stays exactly as in the reference. Single full-frame shot only. Never a split screen, never a comparison, never model-name labels. @product is the car in the reference image. Lock it exactly to the reference photo: its exact silhouette, body colours, stripes, lights, wheels and glass. Do not describe or change them. Same shape, colours, lights and wheels in every frame. One car, never duplicated. Setting: infinite minimalist virtual studio, deep black void, polished black obsidian floor that mirrors the scene. No people. Lighting: cool-white (6000K) softbox from above. Light in the colours of @product from the sphere, throwing dynamic reflections on the floor. Transformation Start: a single dense sphere, painted in the exact colours of @product, with a thin light line in its accent colour around its equator, sitting on the obsidian floor. End: @product, fully solid, settled on the floor. AUDIO — required: sphere rolling on glass-like stone, then a burst, metallic crackles, panels locking, electric-motor hum. No dialogue, no lyrics. 0-2 seconds Already in the scene: the sphere rolls across the black mirror floor toward camera, rotating so the colours of @product catch the light. About one full second of continuous roll. Macro-to-medium, 85mm. 2-5 seconds The rolling sphere bursts outward in zero-gravity. Liquid-metal tendrils in the colours of @product stretch into the wireframe of @product, traced by glowing electric-blue energy lines. 5-7 seconds Metal flows over the energy frame, solidifying into the exact body panels, paint, lights and wheels of @product. 7-8 seconds @product gently settles onto the reflective obsidian floor. Headlights flash on. Hold. Negative: extra cars, extra people, readable on-screen text, added logos, split-screen, hovering drop that never rolls, studio still of the reference photo as frame 1.

2 steps12505
MiniMax H38s · 9:16
Inspired by arsalannazir07on X

Create a 15-second vertical 9:16 cinematic anime-style food-cooking sequence. Warm hand-painted animation aesthetics, highly detailed backgrounds, clean cel shading, rich textures, natural hand movement, smooth cinematic transitions. Beautifully animated cooking short — not photorealistic, not 3D. No on-screen text, no subtitles, no logos. @product is the dish in the reference, being cooked and served. Same pan, ingredients and finish as the reference, throughout. AUDIO — required: sizzle, butter in the pan, spatula scrape, steam. No dialogue, no lyrics, no voiceover. 0-2 seconds Top-down rustic wooden kitchen table. The empty pan of @product sits in the center, surrounded by the raw ingredients visible in the reference dish, a knob of butter and crusty bread. Warm interior light, cozy traditional kitchen. 2-4 seconds Close-up. A hand lays the first main ingredient of @product into the hot pan from the reference over a visible blue gas flame. It sizzles and browns. Oil pops. Camera pushes in slightly. 4-6 seconds The first ingredient is pushed to the side. Butter melts in the empty half of the pan. A hand adds the next ingredient of @product. Edges bubble. 6-8 seconds The remaining ingredients of @product hit the pan. They blister and gloss. Steam rises. This is @product coming together. 8-10 seconds A spatula arranges everything exactly as in the reference dish; any garnish from the reference is scattered over the top. 10-12 seconds Hero close-up three-quarter: the skillet in full — @product exactly as the reference, steam. 12-13.5 seconds The skillet is lifted off the flame and set onto a wooden board. A slice of toasted bread is placed beside it. Butter gleams. Dynamic settle of the pan. 13.5-15 seconds Hero shot of the finished @product on the wooden table: the finished dish in its pan, toast, a small pot of greens, warm golden light. Slow push-in to an appetizing final frame. Visual direction: warm golden lighting, cozy rustic kitchen, anime food animation, hand-painted textures, expressive food movement, smooth transitions, cinematic framing, natural steam and sizzle, consistent hands and kitchen throughout. Negative: photorealism, live action, 3D CGI, plastic textures, malformed hands, extra fingers, deformed food, text, subtitles, logos, watermark.

2 steps47684
MiniMax H315s · 9:16
Inspired by @AIwithkhanon X

A cozy morning UGC clip: @avatar sits in bed and shows off @product, turning it over and gushing about it, then reaching out to cover the lens as it cuts off. Authentic handheld vlog feel, warm morning light, natural sound, no music.

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

Ultra-realistic underground apartment parking-garage horror, claustrophobic handheld camera, flickering fluorescent lights, wet concrete reflections, natural motion blur, subtle camera shake, cinematic but believable. Characters ONLY from references, unchanged except for the scripted transformation; no physical, gender or clothing description: @image1 is the lead (appearance and outfit only from @image1); @image2 is the creature @image1 becomes (after the transformation @image1 looks exactly like @image2). A uniformed security guard and later a resident are separate, clearly different-looking people, never resembling @image1 or @image2. No gore, no blood, no visible injuries. HARD PHYSICS RULE (every shot): all barriers — the booth glass, the metal security shutter, the glass exit door — are SOLID and impenetrable. No character or creature ever passes, clips, phases or ghosts through solid matter. A barrier is only crossed by visibly breaking or deforming it, and any damage is PERMANENT and stays on screen — cracked glass stays cracked, a dented shutter stays dented and bent, nothing snaps back to intact. BEATS (20 s): 0–2s: @image1 waits alone in the quiet garage while the guard watches from a lit booth; lights flicker; @image1's head slowly turns toward a distant sound. 2–4s: @image1 jerks violently, the guard steps back, @image1 drops a bag and collapses beside a parked car, then goes still. 4–7s: @image1 rises slowly with blank eyes, unnatural posture and twitching hands, transforming into @image2; the guard locks the booth and grabs the emergency phone. 7–10s: the creature (@image2) sprints at the booth and SLAMS bodily into the solid glass — it does not pass through; the glass visibly cracks and spiderwebs and stays cracked; the guard escapes through the rear door and runs between parked cars. 10–12s: a resident steps out of an elevator and freezes; the creature charges; the resident shoves a shopping cart into it, the cart physically collides and briefly stops it, then it shoves the cart aside and keeps coming. 12–14s: the guard triggers the ceiling sprinklers; water pours down; the soaked creature recoils under flashing emergency lights, briefly disoriented. 14–17s: the resident yanks down a heavy metal security shutter; the creature RAMS it repeatedly, the panel visibly DENTS and buckles outward with each hit and stays mangled, then it forces the buckled bottom edge up and squeezes through the torn gap it made (never through intact metal). 17–20s: FINAL BEAT — everyone runs for the building entrance; the creature reaches the solid glass exit door and slams into it; the glass cracks then shatters into falling shards, and it passes only through the broken opening as the lights flicker, vanishing into the dark rainy street; the survivors stand frozen, camera slowly turning back toward the flickering garage lights and the mangled shutter, holding on that view to the final frame at 20s. Continuous believable physics, real weight, momentum and impact; solid objects behave solidly; consistent identities and setting. SOUND: tense low drone and cinematic horror score, flickering-light buzz, wet footsteps, sprinkler water, metal denting and glass cracking, snarls and impacts, distant rain; NO spoken dialogue, NO voiceover. Negative: any character or creature passing, clipping, phasing or ghosting through solid glass, shutters, doors or walls; a damaged barrier snapping back to intact; any ethnic, racial, gender or clothing description; a lead not matching @image1, a creature not matching @image2; gore, blood or visible injuries; distorted limbs or faces; on-screen text, captions, logos or watermarks; identity changing outside the scripted transformation; slow motion; CGI-looking surfaces.

1 step
Seedance 2.520s · 16:9
Clips on this page (40)