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 19

Made with OpenClips.AI

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

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 @umesh_aion X

Premium automotive commercial, photorealistic, film-grade, ultra-cinematic, shot at night in a rain-wet neon-lit city; strong emphasis on REALISTIC PHYSICS - believable vehicle weight, suspension travel, tire grip, accurate reflections and real water spray. Subject in every shot: the vehicle from @image1 - exact make, model, shape, colour, wheels and trim ONLY from @image1, identical in every shot, no morphing; no added description of the car. TIMELINE (21 s): 0–3s: extreme macro on the car's rear emblem/badge, magenta and cyan neon reflections crawling slowly across the wet glossy paint, fine rain beads trembling on the surface. 3–6s: THEN a slow dolly along the flank, neon light streaks sliding down the doors and window trim, shallow depth of field. 6–9s: THEN a front three-quarter hero as the headlights ignite, a clean puddle mirror-reflecting the car and neon signs. 9–12s: THEN the car rolls forward slowly over glossy wet asphalt, tires parting a thin sheet of standing water with realistic spray and ripples. 12–15s: THEN a low tracking shot of the wheels turning, suspension compressing believably over a slight bump, droplets flicking off the tread. 15–18s: THEN a rear three-quarter as it eases away, taillights glowing, a soft mist of tire spray behind, convincing mass and momentum. 18–21s: FINAL BEAT, the car settles to a stop, camera cranes up to a low front hero angle, a final neon flare sweeps across the hood, holding on the front of the car to the final frame at 21s. Smooth stable professional camera, rich blacks, wet reflective highlights, cinematic color; the car matches @image1 exactly throughout. SOUND: a driving cinematic TECHNO / dark electronic music track that fits a sleek performance car - steady four-on-the-floor kick, deep pulsing sub-bass, tight hi-hats, a moody synth arp building through the clip, energetic and premium; layered with subtle engine hum and tire-on-wet-asphalt hiss and faint city ambience; techno music present and prominent throughout. NO spoken words, NO voiceover. Negative: a car not matching @image1, changing make/model/shape/colour, warped or melting body panels, morphing; distorted or invented badges or logos of any brand; floating or physics-defying motion, jittery editing; on-screen text, captions or price; watermark; low quality, blurry.

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

30 seconds | 16:9 | 12-shot live-action fashion-event vlog. Fictional dramatization. Documentary-style visual realism. SETTING A fictional high-fashion charity gala held at a historic grand palazzo on Venice's Grand Canal. The event is inspired by the atmosphere of an exclusive annual fashion gala, but is entirely fictional. Time: evening transitioning into night. Arrival by private water taxi along the canal, a torch-lit stone landing, a red carpet leading up shallow palazzo steps, photographers positioned on pontoons and along the fondamenta, press barriers, security personnel, elegant guests and spectators lining the water's edge. Inside: a frescoed ballroom with towering chandeliers, gilded mirrors, floral installations, long dining tables and warm candlelight. The environment feels like a genuine high-profile fashion event rather than a staged commercial. CHARACTERS @avatar as a fictional fashion creator, confident but slightly overwhelmed, wearing an original high-fashion couture outfit designed specifically for the fictional gala. A fictional celebrity guest wearing an original couture look. Fictional photographers, journalists, security personnel, event staff and fashion guests. The celebrity guest and everyone else around @avatar are generated extras with invented faces, not a second lead; @avatar is the only lead and the only person taken from the reference image. CHARACTER LOCK — HIGHEST PRIORITY: @avatar's facial identity, facial structure, exact skin tone, hairstyle, hair length, texture and colour, build and apparent age come entirely from the reference image — preserve them identically throughout, do not alter or reinterpret any of it. Preserve their gender presentation exactly as shown. No face changes, no identity drift. Human behaviour remains grounded and spontaneous. STORY 00–02.5s — ARRIVAL Handheld selfie footage from inside a private water taxi gliding down the canal toward the fictional gala. Torchlight and camera flashes are already visible ahead through the window. @avatar turns the camera toward themselves and says: ""Okay… we're actually here."" The camera shakes naturally as the boat slows near the landing. 02.5–05s — OUTSIDE @avatar steps off the boat onto the stone landing. The handheld camera briefly points toward the wet stone before being raised toward the venue. Crowd barriers, photographers on the fondamenta, security and spectators fill the landing. Hundreds of camera flashes reflect off the canal water, creating realistic exposure changes. 05–07.5s — THE LOOK Selfie camera reveals @avatar's complete couture outfit. They turn slightly toward the photographers. The camera struggles briefly with exposure from the intense flashes. Photographers react naturally. 07.5–10s — CARPET Handheld camera follows @avatar approaching the shallow palazzo steps. Photographers call out from behind barriers. @avatar stops and poses naturally. Camera operators and guests partially obstruct the frame. 10–12.5s — PHOTOGRAPHERS Rapid camera flashes fill the frame. Several fictional photographers call @avatar's name. @avatar laughs and says: ""There's literally a thousand cameras."" The camera shakes slightly from the surrounding crowd. 12.5–15s — CELEBRITY ENCOUNTER @avatar turns and unexpectedly sees another fictional celebrity guest arriving by boat. They exchange a quick hug. @avatar turns toward the phone and quietly says: ""I did not expect to see them here."" 15–17.5s — INTERVIEW A fictional fashion reporter approaches with a microphone. ""What are you wearing tonight?"" @avatar gives a short natural answer describing the original couture look. Background photographers continue taking pictures. 17.5–20s — RED CARPET CHAOS Security gently directs guests toward the steps. Photographers continue shouting questions. Another guest briefly blocks the camera. @avatar laughs and adjusts their position. The moment feels spontaneous and unscripted. 20–22.5s — STAIRS @avatar climbs the shallow palazzo steps. The handheld camera tilts upward toward the ornate facade and enormous crowd. Flashes continue behind them. Natural footsteps, crowd noise and distant water lapping dominate the audio. 22.5–25s — INSIDE Cut to handheld footage entering the frescoed ballroom. Warm chandelier light reveals monumental architecture, elegant guests, floral installations and beautifully arranged dining tables. @avatar quietly says: ""This is insane."" 25–27.5s — THE ROOM The camera turns toward a grand dining room filled with fictional fashion personalities and celebrity guests. People talk naturally at tables. Waiters move between guests. Camera flashes occasionally appear in the distance. @avatar slowly pans across the room. 27.5–30s — FINAL MOMENT Selfie shot. @avatar smiles toward the camera and says: ""Okay… phone's going away now."" They lower the phone. The image becomes partially obscured as the recording ends. CAMERA Grounded handheld smartphone-vlog cinematography. Mix: selfie-camera footage, rear-camera POV, wide exterior coverage, close fashion details, crowd reaction shots, brief interview perspective. Natural handheld instability, realistic walking movement, small framing corrections, autofocus hunting between faces and background, exposure pumping caused by camera flashes, occasional motion blur, natural lens smudges and reflections, plausible smartphone camera behaviour. No cinematic gimbal movement, no impossible camera transitions, no floating camera, no excessive slow motion, no polished fashion-film cinematography. LIGHTING Lighting originates from the actual environment. Exterior evening light mixed with torchlight, dock lanterns and intense photographer flashes. Natural exposure shifts when the phone moves between dark surroundings and bright flashes. Inside the gala, warm chandelier and candlelight illuminate the frescoed interior. Realistic highlight roll-off, natural skin tones, deep but detailed shadows. No artificial rim lighting, no excessive beauty lighting. PHYSICS Real gravity and momentum. Guests walk naturally on steps and carpet. Couture garments respond naturally to movement. Hair reacts naturally to the breeze off the water. The water taxi moves with realistic momentum. Camera movement corresponds to @avatar's actual hand and body movement. Crowds maintain believable spacing. Security physically guides guests without exaggerated force. No floating clothing, no impossible fabric movement, no supernatural effects. HUMAN PERFORMANCE Natural high-profile-event behaviour. @avatar appears excited but slightly overwhelmed. Photographers react quickly to celebrity arrivals. Guests pose briefly before continuing. Security remains professional. Journalists ask short questions. Crowds react naturally. No exaggerated screaming, no theatrical acting, no artificial influencer poses, no perfectly synchronized crowd reactions. AUDIO Authentic live-event audio. Camera flashes, crowd chatter, photographers calling names, security instructions, the water taxi engine and dock bumpers, footsteps on stone and marble, distant water lapping, journalist questions, microphone handling, soft indoor conversations, cutlery and dining ambience, natural phone microphone compression. Dialogue remains clearly intelligible. No music, no cinematic sound effects, no artificial bass drops, no trailer-style audio. VISUAL CHARACTER Photorealistic live-action footage. Authentic luxury fashion-event vlog. Natural skin texture, realistic couture fabrics, detailed embroidery, tailoring and accessories, believable palazzo architecture, realistic photographer equipment, natural smartphone-camera imperfections, subtle sensor noise, natural motion blur, imperfect handheld framing. The footage should feel like a real fashion creator secretly documenting their own evening rather than a professionally produced fashion advertisement. BROADCAST AND EVENT GRAPHICS No official real-world gala or Carnevale branding. Use only subtle fictional event graphics when naturally visible on press screens or venue displays. A fictional event title may appear briefly: ""THE GRAND CANAL GALA."" Graphics must look like authentic event signage rather than futuristic interfaces. No real celebrity names, no real celebrity likenesses, no real television network logos, no copyrighted event branding. Avoid: real celebrity likenesses, real fashion personalities, real event logos, real Met Gala or Venice Carnevale branding, fake-looking celebrity faces, CGI appearance, video-game aesthetics, plastic skin, excessive HDR, oversaturated colors, perfect framing, cinematic camera movements, beauty-filter faces, artificial crowd behaviour, impossible fabric physics, overly staged red-carpet poses. CONTINUITY Maintain consistent @avatar identity, face, hairstyle, makeup, couture outfit, accessories and physical appearance throughout all 12 shots. Maintain the same fictional celebrity guest when they appear again. Maintain consistent palazzo architecture, steps, red carpet, crowd layout and lighting. @avatar's outfit must remain physically identical throughout the entire event. Maintain consistent smartphone-camera characteristics, exposure behaviour and handheld movement. Every 2.5-second shot begins from the physical state established by the previous shot. The exterior sequence must naturally lead from boat arrival to red carpet to steps and then interior gala. The entire sequence must feel like one continuous evening documented by the same creator on their phone. End when @avatar lowers the phone and stops recording.

