Regístrate y ahorra hasta −50% al año.Regístrate gratis →Black Friday: hasta −50% en planes anuales.Ver la oferta →
Volver a la galería
Volver a la galería

Arrastra el clip hacia los lados

A continuación
Inspired by Fujimoto_hinaon X

@image1 is the PEACH — photocopy that fruit exactly as shown — skin, colour, flesh and pit. IGNORE any bowl, board, or table in @image1. The film is on chilled dark slate, not wood. Not grapes. Not berries. Not a bottle. 10 seconds, 16:9, cinematic photoreal artisanal culinary commercial. Extreme macro, ultra-shallow DOF, real frost and cryogenic vapor. Palette: the peach's own colours exactly as in @image1, against matte dark slate. No people. AUDIO: ice, fruit split, liquid, churn motor, scoop scrape. No speech. No music lyrics. 0.0–2.5s Tight cluster of frost-kissed peaches from @image1 cascading onto chilled raw slate. Skins split in macro slow motion: translucent pulp and juice in the exact colours of @image1, microscopic mist off the cold stone. Natural peach fuzz and bloom catch morning light. 2.5–5.0s Zero-gravity vortex: cold-pressed peach nectar, fine citrus zest, spun agave syrup collide and emulsify as mid-air crystalline ribbons. Only the @image1 peach colours — no purple grape. 5.0–7.5s Churning cylinder. Sub-zero polished stainless dashers whip the mixture into dense velvety peach sorbet. Sub-zero vapors escape the chamber. Colour is peach, not violet. 7.5–10.0s Ultra-macro stainless scoop carving the mass, rolling a perfect ridged sphere with frost crystals, taut peach translucence, one suspended droplet of concentrated peach reduction. Hold. NO ON-SCREEN TEXT, logos, watermarks, subtitles, grapes, concord, muscat, purple juice, cartoon, slush, plastic.

1 step27698
Seedance 2.510s · 16:9
Inspired by OpenClipson organic

Your avatar turns to ash and is carried off on the wind, aware and reacting with a dramatic raised hand, in a windswept field at golden hour. Music only, loud. See the video step for the full prompt.

1 step
Seedance 2.515s · 9:16
Shared Umbrella

MODEL: Seedance 2.5 — use this model specifically. Do NOT use any other model for this generation. FORMAT: 9:16 (vertical) QUALITY: High-fidelity, 4K render, sharp detail, no compression artifacts CHARACTER LOCK — HIGHEST PRIORITY: The character in every shot is exactly the person shown in @image1 — same face, facial features, hairstyle, skin tone, build and gender presentation throughout all 3 shots. No identity drift between shots. Do not beautify, slim, de-age or restyle them. Refer to them only as they/them in this prompt. @image1 is identity only — face, hair, skin — not the sunny café, not the cobblestone patio, not a seated still. Photocopy the person from @image1 into a rainy city bus-stop scene. ASSET MAP: @image1 — the character. Tell the following story in exactly 3 shots, same character throughout, with a clear visual beginning, twist and ending — never an ambiguous or faded-out close. STORY: The character stands alone at a city bus stop as rain suddenly starts pouring — everyone around them opens an umbrella, but they have none and huddle miserably under the tiny stop roof, getting splashed anyway. A stranger nearby silently steps closer and holds their umbrella out over them instead, sharing it without a word. They look up, surprised, then smile — the two end up walking off together down the street under the one shared umbrella, laughing, just as the rain eases and warm light spills from a café window ahead. STYLE: Warm, relatable live-action realism, soft naturalistic lighting, handheld documentary-style camera energy. Continuous real motion. Never freeze on the reference still. No on-screen text, no subtitles, no logos, no title card. AUDIO (native, synced, no music, no voiceover, no narration): rain pattering on pavement and the stop roof, city ambient noise, footsteps, the rustle of an umbrella opening, a warm shared laugh at the end. SHOT 1 (0-6s): Establish the character clearly at the bus stop in pouring rain. Handheld 35mm, medium-wide then push in. Rain starts hard in the first second — wet asphalt, droplets, people around them already sheltered under umbrellas. They have none. They huddle under the tiny stop roof, shoulders up, getting splashed anyway. The problem is immediately obvious. Crowd extras under umbrellas are background only. Face readable. SHOT 2 (6-12s): The twist. A stranger steps in from frame-left; their umbrella enters frame and tilts to cover them too (fabric rustle). Close enough to read their face: surprise, then a genuine warm smile. Rain still heavy. Handheld, eye-level. The stranger is a generated extra, not a second lead and not from any upload — a different, invented person sharing the umbrella — keep @image1's face locked on the character. SHOT 3 (12-18s): Resolution. Both walk together down the wet street under the one shared umbrella, relaxed and laughing (heard, not voiced as dialogue). Rain visibly eases. Warm golden light from a café window ahead. Handheld follow, then a clear last beat: they keep walking into that light — a finished ending, not a fade-out, not a still.