1 step872.8K
Seedance 2.530s · 16:9
Inspired by shanyanggmon X

Create a 15-second photorealistic workshop video of @product being carved from a single block of wood. Keep @product locked to the reference: same silhouette, proportions, colours, livery and details once the form appears. One object, never duplicated. Two maker hands only — no faces, no other people. @product is an open-wheel race car: low nose, front wing, cockpit, sidepods, rear wing, slick tires. Do not invent extra logos. 0–2s — raw wood. An unworked block of pale hardwood sits on a worn workbench. Two hands pencil the outline of @product onto the top grain. Soft workshop light, wood-pencil scratch, distant shop ambience. 2–6s — carve the form. Hands cut, chisel and sand. Shavings curl off. The open-wheel body of @product emerges from the block: same shape as the reference, still raw wood. Macro of blade in grain, then a wider bench shot. Same block throughout. 6–10s — parts and paint. Hands fit small wooden details that belong to @product (front wing, rear wing, cockpit opening, wheels). Then stain and paint match the reference colours. Wet brush, even coats, wood grain still visible. 10–15s — finished on track. The completed wooden @product sits on empty asphalt under natural daylight. A gentle push, it rolls forward a short way, slow low orbit hero of the carved open-wheel car. No on-screen text. Sound: pencil, chisel taps, sanding, brush, quiet tire roll. No dialogue. No titles, no subtitles, no watermark, no logos that are not already on @product. Duration: exactly 15 seconds. Aspect ratio: 9:16.

2 steps1.3K127.8K
MiniMax H315s · 9:16
Inspired by HeyAbhishekon X

Create a 15-second premium cinematic commercial for @product. The film should feel like a high-budget sportswear advertisement: premium product cinematography, basketball-heritage mood, modern streetwear energy. Ultra-realistic. Elegant pacing. Bold final hero. No fantasy effects, no exaggerated CGI, no distorted proportions. @product stays locked to the reference: same shape, colours, materials, finish, label and logo in every shot. One single product, never duplicated. Shot flow, 15 seconds: 0–2s — box arrival and lid lift. @product shoebox on a dark studio floor under a focused overhead spotlight. Slow overhead push-in. The lid opens, tissue rustles, light spills inward. 2–5s — reveal and material macros. @product is lifted from the box in a low-angle beauty shot. Then tight glides across the real materials: the upper's own material and texture, overlays, any laces, collar, toe, midsole and outsole tread exactly as @product shows them. Light travels across the surfaces. No extra marks invented. 5–8s — court heritage. @product worn on a polished indoor basketball court, warm hardwood, soft arena light. Low wide-angle, then a low tracking shot through a moody arena tunnel. Only the legs and the shoe — no face, no other people. Distant ball bounce, sneaker squeak, firm footsteps. 8–11s — impact and street. A planted step in high-speed slow motion: the sole compresses, fine dust reacts. Then @product on a clean city street at blue hour, low dolly, confident walk forward. Legs and shoe only. 11–15s — studio hero. @product floats on deep black; a controlled orbit shows the full silhouette. A light sweep in @product's own accent colour travels collar to toe. It settles on a reflective dark floor with soft highlights in that colour. Slow low-angle push-in into the final hero pose. Fade to black. No end card, no typography. Sound: cardboard, tissue rustle, material creak, rubber friction, court squeaks, distant basketball, controlled whooshes, warm bass, a clean sting at the end. Music minimal, stylish, building into the hero. No on-screen text, no titles, no subtitles, no watermark, no logos that are not already on @product. Duration: exactly 15 seconds. Aspect ratio: 9:16.

2 steps403.6K
MiniMax H315s · 9:16
Inspired by @abs_uiuxon X

Generate a video of a moving billboard, throwing the product in your hands.

3 steps782.7K
Seedance 2.010s · 16:9
Inspired by @nicoroze591on X

Step 1 — Product Shot Turn the shoe in your reference photo into a clean, isolated product shot — same design, any straps, heel and colours preserved exactly. Neutral studio background, soft even lighting, three-quarter angle. Ultra-realistic, sharp focus. Step 2 — Flower @image1 is your product shot. Generate a real flower (rose, tulip, orchid, daisy — whichever fits) whose species and petal colour echo @image1's own colour, material and silhouette. Sitting on a warm, softly lit surface. Extreme macro, natural botanical detail, no plastic, no glass, no crystal. Step 3 — Final Video @image1 is the finished shoe — the foot must end up wearing exactly this. @image2 is the flower the foot steps onto — same species and colour. Extreme macro close-up, camera slowly orbits around the foot and the flower@image2. A bare foot lowers onto the flower@image2 on a warm-lit marble surface. As the foot presses down, the petals unfold and wrap around the foot and ankle as it sinks in — any straps forming, any embellishments appearing, the heel taking shape — until the petals fully resolve into the exact shoe@image1. Motion is continuous and graceful throughout. Warm golden lighting, elegant mood, ultra-realistic textures. AUDIO: soft elegant music (piano or strings) with gentle petal-rustle and skin-contact foley, one soft chime as the shoe fully forms.

3 steps352460K
Seedance 2.510s · 9:16
Inspired by @ayzalnooor24521on X

ASSET MAP — every reference is bound here and cited by tag below: @image2 — Avatar 1. Refer to @image2 for the person: their face, identity and the clothes they wear. The person in every shot is exactly the person in @image2 and nobody else; read it all off @image2 and invent nothing. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Use they / their / them only. @image1 — the product map. Refer to @image1 for the piece: its shape, proportions, material, finish, stones, clasp and colours, exactly as shown. Pick one single piece from @image1 for this film. Whichever piece you pick is the piece in every shot, from the first frame it appears in to the last. The numbering follows the order the references are attached. A 30-second cinematic luxury jewellery advertisement in a warm and elegant style, in which the person from @image2 unboxes and wears the piece from @image1 through one golden morning. 0–4s — A beautifully decorated bedroom in soft morning sunlight. A premium gift box sits on a wooden table. The camera pushes in slowly. 4–8s — The person from @image2 gently picks up the box. A delicate, unhurried unboxing moment, camera close on their hands. 8–13s — Cinematic close-up of their face and hands as they lift the piece from @image1 out of the box. 13–18s — Detailed macro of the piece from @image1 turning slowly in soft golden light, its stones and finish exactly as @image1 shows them. 18–22s — They fasten the piece on gracefully, the camera holding on the design and its shine. 22–26s — A peaceful moment near the window, a cup held in warm sunlight, the piece catching the light against their skin with realistic shadows and reflections. 26–30s — The gift box in the final frame with the piece from @image1 resting in it, camera easing in and settling. This is the last image of the film. Soft cinematic lighting, warm golden tones, luxury commercial aesthetic, smooth camera movements, shallow depth of field, photorealistic details. The person from @image2 keeps the same face, hair and clothing in every shot. The only jewellery on them anywhere in the film is the piece from @image1. Before they put it on, the skin at their neck, ears, wrists and hands is plain and bare, and their clothing is exactly as @image2 shows it; from the moment they fasten it on, the piece from @image1 is the only thing they wear on their skin. The piece from @image1 keeps the same shape, stones, metal and finish in every shot, and whatever engraving or marking @image1 shows is the only marking on it. No subtitles, no captions, no on-screen text. No music.

2 steps21214.3K
Seedance 2.530s · 9:16
Inspired by @de_mon010on X

Create a first-person POV viral video showing the magic of architectural design coming to life. Real hands in black leather gloves hold up an architectural blueprint of the uploaded building, then pull it away to reveal that building magically assembling in real-time, exactly as shown — same shape, colours and materials; nothing invented or redesigned. Its own walls, frame, roof and windows rapidly materialize with cinematic effects, dust clouds billowing as construction happens at impossible speeds. The blueprint elements transform into real structural components. Set on a bright sunny construction site with clear blue skies.

2 steps40319.5K
Seedance 2.510s · 9:16
Inspired by @PrometheanAIXon X

@avatar is the person walking - 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: a sharp all-black tailored suit - single-breasted jacket with narrow lapels worn closed, straight-leg trousers, a plain black shirt buttoned to the collar with no tie, polished black shoes. Monochromatic, unbranded, no lettering. Fit each garment to their body naturally without changing its design or cut - the garment is fixed, only its drape adapts. Same outfit in every second. 10-second hyper-realistic red-carpet arrival, vertical 9:16, one unbroken shot, late at night. @avatar walks straight toward the camera down a deep red carpet holding direct eye contact with the lens, framed head to toe. A press line runs along both sides behind a low barrier: photographers shoulder to shoulder, long lenses up, firing out of sync. THE LOOK IS HARD DIRECT FLASH. Harsh on-camera flash dominates every frame - bright speculars on skin and black fabric, deep contrast, a crisp hard shadow on the carpet behind @avatar, and fast falloff into black past them. Side flashes rake in at different intensities with overlapping shadows and occasional lens flare; between bursts the scene drops to dim tungsten and the carpet reads deep and saturated. Each burst freezes @avatar razor-sharp mid-stride while the crowd behind smears. Eye level, 35mm, flash at the camera - aggressive tabloid arrival, not soft editorial. High-ISO grain, real skin texture, five fingers, correct legs and feet. [0-4s] The clip opens on the peak of a flash burst with @avatar already mid-stride - no fade from black. @avatar walks at an even confident rhythm, arms swinging subtly, shoulders relaxed, never an exaggerated runway pose. [4-7s] Midway a volley hits from the left, then the right, lighting their face from both sides at once as the framing tightens toward three-quarter. [7-10s] In the last beat @avatar arrives close to the lens, still walking and still holding eye contact, one final burst fills the frame, and the clip ends on that motion. Diegetic sound only: dense overlapping shutter clicks and flash recycle whine, steps on carpet, photographers calling over each other, a low crowd murmur behind the barrier. No BGM; generate only environmental sounds and action sounds. No subtitles.

1 step392.3K
Seedance 2.510s · 9:16
Inspired by @meAsifAion X

A relaxed boardwalk stroll turns into a slick, deadpan action sequence when a bathrobe-clad parent takes down three cocky skateboarders for ruining their kid's ice cream — capped with an unimpressed freeze-frame.

1 step151.3K
Seedance 2.515s · 16:9
Inspired by @ZaraIrahhon X

Premium live-action vampire-romance short-drama teaser (ReelShort / DramaBox style), ultra-realistic cinematic, natural skin texture, emotionally expressive performances, consistent characters throughout. UNHURRIED, BREATHING PACE — every spoken line is delivered slowly and clearly, with a real beat of silence and a visible breath before the other character replies; never rushed, never overlapping; let each line land. LEADS: @image1 is the mortal lead and @image2 is the vampire lead. CHARACTER LOCK — HIGHEST PRIORITY: each lead is exactly the person in their own reference. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve each lead's gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. Preserve their gender presentation exactly as shown. Use they / their / them only. No face changes, no identity drift. No other people. 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. WARDROBE (fixed design, adaptive fit): @image1 wears a simple loose period nightshirt, cut unisex; @image2 wears an elegant black-and-crimson velvet Victorian coat and a piercing gaze from their own eyes. 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. SETTING: a forgotten gothic castle interior lit only by moonlight through towering stained-glass windows, flickering candles and fireplaces, drifting mist, ancient chandeliers, marble floors, velvet curtains, tall bookshelves, gothic arches, carved stone, floating dust. Palette: rich black, crimson, silver, deep blue. Darkly romantic, elegant, seductive but not explicit; tension through eye contact, silence, restrained emotion, powerful chemistry. Prioritize medium close-ups, close-ups, extreme close-ups, slow push-ins, over-the-shoulder shots, trembling hands, subtle breathing, intimate framing. TIMELINE (30 s): 0–6s: SCENE 1 — @image1 walks cautiously down an abandoned castle corridor holding an antique candle, the flame flickering as if watched. They stop, breathe, and whisper slowly: "I shouldn't be here..." — then a long beat of silence, mist drifting, before @image2's voice echoes from the dark, calm and unhurried: "...You finally came." 6–13s: SCENE 2 — a massive stone sarcophagus. Its heavy carved lid grinds and slides aside under its own weight, fine dust and grit spilling off the edges. A single hand rises and grips the stone rim; then, in ONE smooth, controlled, believable motion, @image2 sits up and rises to standing — deliberate and elegant, straightening the coat, their eyes lifting to lock on @image1. Real weight, real balance, limbs intact; no jerky, floating, teleporting, clipping or morphing motion. @image1 freezes. A beat. @image1, barely audible: "Who... who are you?" A breath. @image2, calm and low: "The one fate refused to bury." 13–19s: SCENE 3 — @image2 crosses the room slowly and stops inches from @image1, gently lifting their chin, studying their face as if recognizing someone long forgotten. A held beat, only breathing. @image2: "Your blood remembers a war the world has forgotten." @image1 swallows, a beat. @image1: "I don't know what you're talking about." 19–24s: SCENE 4 — @image1 steps back, refusing to surrender; @image2 blocks their escape effortlessly, unhurried. A beat. @image1, steadier than they feel: "I'm not afraid of you." A slow beat, a faint knowing smile. @image2, soft: "You should be." 24–28s: SCENE 5 — @image2 leans closer, eyes locked with @image1, only their breathing audible. A long beat. @image2, quiet, almost aching: "I searched centuries for you." @image1 breathes. @image1, barely a whisper: "Why me?" 28–30s: SCENE 6 — the castle doors slam shut by themselves, candle flames extinguishing one by one; @image2 slowly reaches for @image1's hand as they hesitate, torn. @image2, low: "You may fight fate..." — @image2 intertwines their fingers with @image1's — "...but you'll never escape me." FINAL SHOT: extreme close-up of @image1 and @image2's locked eyes, orchestral swell, smash cut to black before they kiss — cliffhanger. Cinematic hard cuts, dramatic push-ins, elegant slow motion. SOUND: realistic design — orchestral strings, deep piano, distant thunder, candle crackles, footsteps, soft breathing, fabric movement, subtle heartbeats; the spoken English dialogue is clear, slow and perfectly lip-synced, ONE voice at a time, with audible pauses and breaths between lines — never rushed or overlapping; each lead speaks in their own natural speaking voice. No gore, no cheap horror, no costume-look, no monsters, no modern clothing, no on-screen text or subtitles. Negative: any gendered, ethnic or racial description of either lead; rushed or overlapping dialogue, mumbling or unclear speech, lip movement without audible voice; coffin opening that looks glitchy, clipping, jerky, teleporting or with morphing or extra limbs; deformed or changing faces, changing hairstyles, extra fingers, plastic skin, watermark, on-screen captions.

1 step24018.1K
Seedance 2.530s · 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
Inspired by shanyanggmon X

Create a 15-second 9:16 ultra-realistic miniature model-kit assembly video of @product. @product is the exact model in the reference image. Same shape, paint, markings, trim and wheels as the reference in every frame. One object, never duplicated. Never turn it into a full-size car. OPENING: Frame 1 is already the workshop table with the sealed kit box — no still packshot as a plate, no grey seamless, no portrait. Hands only. Two realistic adult hands, five fingers each. No faces, no other people. 0–3s — unbox: Overhead / POV macro. A premium sealed model-kit box sits on a clean workshop mat. Hands set it down, open it, peel wrapping, lift fitted trays. Parts inside match @product: body shells in its exact paint colour, its trim, wheels, tyres, interior, screws. 3–8s — assemble: Fast but readable time-lapse. Chassis on the mat, engine and suspension, axles, wheels tightened, interior, doors, body panels in the reference's paint colour, trim, lights, and any markings already on the sides as in the reference. Miniature screwdriver and ratchet. Same two hands throughout. 8–12s — finish: Last bolt, wipe with a detailing cloth, place @product on a small rotating display stand. Workshop lighting becomes cinematic. Light sweep. Headlights click on. 12–15s — hero: Slow orbit of the completed @product, its paint and trim catching the light exactly as in the reference. Subtle engine sound. End on a strong 9:16 hero. No on-screen text. Sound: cardboard, tape, tray clicks, screws, ratchet, panel snaps, cloth, headlight click, a small engine blip. No narration, no music bed, no subtitles, no watermark in the prompt (the platform may stamp one). No extra fingers, no floating tools, no full-size car, no morphing paint, no logo distortion. Duration: exactly 15 seconds. Aspect ratio: 9:16.

2 steps
MiniMax H315s · 9:16
Inspired by @ImaStudio_aion X

A crisp autumn afternoon on a tree-lined city path takes an unexpected turn when a passing cyclist clips your avatar's shoulder mid-stride. In that instant, time suspends — earbuds, a latte cup and a small parcel are caught in extreme slow-motion bullet-time, rotating through warm autumn light as coffee arcs and leaves drift mid-air. Time resumes, everything falls, and your avatar turns to camera with a perfectly deadpan "did that really just happen" expression. A polished, 15-second cinematic bullet-time moment blending high-fashion editorial style with a touch of everyday comedy.

2 steps211.4K
Seedance 2.515s · 9:16
Inspired by umesh_aion X

Hyper-realistic 15-second 16:9 continuous ice action. Sound ON. OPENING: Frame 1 is already ON THE ICE, mid-stride. Never a studio portrait or grey still. The person is exactly the attached portrait. A fitted skating outfit and skates. No other people. No on-screen text. PHYSICS — MANDATORY (this failed last time): Sea ice is heavy, thick, slow. Plates do not teleport, stretch, or explode into CGI shards for no reason. A crack opens from a real stress line and widens at a believable speed. When they step on a floe it tilts under their WEIGHT, then they recover. Jumps need a visible crouch, takeoff, flight, and a heavy landing that shakes the plate. No sliding through solid ice. No ice appearing from nowhere. Gravity always down. Camera can move, but the world stays physically consistent. 0–5s: They skate a flat sheet. ONE crack races under the blades. They hop it. The ridge behind them lifts slowly, not a firework. 5–10s: The sheet splits into TWO or THREE large floes. They commit to one plate; it rotates slowly. They skate across it. 10–15s: They jump a dark-water gap onto the next floe, land hard, then a last push onto the snowy bank. Ice behind them is a few big tilting plates — not confetti. AUDIO: blades, ice groan, crack, splash, wind. No voiceover. Duration 15s. Aspect 16:9.

1 step627.3K
MiniMax H315s · 16:9
Inspired by @AmirMushichon X

Turn your own product photo into a warm, everyday moment. First we build one clean reference image of your exact product, then bring it to life in a short kitchen film: found in the fridge, poured with a light touch, shared over genuine laughter with a friend. Warm daylight, real hands, no faces cast, one continuous take from start to finish.

2 steps675266K
Seedance 2.515s · 9:16
Inspired by @itsSaira_1on X

Generate a video of yourself with your dragon.

1 step1321.1K
Seedance 2.515s · 16:9
Inspired by @Kiber_Allaon X

ONE PRODUCT. EIGHT SHOTS. NO PEOPLE ANYWHERE IN FRAME. ASSET MAP - every reference is bound here and cited by tag below: @image_1 - the product. This is the only physical object in the film. @image_1 is the product source only - its background, surface, props, shadows, framing, lighting and colour grade are ignored. Nothing behind or around the product in @image_1 carries into this film. PRODUCT LOCK: the object in every shot is exactly the object in @image_1@image_1. Preserve its silhouette, proportions, material, finish, packaging artwork, colours, typography and every printed detail exactly as shown, identically from the first frame to the last. Never redesign, restyle, re-letter, relabel, recolour or open the product, never add lettering, a logo, a seal or a symbol that is not already on @image_1, never remove one that is, and never damage, break, dent, crush or deform it. It stays whole and sealed for the entire film. Only one of it exists. WORLD (from this text, never from @image_1): a pure black void with no floor line, no horizon, no table, no plinth, no pedestal, no stand, no podium, no room and no set. The product rests on nothing at all until the final shot. One hard rim light rakes the product from behind, a soft key comes from the front left, and a black glossy reflective plane exists only in the final shot. The product is lit like a jewel in a museum case. COLOUR: the rim light, the mist, the liquid and every particle are tinted with the colours already present on @image_1 - if the product carries one dominant colour, everything takes that colour, and if it carries several, they take its whole palette. Nothing in the film is neutral white or plain grey, and everything else stays black. PARTICLES (from this text): fine glowing dust, crystalline shards and clean liquid droplets. They orbit, burst and streak past the lens. They are never a hanging thread and they never touch or stick to the product. PACE: real commercial speed, already at full velocity on the very first frame. Slow motion happens in exactly one shot and nowhere else. Cuts are hard and clean, and no single shot runs longer than about two seconds. Shot 1: the very first frame is already a large, bright, close three-quarter hero view of the product filling the centre of the frame, and it is already in motion - driving forward through a curtain of glowing mist that blasts apart around it and streaks past the lens. The product never starts small, never starts far away, never approaches from the distance and is never a speck against the dark. <a deep rushing whoosh and a bright particle burst> Shot 2: it slams to a dead stop in hero position at the centre of the frame as a shockwave ring of dust and droplets blows outward past the lens and the rim light snaps on hard behind it. <a heavy impact and a wide expanding boom> Shot 3: the camera makes one fast tight orbit around the product while a hard bar of light rakes slowly across its surface, lighting up its material, its finish and every printed detail in turn. <a rising metallic sweep> Shot 4: hard cut to extreme macro on one small part of the product. A single liquid droplet runs across the surface, light kicks off it, and the micro texture and grain of the material are fully readable. <a small wet tick and a soft high shimmer> Shot 5: the product drops into a shallow pool of glossy liquid and throws a tall sharp splash crown around itself, droplets shooting straight up and raining back down. <a thick heavy splash> Shot 6: slow motion, and only here. The product hangs dead centre, whole and untouched, while a full three hundred and sixty degree shockwave of glowing dust, crystalline shards and liquid droplets detonates outward around it and streaks past the lens, then hangs almost still in the air for half a second. <a low detonation and a long trailing particle wash> Shot 7: back to full speed. Every particle reverses at once and rushes back inward, collapsing into a tight bright halo that spins one full turn around the product and dies out. <a fast inward suck and a clean shimmering snap> Shot 8: the final hero. The product stands upright and perfectly still on a black glossy reflective plane, the last of the dust settling and glinting around its base, and the camera holds rock steady. <one deep bass hit and a soft settling patter> (a cool modern advertising track with punchy low bass, bright percussion and confident premium electronic-pop energy, building through the film and landing hard on the final shot) Only one product exists in this entire video and it is never opened, never broken and never duplicated. There are no people, no hands, no fingers, no arms, no human reflections and no animals anywhere in frame at any moment. No kitchen, no table, no wooden surface, no studio set, no plinth, pedestal, stand or podium under the product, no storyboard grid and no numbered frames. Keep it subtitle-free, avoid generating any text or subtitles anywhere in the frame, do not generate any logo, label or lettering other than the artwork already printed on @image_1, and do not generate a watermark. No long hanging thread of liquid, no endless slow motion, no frozen still-life opening frame, no second product and no voiceover. The very first frame of the film is never black, never empty and never a distant wide shot - the product is already large, lit and moving in it.