1 step
Seedance 2.518s · 9:16
Object Restoration Polish

@image1 is an absolute lock for the object: shape, proportions, colour, material, surface finish and markings are taken from it exactly and must not drift, morph or be reinterpreted in any shot. @image2 is the storyboard and is followed exactly — same shot order, same framing, same hand positions, same camera distance, same bench and lighting. The object begins heavily soiled, dulled and discoloured, and is restored across the film to the exact condition shown in @image1. Nothing else about it changes. Five shots of equal length, hard cuts between them, no dissolves. Shot 1: gloved hands work a small abrasive pad back and forth across a soiled area in short firm strokes. Loose deposits lift, flake away and drift down out of frame. Shot 2: hard cut. The hands fold a dark cloth and draw it along the same area in slow overlapping passes, carrying away the loosened residue and leaving the surface beneath uneven and partly revealed. Shot 3: hard cut. A fingertip carrying a small dab of pale compound presses to the surface and works it in tight, even circles, leaving a soft opaque film in its track. Shot 4: hard cut. A clean cloth wrapped over the fingers draws steadily along the object and lifts the film away. The surface brightens behind the cloth as it travels, catching the lamp light in small moving glints along the cleaned edges. Shot 5: hard cut. The hands withdraw out of frame and the finished object is held alone while the lamp light travels slowly across its surface and settles. Camera: locked-off macro, one fixed framing per shot. No push in, no pull back, no pan, no tilt, no orbit, no handheld drift. Audio: close ASMR. The dry grain of the abrasive pad, the soft drag of cloth across the surface, the faint squeak of a fingertip working compound in circles, quiet room tone underneath. No music, no voice, no narration. Keep the object's own label and logo exactly as shown; do not add any other text, captions, subtitles, watermarks or logos.

3 steps
Seedance 2.510s · 9:16
Inspired by OpenClipson organic

Your avatar melts like a candle, aware and reacting, until the whole body runs out into a pool of wax on the floor of their room. Music only, loud. See the video step for the full prompt.