2 steps9209
Seedance 2.015s · 1:1
Inspired by @michaelraboneon X

Generate a short video of yourself on your last vacation visit.

1 step14948
Seedance 2.010s · 16:9
Inspired by Dyyhoangon X

Generate a video in which a rider drops a long flight of stone steps through an ancient desert city, launches off a stone ramp, flies over the rooftops and sprints away into a rising dust cloud, with a second rider closing behind.

4 steps34989
Seedance 2.015s · 54:31
Inspired by @AIwithkhanon X

ASSET MAP — every reference is bound here and cited by tag below: @avatar — the model. This is the person; gender, face, hair, skin and body proportions come entirely from @avatar and not from this text. Its clothing, pose, framing, background and lighting are ignored completely. @product — the sunglasses, the first reference image (@image1). Frame shape, frame colour and finish, lens shape and lens tint come entirely from @product and not from this text. ATTACHED IMAGES ARE MANDATORY AND FINAL: @avatar is the person in every shot and @product are the only sunglasses in the film. The attached images outrank every word written below them: wherever an image and this text disagree, follow the image. CHARACTER LOCK: @avatar keeps the same facial identity, facial structure and proportions, eye shape and spacing, eyebrows, nose, mouth, jawline, exact skin tone and skin texture, hairline, hairstyle, hair length, texture and colour, distinctive marks, apparent age, build and body proportions in every shot, from the first frame to the last. The gender presentation of @avatar stays exactly as shown in that reference; do not masculinize, feminize or otherwise reinterpret it. Do not redesign, beautify, slim, age or de-age @avatar. Preserve their gender presentation exactly as shown. Use they / their / them only. PRODUCT LOCK: @product keeps exactly the frame shape, lens shape, frame colour and finish, lens tint and every detail of its reference in every shot — never regularised, redesigned or recoloured. Never add a logo, letter or mark that is not on the reference, and never remove one that is. WARDROBE (from THIS TEXT, never from @avatar): @avatar wears the same outfit in every shot — a colour-blocked nylon windbreaker in white, cyan and magenta panels worn open over a plain white cotton tee, high-waisted acid-wash straight-leg jeans, white canvas high-tops with slouched white socks. Every garment is cut unisex and keeps that same cut whoever appears in @avatar: the tee is a plain crew-neck whose hem reaches below the waistband of the jeans, and the jeans are straight and reach the ankle. Each garment keeps its design, cut, proportions and colour; only its drape adapts to the body. ONE-SENTENCE SUMMARY @avatar models @product against a flat scarlet paper backdrop in a fast-cut 1987 sunglasses campaign film, with ice cream, bubble gum and a cold drink between editorial poses and macro passes over the frames. DETAILED PLOT — nine shots, fast hard cuts, roughly one and a half seconds each Held through every shot: one flat scarlet paper backdrop with a hot-spot where the hard key lands; the same outfit; @product worn on the face except where a shot says otherwise. The cutting is fast but the motion inside each shot stays small and coherent — no lunging, no whipping, no sudden turns. Shot 1 opens already in motion on a readable face, never on an empty frame or a fade from black. Shot 1: Fixed camera, close-up. @avatar takes a small bite from a vanilla ice cream cone while wearing @product and smiles into the lens. The hard key from the left lays a crisp shadow of the frames on the cheek and a cyan rim traces the jaw. <the crisp bite of the cone> Shot 2: Cut to a fixed camera, full-body wide. @avatar walks four steps toward the lens on the red paper in the white crew-neck tee and the full-length acid-wash jeans, the colour-blocked windbreaker swinging open, and settles into an editorial stance. <soft footsteps on paper> Shot 3: Cut to a fixed camera, medium close-up shot at a hard ninety-degree side angle, so only the profile of the face is seen and the edge of one lens and the temple of @product read as a clean silhouette against the red. <room tone> Shot 4: Cut to a fixed camera, close-up masked into a soft-edged circle like a 1980s television ident. @avatar blows a pink bubble-gum bubble until it fills the circle, then pops it and laughs. <the snap of the bubble> Shot 5: Cut to an extreme macro that tracks slowly across @product worn on the face, from the bridge along the browline to the edge of one lens, specular glints running over the tint. <room tone> Shot 6: Cut to a fixed camera, medium close-up. @avatar holds @product flat on one open palm, raised toward the lens and filling the middle of the frame, with the face soft behind it. <fabric shifting> Shot 7: Cut to a fixed camera, side view. @avatar lifts a plain glass bottle of dark cola, takes a sip, lowers it and grins at the lens, @product still on, wearing the white crew-neck tee and the acid-wash jeans. The bottle is smooth unmarked glass with straight parallel sides and a short plain neck, the drink inside a deep cola brown, with no label, no foil, no cap and no fluting or embossing anywhere on the glass. <the fizz of the drink> Shot 8: Cut to a fixed camera, close product shot with no person in frame: @product stands on a small off-white card laid on the red paper, rotating slowly through three quarters. A white bounce card shields the frame from the red paper so the colour of @product reads as it does in its reference, and the hard key lays a crisp shadow beside it. <room tone> Shot 9: Cut to a slow macro close-up of @product on the face of @avatar, the tint catching the scarlet of the backdrop, held to the final frame. <room tone> LIGHT AND STYLE Shot on 35 mm for a 1987 fashion campaign: saturated primaries, a dense scarlet backdrop, high contrast with clean blacks, warm halation around the brightest highlights, visible fine film grain and a faint gate weave. Period studio light, not modern beauty light — one hard tungsten key with crisp shadow edges, a cyan gelled rim from behind, a magenta bounce opening the shadow side, hard specular sparkle on glossy surfaces. Skin keeps real texture with visible pores and fine hair. Punchy period grade, dense reds, no teal-orange. CAMERA Fixed shots and slow push-ins only, one movement per shot. Hard cuts between shots, no dissolves and no speed ramps. HANDS AND PROPS Hands stay anatomically correct with five fingers on each hand wherever a hand is visible. The cone, the gum and the bottle stay separate objects in the grip. The ice cream stays a plain pale scoop, and the bottle stays smooth unmarked glass with straight parallel sides and a deep cola-brown drink inside — no label and no printed or embossed mark of any kind. AUDIO (a 1980s synth-pop groove at about 112 BPM — gated snare, drum machine kick, analog synth bass, bright bell stabs and tambourine, with thin tape hiss under it) CONSTRAINTS Keep it subtitle-free. Do not generate a logo, a brand name or a product label on any prop, garment or surface; @product keeps its own logo and markings exactly as shown, nothing added. Do not generate a watermark. Throughout the video, characters with completely identical appearance, clothing and accessories are prohibited; do not generate duplicate avatars or a twin effect, and keep only a single corresponding character in the same frame. The face of @avatar remains stable without deformation; movements are natural and smooth, with no stutter or flicker.

1 step458.3K
Seedance 2.015s · 1:1
Inspired by @SeharShinwarion X

Generate a twenty-second vertical ultra-realistic cinematic aerial stunt film from the provided first frame. ASSET MAP - every reference is bound here and cited below: @image_1 - the first frame of this video. It is the exact opening image, and the person in it is the athlete for the whole film. CHARACTER LOCK - HIGHEST PRIORITY: the athlete in every segment is exactly the person in @image_1. Preserve the facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions - identically, segment to segment. Preserve the 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. One single athlete appears in this film. ATTACHED IMAGE IS MANDATORY AND FINAL FOR THE OPENING AND THE IDENTITY: start from @image_1 as the exact first frame, and wherever @image_1 and this text disagree about a face, hair, skin tone, body, age, the jumpsuit, the harness or the helicopter interior, follow @image_1. The camera path, the timing and everything that happens after the first frame come from this text. WARDROBE LOCK: the athlete wears the matte black aerodynamic jumpsuit with dark red panels, the compact safety harness and parachute pack, black gloves, lightweight boots, clear goggles and the small helmet-mounted camera exactly as established in @image_1, unchanged from the first frame to the last. No visible logos, brand marks, printed words or numbers on any garment or on the equipment. Nothing is ever strapped to the feet of the athlete - no board, no ski and no equipment of any kind, at any point in the film. Both hands keep five fingers in every segment. Summary: a professionally supervised fictional stunt - the athlete exits a helicopter above Paris at golden hour, free-falls the full height of a vast wrought-iron lattice tower, passes it within metres, stabilises, deploys a guided parachute with a hard snap, and lands on marked open ground at the far end of the esplanade, well clear of the tower. Visual style: ultra-realistic vertical sports footage with the grit of real helmet-cam and chase-cam material - hard low golden light on grey zinc rooftops and cream stone, heavy motion blur, rolling horizon, lens vibration, fine grain, deep readable shadows. Cinematic but never glossy or staged. SPEED RULE - this is what sells the fall: the camera never travels at the same speed as the athlete during free fall. In every falling segment something must rush past inside the frame - the tower's ironwork, a platform edge, a cloud layer, the rooftops - so the speed is visible against a moving foreground rather than a still one. The horizon rolls, the frame vibrates, and the body is thrown by the airflow. 0-2 seconds: the film starts exactly on @image_1 and immediately moves. The camera pushes in fast from the doorway framing to a tight shot of the face of @image_1, wind hammering the jumpsuit and tearing at the hair, the rotor beat shaking the lens. The goggles come down over the eyes, the jaw sets, and the crew member deeper in the cabin slaps the shoulder of the athlete once. <rotor beat, hard wind at the open door, a single hand slap on fabric> (a low tense drone, one slow pulse) 2-4 seconds: one continuous shot from inside the door, camera locked to the doorframe. The athlete pushes off hard with both hands and falls away from the camera, shrinking fast against the rooftops in under a second while the doorframe stays in frame in the foreground for scale. Then the camera whips down after the athlete with full motion blur. The exit is fully visible - the body leaves the frame downward, never by a cut. <a hard push off metal, the wind opening into a roar, the rotor snapping away above> (the pulse cuts to silence) 4-7 seconds: helmet-camera point of view from the athlete looking down along the body - the boots against the rooftops far below, the iron tower rushing up toward the lens from the bottom of the frame, the city rotating slowly around the edges. The frame vibrates hard. <a solid wall of rushing air, the suit drumming, breathing inside the helmet> (a rising low string swell) 7-10 seconds: the camera drops to a chase position beside the athlete as they pass the tower within metres, belly-down and arms spread. The lattice ironwork rips past the frame at speed, one platform edge ticking by close to the lens, the golden light strobing through the girders. <ironwork wind roar, a hard flutter of fabric> (the swell keeps climbing) 10-12 seconds: a tight close-up on the face of @image_1 in free fall, filling the frame - the cheeks pulled back by the airflow, the goggles pressed against the skin, loose hair hammering across the temple, the eyes locked forward and calm. Brief slow motion, then back to real time. The face, hair and skin tone stay exactly as in @image_1. <the roar going slightly muffled, then full> (the swell thins to a single held note) 12-14 seconds: the hand of @image_1 finds the deployment handle and pulls it hard. The pack cracks open, the suspension lines rip out and snap taut, and a compact red-and-white canopy slams open above the athlete. The harness takes the weight with a hard jolt that throws the legs forward and the descent breaks sharply. Slow motion across the snap, then real time. <the pack cracking, lines snapping tight, a deep canopy boom, the harness creaking under load> (the held note breaks into a wide warm chord) 14-17 seconds: the camera settles behind and slightly above the athlete, hanging in the harness with both arms spread wide, the long formal lawns, gravel paths and clipped tree rows of the esplanade sliding beneath and a gilded dome standing in the distance ahead. The canopy breathes in the air above. <calm air, fabric luffing, distant city> (the chord opens up) 17-20 seconds: a low camera at grass height as the ground rushes up - the lawn filling the frame, then the boots slam down and take two hard running steps, the canopy collapsing forward onto the grass behind. Ground crew in high-visibility vests stand well back beside coloured markers. The camera rises and settles locked off on the face of @image_1, who straightens up facing the lens, still breathing hard, the dome and the grey Paris rooftops glowing behind. The composition holds still to the final frame. <ground rush, boots hitting grass, fabric collapsing, hard breathing, wind dropping away> (the chord holds and fades) Continuity and physics: one single athlete throughout, always the person in @image_1, in the same jumpsuit, harness and goggles from the first frame to the last. Every falling segment is the same uninterrupted fall, and the athlete is lower and closer to the ground in each one. Real air resistance and real mass: the body accelerates for the first seconds, the fabric flutters and snaps under load, the canopy inflates in stages and takes the weight before the descent slows, the lines stay attached and visible, and the landing carries forward momentum into two steps. The iron tower, the esplanade and the city stay background geography and are never touched, never landed on and never damaged; the landing ground is open, marked and well away from the tower. The jump is a supervised fictional stunt: the harness, the crew and the marked landing ground are visible, the canopy deploys cleanly, and the athlete lands safely on both feet. Constraints: no subtitles and no on-screen text of any kind anywhere in the film. Do not generate a watermark. Do not generate a logo.

2 steps98911
Seedance 2.520s · 9:16
@markgadala

SUBJECT ANCHOR: The pet in the input image is the protagonist. Keep its fur pattern, markings and eye colour identical in every shot. The input image defines the look of the whole film. TONE: The subject is worried, never amused. Mouth closed, eyes wide with concern. Wistful → alarmed → urgent → tender. Shot 1 (3s) — Profile shot at the window, slow push in. The subject gazes through rain-streaked glass, then spots something far below. Snap to close-up: pupils dilating, ears back. Rain on glass. Shot 2 (3s) — Wide kitchen, camera whip-pans with the movement. The subject bolts through the kitchen in one burst, knocking pots and pans flying behind it. Ceramic crashes, rolling metal. Shot 3 (2s) — Low-angle tracking down the hallway, the subject sprinting toward lens. It grabs a bright red knitted scarf from a coat rack in its jaws. The scarf streams behind it in the air, never touching the floor. Shot 4 (3s) — Handheld, low, through a rain-slicked city street at dusk, neon on wet asphalt. The subject weaves between honking cars. Car horns, heavy rain. Shot 5 (4s) — Slow push-in to a static wide. Under an awning, a tiny shivering puppy. The subject gently drapes the red scarf around it, then curls up beside it. Rain softens, quiet warm ambience. NEGATIVE: no smiling, no scarf dragging on the ground, no text, no captions, no logos, no watermarks.

2 steps16918.6K
Kling 3.010s · 16:9
Inspired by @eshal__aion X

SCENE 1 0 to 4s — arrival. Crisp morning, light snow falling. @avatar steps out of a timber chalet doorway, breath visible in the cold. Camera trails from behind down a snowy cobblestone lane lined with wooden cottages, then swings round into a close-up as @avatar turns, catches the lens, and laughs, shaking their head slightly. SCENE 2 4 to 8s — first ski run. @avatar glides down a gentle beginner slope, snow spraying at the skis, pines blurring past. A low chase shot from behind, then a front-facing action-camera angle catching @avatar laughing while wobbling and steadying. SCENE 3 8 to 12s — pine forest. A worm's-eye view up through frosted branches, pale sun filtering down with soft flares off ice crystals. Cut to a close-up of @avatar walking through untouched snow, one mittened hand trailing a low branch, stopping to exhale a long visible breath and look up. SCENE 4 12 to 16s — café break. @avatar sits at a frosted window inside a small timber café, both hands wrapped round a steaming mug of hot chocolate under whipped cream. Warm interior light against the blue-white world outside. Close-up of marshmallows melting, then @avatar's contented half-smile watching the snow drift past the glass. SCENE 5 16 to 20s — sledding. @avatar pushes off on a wooden sled at the top of a gentle hill and speeds down laughing, hair flying loose from under the beanie. Camera tracks alongside at sled height. @avatar tumbles softly into a snowbank at the bottom, still laughing, covers their face with one mitten, then drops it and grins straight at the lens. SCENE 6 20 to 24s — evening market. A glowing market strung with warm fairy lights, snow settling on wooden stalls, steam rising from vendor carts. @avatar weaves through a crowd of generated extras (passers-by, never a second lead) sampling mulled cider and gingerbread, face lit by string lights and lantern glow. Close-up as @avatar's eyes widen at the taste, lights thrown into soft bokeh behind. SCENE 7 24 to 27s — sunset. A wide silhouette of @avatar on a snowy overlook as the sun drops behind the range, sky shifting pale gold into soft violet, scarf drifting in the wind. @avatar tilts their face toward the fading light, one hand holding the beanie in place. SCENE 8 27 to 30s — fireside. A cabin interior at night, fire glowing, snow at a frosted window behind. @avatar sits curled on a wool blanket, mug in hand, firelight flickering across the face. Final intimate close-up: @avatar looks straight into the lens, lifts the mug slightly in a small toast, and smiles. NOBODY SPEAKS. No lines are delivered to camera at any point. Every beat is carried by expression, gesture and movement. CAMERA. Authentic travel-vlog cinematography — handheld shake, slow push-ins, natural drifting movement, occasional POV, subtle motion blur. Smooth cuts between scenes, no flashy transitions.

1 step1693.1K
Seedance 2.530s · 16:9
Inspired by @Goodmanprotocolon X

Wet sand at the tideline holds the perfect impression of a bottle, until a wave rolls in and the real thing is sitting there, the bottle catching the light. Your avatar picks it up, mists it on, and walks the shoreline glowing gold. A 9:16 luxury beach beauty ad built around one seamless sand-to-product reveal.

2 steps171.2K
Seedance 2.515s · 9:16
Inspired by @AIwithSynthiaon X

Ultra-realistic emotional live-action scene: @image1 discovers their partner kissing someone else in a quiet café. Authentic emotion, natural crying, subtle expressions, no melodrama. LEADS (identity ONLY from references, identical every shot, no physical or gender description beyond the reference): @image1 is the heartbroken lead, in everyday casual clothing suited to a rainy evening, carrying a small bag — fit the clothing to their body naturally without altering their build or proportions; @image2 is @image1's partner; @image3 is the other person @image2 is kissing. Preserve their gender presentation exactly as shown. Use they / their / them only. They never swap, change or duplicate; background customers are clearly different-looking. LOCATION: a cozy modern café on a rainy evening, warm light, rain-beaded windows, a window table across the room. STAGING & EYELINE (critical): @image2 and @image3 sit together at the window table ACROSS THE ROOM, directly AHEAD of @image1 and within the line of sight; the couple is ALWAYS in front of @image1 and visible in the same frame as the reaction (over-the-shoulder from behind @image1 toward the kissing couple, or @image1 in foreground with the couple in soft focus ahead). @image1 must SEE them and lock gaze on them BEFORE any tears; @image1 is always turned toward and facing them, never crying while they are behind or out of view. BEATS: 0–4s: @image1 enters and scans the room; 4–8s: the camera reveals @image2 and @image3 kissing at the window table ahead; 8–13s: @image1's eyes land on them and stop, gaze fixed on the couple, expression shifting confusion to disbelief; 13–19s: @image1 slowly lowers the bag, still watching, and tears form naturally along the lower eyelids and roll down the cheeks; 19–22s: @image2 notices and their face falls to shock, @image3 turns uncomfortable; 22–25s: @image1 shakes the head once, heartbreak not anger, takes a step back; 25–30s: @image1 turns and walks toward the café door quietly crying, wiping the face on the way, and the shot holds on @image1 at the door, back to camera, to the final frame at 30s. CAMERA/LOOK: handheld cinematic, subtle movement — follow @image1 in, reveal the couple ahead, push closer on the reaction; realistic close-ups of eyes, trembling lips, tears; shallow depth of field, real skin pores, rain reflections, soft rainy light, natural motion blur, photorealistic. Crying spontaneous and uncomfortable, never glamorous. CONTINUITY: tears stay consistent once they appear; consistent clothing, hair, identity; no disappearing tears, no changing layout. SOUND: diegetic only — rain on windows, quiet conversations, cups, footsteps, subtle breathing; NO spoken dialogue, NO voiceover, NO music, NO invented language. Negative: any ethnic, racial or gender description; the couple positioned behind @image1 or outside the eyeline; @image1 crying while facing away from the couple or before seeing them; plastic skin, fake or disappearing tears, exaggerated crying, screaming, violence, distorted faces, extra fingers, identity drift, outfit changes, duplicated people, second lookalike, on-screen text, watermark, cartoon or CGI look.