1 step
Seedance 2.510s · 9:16
Tiny Bookbind

CHARACTER LOCK — HIGHEST PRIORITY: the person 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. Preserve their gender presentation exactly as shown. Photocopy their hair, eyes, skin, outfit and accessories exactly as in @image1. Do not beautify, slim, de-age or restyle them. Do not change the hair or the outfit. @image1 is identity and wardrobe — only their scale changes. No other people in frame. Use they / their / them only. SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. If it is a person: their exact face, facial features, hairstyle, skin tone, build and gender presentation stay unchanged — only their scale changes. Do not beautify, restyle or alter identity in any way. @image1 is a REFERENCE still. Do not paste it as the opening frame. Do not open on a studio-grey headshot. CONTINUOUS MOTION REQUIRED: Real, visible physical motion for almost the entire 12 seconds — but the opening 2 seconds prioritize CLARITY over speed, so a first-time viewer immediately understands both the craft and the scale. SCENE: The subject, shrunk to a few centimeters tall, works at a tiny wooden bookbinding desk tucked into the gap between two real, full-sized books leaning against each other, their towering spines and pages framing the scene on both sides — the scale contrast unmistakable from the first frame. A tiny pot of glue, a miniature awl and a needle and thread sit on the desk. Warm desk-lamp light. 0-2s: ESTABLISHING SHOT — wide, clear view: the subject sits at the tiny desk stitching the pages of a small handmade book together with a needle and thread, the two giant books clearly visible looming on either side. Camera slowly pushes in, making both the craft (bookbinding) and the scale obvious immediately. 2-4s: They finish stitching the spine, set down the needle, and carefully brush glue along the book’s spine with a tiny brush, focused and precise. WOW MOMENT — TIME FREEZE + ORBIT (4-6.5s): They lift the finished tiny book and open its cover. As the pages begin to flutter open, everything suddenly FREEZES — the pages suspended mid-flutter catching warm light, tiny dust motes glittering around the subject. The camera performs a slow, cinematic 180-degree orbit around the frozen book and subject, revealing the two giant books towering on either side from multiple angles, shallow depth of field. This freeze holds for roughly 2 seconds. 6.5-7s: TIME RESUMES at full speed — the pages settle open, the tiny book now fully assembled in their hands. 7-9.5s: They close the book gently, walk it to the base of one giant book, and lean it upright directly against it — a small, complete, unmistakably-a-book object standing next to a real book, the scale payoff instantly clear. 9.5-12s: They step back, dust off their hands, and give a proud, satisfied smile toward camera, warm lamp light around them. SCALE REALISM: The giant books’ paper texture, cover material and page edges, and the tiny desk’s wood grain must all read at true scale relative to the tiny subject — every texture enormous next to them. Match lighting and color grade between the subject, the tiny book and the giant books throughout so the whole shot reads as one real photograph, not a composite. Frame wide enough that the establishing shot, the stitching, the freeze-orbit, and the final side-by-side book comparison all stay clearly visible. AUDIO: Generate synchronized natural audio for this scene — quiet thread pulling and stitching sounds, soft brush strokes, a gentle page flutter, near-silence during the freeze, then a soft whoosh as pages settle, and a satisfied contented sigh at the end. No music, no voiceover, no narration. No on-screen text, no watermark, no subtitles.