1 step
Seedance 2.530s · 16:9
Inspired by SajidHassain6won X

ASSET MAP: @image1 — the storyboard sheet from step 1, rendered from the uploaded building photo (house, villa or architectural model). Wherever this prompt says @product or "the reference", it means that building exactly as it appears in @image1; follow its panels in order and never show the sheet itself. Create a 15-second ultra-realistic cinematic 9:16 video of @product being built as a luxury miniature countryside villa, then revealed at golden hour. Keep @product locked to the reference: same silhouette, proportions, materials and colours once the form appears. One object, never duplicated. Two maker hands only — no faces, no other people. 0–3s — empty plot. A miniature countryside diorama: lush grass, olive trees, natural rocks, rustic wooden fencing, rolling farmland and distant hills under an orange-pink sunset. The footprint of @product is marked in the earth. Soft cinematic aerial, shallow depth of field. 3–7s — villa rises. Two hands, macro, miniature tools. The walls of @product are laid in its own materials and colours, cement spread, its own roof set, its own doors and windows fitted, a covered outdoor dining patio added. Warm interior lights begin to glow. No cuts that break the same miniature. 7–11s — pool and water. Hands tile a crystal-clear turquoise swimming pool in front of @product: stone paving, wide steps, a dramatic infinity-style waterfall edge. Water fills; the cascade starts to flow with realistic liquid physics and photorealistic reflections. 11–15s — aerial pull-back. Smooth cinematic aerial pull-back revealing completed @product: glowing interiors, outdoor furniture, lanterns, olive trees, flowers, waterfall edge, the whole miniature property in golden-hour farmland. Hold the hero. No on-screen text. Sound: tiny masonry taps, water fill, waterfall, evening insects, a soft wind. No dialogue. No titles, no subtitles, no watermark, no logos that are not already on @product. Duration: exactly 15 seconds. Aspect ratio: 9:16.

2 steps301.2K
Seedance 2.0 Fast15s · 9:16
Inspired by frametheory058on 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 15-second ultra-realistic early-2000s consumer camcorder home video in London. 9:16. The person in the attached reference is the only person. OPENING — MANDATORY: Frame 1 is already in the London street, handheld camcorder running. They are already mid-run toward a bus. Do not open on a studio portrait, grey backdrop, still headshot, or the attached image as a plate. NEVER insert the attached still, a grey seamless, or a beauty-headshot as a cutaway. Every single frame is handheld location footage. The spoken line is delivered on the street, in the hoodie, after missing the bus — not as a studio talking-head. IDENTITY: preserve the attached face exactly, including eye colour, skin marks, hair and ears exactly as in @image1. Do not change the face. Wardrobe, locked: a light summer hoodie over a plain top, shorts, sneakers and a small crossbody bag. Fit these clothes to the attached person's body. Do not restyle the hair except as wind and running move it. STYLE: handheld footage from an old consumer DV camcorder on a hot summer afternoon in a quiet older London neighborhood. Brick terraces, a red double-decker bus, a corner café with a takeaway window, a shop front with a glass display. Strong natural handheld shake, imperfect framing, autofocus hunting, faded DV colours, mild tape noise. No cinematic gimbal. Never show the camera operator. No other faces (barista hands only if needed, no face). 0–3s — chase: Already running after a red double-decker pulling away from the stop. Chaotic handheld chase, breathing, footsteps. They miss it by a second. 3–6s — the line: They stop, out of breath, turn fully toward the camera and clearly say in English, exact lip sync: "Oh, I guess I'll walk today." Those exact words. Then a small resigned laugh. Do not say "I'm going to drive it." 6–10s — coffee: They duck to a neighbourhood café takeaway counter, grab a paper takeaway coffee cup with a lid (plain cup, no brand logo), pay quickly, keep walking. Cup stays in one hand for the rest of the clip. 10–13s — shop window: They slow down and peer through a shop window at something in the display, coffee in hand, a beat of curiosity, then keep walking. 13–15s — heat: It is baking hot. They pull a small paper fan from the bag and fan their face while holding the coffee, slightly overheated, a little laugh, camera still following. Abrupt DV cut. AUDIO: one spoken English line only — "Oh, I guess I'll walk today." Plus running, breathing, bus engine, café clink, street, fan flutter. No music, no subtitles, no logos, no watermark. No on-screen text. Duration: exactly 15 seconds. Aspect ratio: 9:16.

1 step322.2K
MiniMax H315s · 9:16
Inspired by @oggii_0on X

0.0–1.5s. The camera is on the gravel, looking up at the @avatar crouched behind an HVAC box, staying small, head tucked down, handbag clutched to their chest. The helicopter is already coming in fast along the skyline, city behind it. The gunner is in the open door, watching the roof. 1.5–3.0s. The @avatar lifts their head and sees the helicopter. Their jaw sets — it's now or never. @avatar breaks from the crouch and moves straight at the roof edge the helicopter is lining up on, a heavy determined run, bathrobe streaming. The pilot banks the nose toward the building and starts the descent. 3.0–4.5s. The gunner shoulders the M4 and fires a burst at the runner. Rounds chew gravel ahead of the @avatar’s left slipper. @avatar cuts right without flinching and keeps closing. The pilot sideslips so the open door faces them. 4.5–6.0s. The gunner walks the next burst to follow the cut. Rounds spark the HVAC @avatar just left. @avatar drops a shoulder and holds their line toward the lip, hair flattened in the rotor wash. The helicopter drops until the near skid is almost level with that lip. 6.0–7.5s. The gunner leans out of the doorway, one boot planted on the sill, and fires shorter bursts as the gap shrinks. A round passes at their hip and spalls a roof light. @avatar weaves once and does not break for cover, committed to the edge. 7.5–9.0s. The pilot holds the helicopter parallel, the skid running just above the lip, a few meters of air between them. The gunner dumps the rest of the magazine along the lip. The @avatar hits the lip at full stride. 9.0–10.5s. BULLET TIME begins as their slippers leave the gravel. Time almost stops. @avatar is in the air over the drop, bathrobe and hair frozen mid-billow, both hands reaching the near landing skid. Two bullets hang behind @avatar with visible shock cones, one at their back, one at their calf. Neither touches @avatar. The gunner is frozen mid-lean in the door above, the bolt locking back, a brass case hanging in the air beside the empty mag well. 10.5–12.0s. BULLET TIME. Their hands close on the skid. Their body starts to swing under the bar, slippers over empty city. The gunner's eyes are wide, the muzzle dropping at the sight of them already on the bar. The gunner's free boot is coming down toward their hands on the skid, the stamp caught halfway. 12.0–13.5s. BULLET TIME. The @avatar hangs, one arm locked over the skid, the other reaching up toward the gunner's sill-boot with unbothered calm. The gunner's stamp is still coming, the sole aimed at that reaching hand, fear plain on the gunner's face. A third bullet hangs between them, already past their ear from the last burst. 13.5–15.0s. Time snaps back to full speed. The gunner's stamp misses the hand and hits the door frame. The @avatar gets that boot and yanks downward with their whole weight and impossible strength. The gunner pitches forward out of the doorway. 15.0–16.5s. The gunner catches the door frame with one hand. The empty M4 swings on the sling and hits the frame. The @avatar keeps the yank on the boot. The pilot, seeing it in the side window, yanks the cyclic to shake @avatar off the skid. The helicopter lurches. 16.5–18.0s. The lurch is a beat late. The gunner's fingers slip. The gunner falls past the skid, past the hanging @avatar, and drops away into the open air beside the tower (the fall continues off-screen, no impact shown). The pilot keeps the yaw going, trying to peel @avatar off the bar. 18.0–19.5s. The swing throws the @avatar’s legs out, but @avatar is already hauling themselves to the door sill with steady, unhurried effort, one hand on the frame, a knee coming up. In the cockpit the pilot leaves one hand on the cyclic, twists back, and pulls a pistol from the door pocket. 19.5–21.0s. The @avatar is in the cabin. The pilot fires one wild shot into the cabin roof. @avatar ducks the line and crosses the short cabin under the rotor noise, eyes level on the pilot, the open door still behind @avatar. 21.0–22.5s. The @avatar strikes the pilot across the side of the head — one flat, heavy, unhurried blow. The pistol clatters into the footwell. The pilot is still harnessed. The cyclic goes light and the helicopter yaws over the street grid. 22.5–24.0s. The @avatar pops the harness. The pilot grabs their wrist with one hand and the cyclic with the other, trying to fly and fight at the same time. Slippers brace against the pedestal. The city slides sideways in the windshield. 24.0–25.5s. @avatar breaks the grip without visible strain and drags the pilot backward out of the seat toward the open door, using the yaw. The pilot's heels scrape the cabin floor. A glass tower is starting to fill the right side of the windshield. 25.5–27.0s. At the door lip the pilot catches the frame with a free hand. The @avatar drives a shoulder into the pilot and shoves. The pilot loses the frame, goes out into the slipstream, and falls away beside the building (off-screen, no impact). The doorway is empty. @avatar turns back to the cockpit. 27.0–28.5s. The @avatar drops into the right-front seat and takes the cyclic. The glass tower is close on the right, individual facade windows readable. @avatar hauls the cyclic left. 28.5–30.0s. The helicopter banks left. The tower face slides along the right window and falls behind. @avatar is alone in the cockpit, rotors steady, the avenue opening under the nose, hair settling. Hold on their hands on the cyclic and the city moving correctly past the glass.

1 step251K
Seedance 2.530s · 16:9
Inspired by @Diplomemeon X

30 seconds | 16:9 | Professional Beauty Ritual CHARACTER: the person in @image3 — using tool professionally Documentary handheld video. Warm 1970s-inspired salon. Soft golden lighting, observational framing, natural camera movement. TIMELINE (30 s): 0–3s: Prep hands, tool 3–6s: Professional positioning 6–10s: Tool starts, begins work 10–15s: Close-up technique 15–18s: Wide working shot 18–22s: Transformation moment 22–25s: Final touches 25–30s: Result reveal CAMERA: Handheld, no stabilization, intimate, observational LIGHTING: Soft, warm, golden, natural window light AUDIO: Diegetic — tool sounds, breathing, footsteps VISUAL: Photorealistic, warm color grade, natural grain Tool shown as skilled instrument in professional hands.

2 steps1274.7K
Seedance 2.530s · 16:9
Inspired by Zarnab_with_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. Use they/them throughout. No other people. CHARACTER LOCK — HIGHEST PRIORITY: The person in every panel is exactly the person in @image1. 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, panel to panel. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. The avatar reference shows their face and build, not this outfit — put the outfit on them. Fit each garment to the character's body naturally without altering its design, cut, proportions or colour — the garment is fixed, only its drape adapts. Create a high-quality 3D animated fantasy scene in a colorful, cinematic style. The person wears simple, plain everyday clothes. Beside them is a large baby dragon, pearly white with light blue accents, small horns, soft feather-like scales around its head and neck, and a long elegant tail. The scene takes place in a magical tropical valley surrounded by lush green mountains, crystal-clear turquoise water, tropical trees, and a bright blue sky with soft white clouds. Start with a close-up shot of the sleeping baby dragon peacefully resting among vibrant pink-red flowers while the person sits nearby. The dragon slowly opens its eyes, looks around curiously, and makes a cute playful expression. Transition to a wider shot where the dragon and the person are surrounded by a field of beautiful blue flowers near the water. The dragon playfully rolls backward through the flowers while the person watches and laughs. Show a cinematic aerial wide shot revealing the beautiful island-like landscape, flowering fields, tropical trees, mountains, and turquoise water. Colorful small birds fly and hop around a nearby tree while the person and dragon play together below. Then return to a close-up of the person sitting on the dragon's back. The dragon makes funny, playful facial expressions as the person laughs happily. End with the person and the adorable dragon lying peacefully together in a huge colorful flower meadow, smiling and enjoying the magical moment. Use smooth character animation, expressive facial emotions, natural body movement, cinematic camera transitions, shallow depth of field, soft volumetric lighting, vibrant colors, detailed 3D textures, magical family-friendly atmosphere, polished animated-movie quality, and a warm heartwarming tone. No text, no subtitles, no watermark. Aspect ratio: 16:9. Duration: approximately 15 seconds.

1 step1281.8K
MiniMax H315s · 9:16
Inspired by @Iancu_aion X

— REFERENCE DEFINITIONS — ASSET MAP — every reference is bound here and cited by tag below. The numbering follows the order the references are attached. @image3: the protagonist — face, bone structure and hairstyle exactly as shown, at 100% fidelity, in every second of the film. Read their identity and everything they wear off @image3 and invent nothing; preserve their gender presentation exactly as shown and do not masculinize, feminize or otherwise reinterpret it. Combat-worn dark tactical layering, rain-soaked hair, its length and style exactly as in @image3, fine scratch wounds across cheekbone and temple. Character appearance only — do not use for environment, lighting or camera design. Reference. @image1: the creature — exactly the design on that sheet, charcoal chitin plating over muted arterial-red musculature, elongated multi-jointed claws, no visible eyes, scale texture in hyper-detail. Creature design and silhouette only. Reference. @image2: the location — exactly the place on that sheet, flooded asphalt, wet concrete, shattered curtain-wall glass, exposed rebar, ash falling continuously, red emergency glow bleeding through smoke. Location, materiality and mood reference only. Reference. — TECHNICAL BLOCK — Ultra filmic, IMAX cinema texture, 35mm anamorphic lens, f/4, desaturated red-black grade, ISO 800 film grain, soft halation on highlights, sci-fi materiality with divine VFX. SFX only, no music. High contrast, heavy motion blur, persistent atmospheric particles (ash, sparks, nano-smoke), volumetric red lighting, photoreal physical destruction. Single continuous oner — all cuts invisible, masked by motion blur, whip pans and flash frames. Character identity locked to @image3 from the first frame to the last: the face and hairstyle stay identical throughout. COLOR SYSTEM: Cold crimson + obsidian black (protagonist and blade) vs. charcoal + muted arterial red (@image1 and @image2). The protagonist is always the coldest, cleanest red in frame; the environment is always the dirtier, warmer red. — PROMPT — SHOT 1 (00:00–00:02) Desperate Sprint EFFECT: Speed ramp 100%→150% + extreme handheld shake + splash FX + destruction particles. Ultra-low camera 20cm off ground, tracking the legs of the character from @image3 through the flooded @image2 street. Each footstrike detonates a full-frame mudwater splash with motion-blur streaks. Background wall explodes inward — concrete chunks and rebar shrapnel cross frame, dust plume trailing. Film grain spikes on every shake. First step at normal speed, final step ~150%. Transition: camera whips upward. SHOT 2 (00:02–00:04) Death Compression EFFECT: Crash zoom 200% over 0.4s + snap rack focus (2 frames) + lens breathing. Camera PUNCHES into the turning side-profile of the character from @image3 — eyes wide, scratch wounds visible, rain beading on the jaw. A claw of the creature from @image1 enters frame top-right, displacing air in a visible pressure wave, scales in hyper-detail. Focus snaps background→foreground in 2 frames. The claw fills 60% of the background by shot end. Transition: the claw descent triggers time dilation. SHOT 3 (00:04–00:06) Limit Slide EFFECT: Speed ramp 100%→15% + bullet-time 180° orbit + volumetric particle suspension. Time fractures. The character from @image3 throws their body backward into a power slide, back at 25° to the ground. Camera detaches and sweeps a full 180° around their torso at chest height. Hair strands trace visible arcs; raindrops hang suspended, refracting red light; the claw-tip passes 3cm from their nose — displaced air ripples visibly across the skin. Ash, mist and dust float frozen in 3D space, volumetrically lit by red glow. SIGNATURE MOMENT #1 — the silence of near-death. Transition: camera settles behind their rising hand, pulling focus. SHOT 4 (00:06–00:09) Void Blade Condensation EFFECT: Extreme slow-motion ~10% + macro 100mm + CG nano-particle assembly + 45° slow orbit. Extreme close-up of their right hand, fingers uncurling in ultra-slow-motion. Crimson-black nano-smoke bleeds between the fingers and ASSEMBLES with algorithmic intentionality — individual filaments weaving into a metallic crystalline katana hilt, resolved at near-microscopic scale. Camera orbits 45° clockwise holding macro focus; background collapses to complete bokeh, only particle glow visible. The smoke has internal luminescence — dark red core, black edges, contained energy. SIGNATURE MOMENT #2 — the quiet before violence. Transition: the final particle locks into place. SHOT 5 (00:09–00:11) Draw Ignition EFFECT: Speed snap 10%→100% in one frame + red bloom flash + 3-pulse strobe + expression shift. Their hand clamps the hilt — a red-light detonation blooms outward, overexposing frame for 2 frames. Three aggressive light pulses (red–black–red) inside 0.5s, each from a different angle, throwing staccato shadows. Their expression across the strobe: pulse 1 = fear, pulse 2 = darkness, pulse 3 = lethal focus. Medium shot, waist-up, for emotional clarity. Transition: third pulse smears into horizontal motion blur. SHOT 6 (00:11–00:13) Dimensional Kill EFFECT: Extreme speed ramp 100%→800% + whip pan full traverse (4 frames) + single-frame energy line + freeze endpoint. The character from @image3 vanishes — replaced by a razor-thin red-black luminous line traversing the entire frame in 4 frames, fading afterimage trail behind it. The line is precise and geometric, roughly 2 pixels wide, decaying red particle scatter along its path. Whip pan follows the trajectory at impossible speed, then hard-freezes on their landing crouch, blade extended behind them, back to camera. Transition: freeze holds 6 frames of absolute stillness. SHOT 7 (00:13–00:15) Delayed Severance EFFECT: Frozen stillness → sudden 100% restoration + gravity-accurate collapse + blood-mist atomization. Nothing moves. The creature from @image1 still stands, intact. Then a hairline seam of red light traces diagonally across its torso — and the body slides apart along that seam, chitin plating grinding, arterial mist atomizing into ash. Camera slowly dollies in on the still-crouched back of the character from @image3 as tonnage collapses behind them, out of focus. They do not look back. Transition: falling debris wipes frame. SHOT 8 (00:15–00:17) Ash Rain Overcrank EFFECT: 60% overcrank + 85mm portrait lens + volumetric backlight. Low-angle push-in on the character from @image3 rising to full height. Ash and red mist fall around them in slow, heavy flakes, backlit into a corona. Blade held low and reverse-gripped, its surface drinking light rather than reflecting it. Their breathing is visible in the cold air. Chest heaving, jaw set. Transition: their eyes flick upward — camera follows the eyeline. SHOT 9 (00:17–00:19) The Swarm Reveal EFFECT: Vertical crane-up 40m + rack focus foreground→infinity + scale reveal. Camera cranes straight up off their shoulder, revealing the true scale of @image2 — a ruined boulevard stretching to the horizon, and thirty more silhouettes of the creature from @image1 emerging from the smoke on every rooftop, in every doorway, wading through the flooded street. They are a single cold-crimson pinpoint in an ocean of charcoal and arterial red. Transition: they launch upward — camera drops to meet them. SHOT 10 (00:19–00:22) Chain Sever EFFECT: Continuous handheld oner + 4 speed ramps (100%→400%→20%→400%→100%) + geometric light-trail persistence. One unbroken take: the character from @image3 moves through four bodies of the creature from @image1 without stopping. Each engagement compresses to a red-black light line, then decompresses into 20% slow-motion at the exact instant of contact — chitin splitting, sparks fountaining, their hair and coat lagging one beat behind the body. Camera stays with them the whole way, whipping and reframing handheld, never cutting. Blood mist and ash accumulate on the lens. Transition: they plant their feet, water exploding outward in a ring. SHOT 11 (00:22–00:25) The Titan Arrives EFFECT: Ground-shake camera + extreme wide 24mm + atmospheric displacement + scale contrast 1:200. A shockwave rolls the standing water. From behind the collapsed tower, one creature from @image1 at the height of a skyscraper steps into frame — its footfall punching a crater through asphalt, dust ring expanding at 100m radius. Camera at ground level behind the character from @image3, their silhouette occupying 3% of frame against its mass. They raise the blade to eye level. Transition: blade begins to overcharge. SHOT 12 (00:25–00:27) Divine Overcharge EFFECT: 30% slow-motion + energy accretion VFX + light-source inversion + slow 30° orbit. Crimson nano-smoke pours upward from the ground into the blade, streams of particles bending toward it as if to a singularity. The blade's core goes white-hot behind black edges — for the first time in the film they are the brightest object in frame, casting hard red shadows across a hundred meters of ruin. Their face lit from below, absolutely calm. Rain evaporates before it reaches them. Transition: they step forward — the light collapses inward. SHOT 13 (00:27–00:29) Sky Severed EFFECT: Speed snap to 1200% + full-frame flash-white + 3-frame vertical light column + hard freeze. A single vertical stroke. A red-black light column splits the frame top to bottom, cleaving the titan, the tower behind it, and the cloud layer above in one continuous line. Two frames of full-white overexposure, then absolute darkness, then the world returns — the cut-line glowing along its entire length before the halves begin to separate. Transition: silence falls. SHOT 14 (00:29–00:30) Ember Hold EFFECT: Return to 100% + static locked frame + falling ember particles + film grain resolve. Locked wide. The character from @image3 stands motionless in the center of the split city, blade point resting on wet concrete, a thin thread of crimson smoke still rising from its edge. Behind them the titan's two halves fall away from each other in real time. Embers drift up, not down. Hard cut to black on the last frame. SFX only: mud and water impacts, rebar snapping, concrete detonation, low-frequency creature respiration, air pressure displacement, high-frequency tinnitus tone during bullet-time, granular nano-particle assembly shimmer, metallic blade resonance, red-light bloom concussion, whip-pan air tear, wet chitin severance, tonnage collapse rumble, ash rainfall, distant swarm chittering, titan footfall subsonic impact, energy accretion rising whine, single clean sword stroke, two seconds of total silence, falling ember crackle.