1 step
Seedance 2.512s · 9:16
Inspired by Noor_ul_ain43on X

HIGHEST PRIORITY — THREE FACE LOCKS. Photocopy each tag. Do not invent a stock trio. Do not morph. Do not average faces. Three distinct people in every wide shot. Preserve their gender presentation exactly as shown. Use they / their / them only. @image1 is the first rider — photocopy their exact face, bone structure, mouth, nose, brows, skin and hair exactly as shown. IGNORE any clothing, accessories or sunglasses in @image1. Eyes visible. No sunglasses anywhere in this film. @image2 is the second rider — photocopy their exact face, bone structure, hair and any facial hair exactly as shown. IGNORE any clothing in @image2. @image3 is the third rider — photocopy their exact face, bone structure, hair exactly as shown. IGNORE any clothing or background in @image3. WARDROBE FROM THIS FILM ONLY (not the stills): - The person in @image1: a casual short-sleeve t-shirt, jeans and sneakers in their own style. Hair moving in the wind, styled exactly as in @image1. - The person in @image2: a casual short-sleeve t-shirt, jeans and sneakers in their own style. Front rider. - The person in @image3: a casual short-sleeve t-shirt, jeans and sneakers in their own style. Bare heads. No helmets. Each rides their own longboard (not a short skateboard). Wheels spin. Real weight shifts, lean into turns, wind in hair and cloth. 30 seconds, 16:9, photoreal, natural daylight. Winding coastal mountain road over a turquoise ocean and a seaside city (Hawaii-style: green hills, hotels, beach). Bright blue sky, white clouds. Ultra-realistic physics, road motion blur, wide-angle, action-camera, smooth stabilize. Frame 0 is ALREADY at speed — never a studio portrait, never a grey still. AUDIO: wheels on tarmac, wind rush, distant surf. No speech. No lyrics. No song. 0.0–3.0s LOW TRACKING, already racing downhill. Camera near the tarmac behind/beside the trio. The person in @image2 in front, the person in @image1 left/rear, the person in @image3 right/rear. Faces readable. Hair and clothes whipping. 3.0–6.5s CLOSER FOLLOW. The person in @image2 carves a sweeping right-hand bend, board on edge, body committed. The people in @image1 and @image3 tucked behind them. Wheels blur. Ocean flashes left. 6.5–12.0s HIGH AERIAL of the S-curve mountain road. Three small longboarders racing the ribbon of asphalt. Turquoise water, white surf, beach hotels, lush green slope. Strong sense of speed. Same three people — do not recast. 12.0–18.0s GROUND FOLLOW from behind and slightly left. The person in @image2 still leads. The person in @image1 left, the person in @image3 right. Boards, jeans, tees match the wardrobe lock. Coastal drop on the left. 18.0–24.0s DRAMATIC SIDE ANGLE, low, traveling with them. Close enough to read the face of the person in @image1, then @image2, then @image3 as they pass — each matches its tag. Wind, motion blur on the road, sharp on the riders. 24.0–30.0s BEHIND THEM downhill, three-quarter. Ocean left, city ahead. Same three, same clothes, same boards. Hold the run. Cut. NO ON-SCREEN TEXT, titles, logos, watermarks, subtitles, helmets, sunglasses, clothing from the face photos. NEGATIVE: different faces, fourth rider, studio headshot as frame 0, empty boards, short skateboards, night, rain.