3 steps502.1K
Seedance 2.530s · 16:9
Inspired by @airina_xyzon X

Generate a 16-bit prite of yourself, how you're leveling up while working on yourself.

2 steps6150
MiniMax H315s · 16:9
Inspired by @itxabdullaaon X

Generate an 8 macro shot video of your product.

3 steps1062K
MiniMax H315s · 3:4
Inspired by @iamahmedfaraz66on X

A fifteen-second candid handheld home video in a modern kitchen on a dark rainy morning. @image_1 fights a tightly sealed glass jar in three escalating attempts - bare hands, then a tea towel wrapped around the lid, then the whole body braced against the worktop - and when the lid finally pops, dips a fingertip in to taste it and turns to the camera with a small proud smile. Natural location sound only, no music.

1 step34475
Seedance 2.015s · 1:1
Inspired by @AiwithSaif7on X

A fifteen-second premium 3D animated fantasy short. @image1 plays with a small white feathered dragon hatchling on a floating island above a sea of clouds, an enormous green-and-gold dragon comes up over the rim, and after a run and a hiding place in the rock the giant turns out to be no threat at all - the film ends with the hatchling settling on @image1's shoulder at the island rim, both dragons and the whole cloud sea behind.

2 steps5260
Seedance 2.515s · 1:1
Inspired by @meAsifAion X

ASSET MAP — every reference is bound here and cited by tag below: @avatar — the traveller. This is the person; it defines face and identity only. Its clothing, pose, framing, background and lighting are ignored completely. ATTACHED IMAGES ARE MANDATORY AND FINAL: the person in @avatar is the person in every one of the twenty shots — reproduce them exactly, 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 image and this text disagree, follow the image. CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @avatar. Preserve their facial identity, facial structure, facial proportions, eye shape and spacing, eyebrows, nose, mouth, cheek structure, jawline, chin, exact skin tone and natural skin characteristics, 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 redesign, beautify, slim, age, de-age or restyle them. Only one person carries the camera, and no duplicate of that person ever appears. WARDROBE (comes from THIS TEXT, never from @avatar) Each shot has its own location-appropriate layer, named in that shot. @avatar shows face and build, not these clothes — put each outfit on them. Fit every garment to the body naturally without altering its design, cut, proportions or colour: the garment is fixed, only its drape adapts. An outfit belongs to its own shot only and never blends into the next one. ONE-SENTENCE SUMMARY @avatar travels the world in a beat-synced selfie hyper-lapse, holding the camera at arm's length in front of twenty famous landmarks, one hard cut every half second, shot on a wide-angle phone lens as a premium travel vlog. DETAILED PLOT — exactly 20 shots, one hard cut every 0.5 seconds, exactly 10 seconds in total Every shot: handheld selfie-stick perspective at natural arm-length distance, wide-angle phone lens with authentic perspective distortion, realistic handheld micro-movement and subtle motion blur, @avatar filling the near frame with the face fully visible and the landmark clearly readable behind. One landmark per shot, one gesture per shot. Hard cut on the beat between every shot, never a dissolve, a morph or a gradual change of place or outfit. The first shot opens already in motion, on a readable face — never on an empty frame or a fade from black. Shot 1 — the Eiffel Tower, Paris. Cream knit sweater and a wool beret. @avatar waves at the lens. Soft morning light. Shot 2 — Shibuya Crossing, Tokyo. Varsity bomber jacket. @avatar gives a peace sign as the crowd streams past. Neon dusk. Shot 3 — Times Square, New York City. Denim jacket. @avatar points up at the screens. Night, saturated billboard light. Shot 4 — the Colosseum, Rome. White linen shirt. @avatar gives a thumbs-up. Hard midday sun. Shot 5 — the Pyramids of Giza, Egypt. Sand-coloured shirt and a wide-brim straw hat. @avatar pulls a surprised open-mouthed reaction. Desert haze. Shot 6 — Christ the Redeemer, Rio de Janeiro. Green-and-yellow print shirt. @avatar makes a finger heart. Bright overcast. Shot 7 — Big Ben, London. Beige trench coat. @avatar points back at the clock tower. Flat grey daylight. Shot 8 — the Sydney Opera House, Sydney. Striped cotton tee. @avatar laughs at the lens with the harbour behind. Clean blue afternoon. Shot 9 — the Grand Palace, Bangkok. Light printed overshirt. @avatar holds a namaste. Gold hour glare off the spires. Shot 10 — the Taj Mahal, India. Patterned scarf over a pale shirt. @avatar tilts the head and smiles. Warm early sun. Shot 11 — the Great Wall, China. Grey fleece shell. @avatar waves with the wall running away behind. Cool mountain light. Shot 12 — the Burj Khalifa, Dubai. White linen set. @avatar points straight up along the tower. Bleached noon sky. Shot 13 — Hagia Sophia, Istanbul. Woven pashmina. @avatar raises one hand in a small greeting. Low afternoon sun. Shot 14 — the Grand Canal, Venice. Navy striped top, seated in a gondola. @avatar lifts both hands in delight. Soft reflected water light. Shot 15 — Machu Picchu, Peru. Knitted andean-pattern layer. @avatar gives a thumbs-up on the terraces. Thin high-altitude light. Shot 16 — the Acropolis, Athens. White cotton shirt. @avatar shades the eyes with one hand and squints into the sun. Harsh white daylight. Shot 17 — the Sagrada Família, Barcelona. Soft ivory shirt. @avatar leans back with an amazed look up at the spires. Clear blue sky. Shot 18 — the windmills of Zaanse Schans, Amsterdam. Brown corduroy jacket. @avatar claps once, delighted. Windy bright overcast. Shot 19 — Gyeongbokgung Palace, Seoul. A pale traditional Korean jacket rented at the palace gate. @avatar gives a small bow toward the lens. Even autumn light. Shot 20 — Marina Bay Sands, Singapore. Dark evening shirt. @avatar grins and swings the camera slightly as the skyline lights burn behind. Blue-hour night. ADDITIONAL NOTES PACE AND CUTS Twenty shots of equal length, one hard cut every 0.5 seconds, 10.0 seconds in total. Every cut lands on the beat. No shot is held longer than another, no location is blended with the next, and no outfit carries across a cut. LOOK Ultra-realistic cinematic travel photography with a premium travel-vlog finish: natural colour science, realistic depth of field, authentic wide-angle perspective, subtle cinematic contrast, real motion blur. Physically believable location-specific light in every shot — natural sunlight, accurate shadows and reflections, atmospheric depth, consistent exposure across the cuts. Natural skin texture with visible pores and fine facial detail, physically accurate hair strands, real fabric behaviour, believable local crowds and environmental movement. Nothing looks rendered or retouched. HANDS Hands stay anatomically correct with five fingers on each hand in every gesture, and the hand holding the camera stays out of the way of the face. TEXT IN FRAME Only the real signage that belongs to each location appears. Do not generate a logo and do not generate a watermark. No subtitles. AUDIO An upbeat electronic travel track at about 120 BPM with a clean beat landing on every cut, plus a thin layer of location ambience under each shot — crowd, traffic, wind, water. No dialogue.

1 step5268
Seedance 2.510s · 16:9
Inspired by @HumanBeing34061on X

12-second cinematic rally film, 16:9. Six shots, hard cuts, fast pace. @avatar — the driver. @image1 — the car. Keep the driver's face and the car's livery identical in every shot. Wardrobe: white racing suit, helmet, goggles, gloves. Location: red desert plateau, low sun, dust, open dirt track. Shot 1: the car drifts past camera, low and wide, dust everywhere. Shot 2: inside the cabin, close on the driver's face. Shot 3: ground level at the rear wheel, gravel at the lens. Shot 4: wide tracking alongside, tail out through a curve. Shot 5: back in the cabin, the driver catching the slide. Shot 6: the car stops side-on, dust clears, whole car in frame. Hold. Style: photoreal motorsport, heavy dust, motion blur. Audio: engine, gravel, wind. No music, no dialogue. Avoid: no crashes, no other cars, no added text or logos (the car keeps its own badges and markings exactly as shown).

2 steps1053.3K
Seedance 2.512s · 16:9
Inspired by @laviniavelleon X

Commercial-style HD beauty sequence, 12 seconds, 9:16. THE MODEL: the lead is an unnamed adult model generated for this film (no person photo is uploaded) — the same model shown in @image1. Keep their skin tone, facial structure, hairstyle and apparent age the same throughout. Use they / their / them only. No identity drift. PRODUCT LOCK: @image1 is the step-1 still; the product in it is the product exactly as shown — same shape, colour, materials, label and logo; nothing invented or redesigned — keep identical across every shot. The product carries only the marks that exist on the product in @image1. Open on close-up shots of the model's skin showing minor texture, tiredness and dullness — soft under-eye shadow, slightly dry patches — while they work at a laptop in a sunlit, plant-filled loft. They pause, rub their eyes, and reach for the product from @image1 resting on a sunlit wooden shelf among potted plants. Macro close-up: a little of the product from @image1 goes onto the model's palm and is gently pressed and smoothed into their skin. As it absorbs, their complexion transforms — dewy, deeply hydrated, glass-like glow. The model smiles confidently, natural light streaming through sheer curtains billowing in the breeze behind them. Style: soft natural lighting, aesthetic beauty commercial cinematography, 4K, 60fps, smooth cinematic cuts. Negative: no change to the model's identity, no change to the @image1 product's shape or label, no subtitles, no watermark.

2 steps27912.4K
Seedance 2.512s · 9:16
Clips on this page (40)