1 step11276
Seedance 2.530s · 16:9
Inspired by OpenClipson organic

TORNADO IN THE CITY — Pulled Into the Vortex Audio: one continuous dramatic cinematic instrumental, studio-recorded, loud and forward — low pulsing strings, a deep sub-bass rumble, a rising tension build and heavy percussive hits on the biggest moments. The picture itself has no recorded sound. IDENTITY LOCK — @image1 is the one person we follow: keep the exact face, bone structure, eyes, eyebrows, nose, mouth, skin tone, hairline, hairstyle, hair length, texture and colour, freckles or marks, apparent age, build and proportions identical in every frame. The attached @image1 outranks every word: where text and image disagree, follow the image. @image1 is an adult and never turns into anyone else. Other people are anonymous background civilians whose faces are never featured; they never match or duplicate @image1. WARDROBE — @image1 wears an everyday outfit taken from the reference and unchanged; fully dressed, never barefoot. THE SEQUENCE — a photoreal disaster sequence in a big city during a tornado, following @image1 who FIGHTS the storm rather than waiting for it: bracing, gripping, being dragged, and finally torn off the ground and pulled INTO the funnel, ending inside the spinning vortex where @image1 tumbles and screams in terror. The tornado must physically advance ALL THE WAY down the street and engulf @image1 up close — never merely reach from a great distance. DIRECTION — one continuous handheld storm-chaser take: wide establishing down the avenue, running follows, low angles as the funnel bears down, then a tight handheld ride as @image1 is dragged and lifted, and finally an interior vortex shot circling @image1's terrified face. No hard cuts; one continuous shot; no teleporting. SCENE — a wide city avenue between skyscrapers with the storm sky above, wet reflective road, cars and debris, then the churning grey-brown interior of the tornado full of swirling dust, papers and debris for the final beats. Nobody's face is featured except @image1. TIMELINE (30 s): 0–4s: wide down the avenue: skyscrapers and a huge tornado funnel on the skyline, overcast storm light, wet street, crowds of civilians fleeing past; @image1 stands their ground, bracing against the wind, clothes and hair snapping. 4–8s: the funnel visibly ADVANCES down the street toward @image1, growing fast; @image1 grabs a lamp post and holds on, leaning hard against the pull, feet sliding on the wet asphalt as the wind drags at them; debris flies past. 8–13s: the tornado reaches them: it fills the street right around @image1, the roar peaking; @image1 clings to the post with both hands, legs lifting off the ground, body streaming horizontally in the wind, fighting with everything, face straining — a wide-to-medium shot, no close-up yet. 13–17s: the grip is torn loose; @image1 is ripped off the post and dragged low across the ground, clawing at the asphalt, then snatched upward as the funnel takes them; the camera cranes up following the body as it is pulled into the base of the vortex. 17–23s: INSIDE THE TORNADO: @image1 tumbles and spins inside the churning grey-brown column, surrounded by swirling debris and dust, limbs flailing against the spin, hair and clothes whipping, rising through the vortex. 23–30s: CLOSE-UP inside the vortex on @image1's terrified face: eyes wide, mouth open screaming, hair lashing across the face, debris streaking past, the body spinning; hold on the terror as @image1 is carried higher into the roaring funnel to the last frame. CHOREOGRAPHY — believable resistance and weight throughout: bracing, gripping the post, feet sliding, being torn loose, clawing, then the helpless tumble and scream inside the vortex; real inertia and violent wind on hair, clothes and debris; escalating, never idle, never passively waiting. ANATOMY — @image1 has exactly two arms and two hands with five fingers per hand, two legs and two feet; dramatic but never grotesque, no gore, no blood, no dismemberment. LOOK — ultra-photorealistic disaster-film realism, 28mm and 35mm, deep focus on the street and funnel then tight on the face in the vortex, cool desaturated storm grade, rain sheen, heavy volumetric dust and debris, realistic grain, strong natural motion blur, cinematic shutter. Never plastic, never cartoon, never CGI-looking. NEGATIVE — @image1 passively standing and waiting to be sucked up instead of resisting; the tornado only reaching from a great distance without advancing close and engulfing them; no interior-of-the-tornado shot; no close-up of the screaming terrified face; the featured person's face changing or duplicating; another person's face featured or matching @image1; a costume or props instead of real storm effects; the lift snapping instantly with no struggle; the body dismembering, gore, blood; a stretched or warped face, taffy limbs, wrong proportions, body distortion; feet sliding unnaturally or gait glitching; hard cuts, the camera teleporting, jumping to an unrelated scene; a scene cutting off mid-action; skipped beats; slow motion, speed ramps, repeated loops, aerial establishing drone shot; plastic or beauty-filtered skin, anime, cartoon or CGI look; on-screen text, captions, subtitles, numbers, readable signage, invented logos or watermark; only the elements explicitly described appear.

1 step
Seedance 2.530s · 16:9
Street Busk

CHARACTER LOCK — HIGHEST PRIORITY: The character in every shot is exactly the person shown in @image1 — same face, facial features, hairstyle, skin tone, build and gender presentation throughout all 3 shots. No identity drift between shots. Do not beautify, slim, de-age or restyle the face or hair. @image1 is identity only — face, hair, skin and any jewellery they actually wear in @image1 — not the sunny café, not the cobblestone patio, not a seated-at-a-table still, not a teacup, not a woven handbag. Photocopy the person from @image1 onto a city sidewalk as a street musician. ASSET MAP: @image1 — the character. The child, the parent, the passersby and the gathering crowd are generated extras, not second leads. Tell the following story in exactly 3 shots, same character throughout, with a clear visual beginning, twist and ending — never an ambiguous or faded-out close. STORY: A street musician sits on a sidewalk corner playing guitar to an almost empty street, their open case holding just a few scattered coins. People walk past without stopping, and the musician glances at the low afternoon sun, visibly discouraged, considering packing up. Then a small child breaks away from a nearby parent, walks up, drops a coin into the case, and starts spontaneously dancing to the rhythm — clumsy, joyful, completely unselfconscious. A couple of passersby stop to watch and smile. Word seems to spread in real time: within moments a proper small crowd has gathered around the musician, clapping along to the beat, more coins landing in the case, the musician now playing with visible renewed energy and joy, golden late-afternoon light warming the whole scene. STYLE: Warm, grounded live-action realism, soft golden-hour lighting, gentle handheld documentary-style camera energy, no stylization or slow-motion tricks. Vertical 9:16. Continuous real motion. Never freeze on the reference still. No on-screen text, no subtitles, no logos, no title card. AUDIO (native, synced, no added music track, no voiceover, no narration): live acoustic guitar playing throughout — the guitar itself carries the sound. Quiet street ambience at first, a coin dropping into the case, scattered footsteps slowing to a stop, then a swelling crowd murmur with rhythmic clapping by the end. SHOT 1 (0.0-9.0s): Establish the character clearly — sitting on the sidewalk corner playing guitar, case open with only a few coins, people walking past without stopping. Handheld 35mm, medium-wide then push in. The discouragement must be immediately obvious: a glance at the low afternoon sun, a tired shift in posture, maybe starting to reach for the case as if to pack up. Face readable. Passersby are background only. Guitar is being played for real — fingers moving on strings. SHOT 2 (9.0-18.0s): The twist — a small child approaches, drops a coin into the open case (heard), and begins dancing unselfconsciously to the music — clumsy, joyful. The musician’s surprised, delighted reaction is clear and readable on @image1’s face. One or two passersby slow down and stop to watch, smiling. Handheld, eye-level. Child, parent and passersby are real extra people — keep @image1’s face locked on the musician only. SHOT 3 (18.0-28.0s): The resolution — a small crowd has now gathered, clapping along in rhythm, more coins visibly landing in the case, the musician playing with clear renewed joy and energy, golden late-afternoon light across the whole scene. Handheld among the crowd then a clear last beat: musician still playing, crowd still there, a finished warm ending — not a fade-out, not a still.

1 step
Seedance 2.528s · 9:16
Tiny Books

CHARACTER LOCK — HIGHEST PRIORITY: the person 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. Preserve their gender presentation exactly as shown. Photocopy their hair, eyes, any eyewear and outfit exactly as in @image1. Do not beautify, slim, de-age or restyle them. Keep glasses only if @image1 shows them; never add any. @image1 is identity and wardrobe — only their scale changes. No other people in frame. Use they / their / them only. SUBJECT LOCK — HIGHEST PRIORITY: Preserve the subject in @image1 exactly. If it is a person: their exact face, facial features, hairstyle, skin tone, build and gender presentation stay unchanged — only their scale changes. Do not beautify, restyle or alter identity in any way. @image1 is a REFERENCE still. Do not paste it as the opening frame. Do not open on a studio-grey headshot. CONTINUOUS MOTION REQUIRED: Real, visible physical motion for almost the entire 12 seconds — but the opening 2 seconds prioritize CLARITY over speed, so a first-time viewer immediately understands the setting before the action builds. NO MUG. There is no coffee mug, no cup, no steam anywhere in the shot. The scale anchor is a stack of real, full-sized hardcover books. SCENE: The subject, shrunk to a few centimeters tall, works at a tiny handcrafted workshop bench built from scrap wood and matchsticks, laid out with a small anvil and a row of miniature tools — a tiny hammer, wrench and screwdriver — under a small glowing desk lamp. The bench sits on the corner of a real, full-sized desk, right beside a short stack of normal-sized hardcover books (worn cloth and paper spines, a few millimetres of page-edge showing) that tower over the tiny subject and anchor the scale contrast. Warm lamp light from one side. 0-2s: ESTABLISHING SHOT — wide, clear view of the full miniature workshop bench and its tools, the subject standing at it holding a small piece of metal up to the lamp light, inspecting it. The giant stack of hardcover books is visible in the same frame beside the bench, making the scale contrast unmistakable from the very first seconds. Camera slowly pushes in. 2-4s: The subject sets the metal piece onto the anvil, picks up the tiny hammer, and begins striking it in a steady rhythm — each hit sends a spark into the air, the metal slowly glowing and taking shape, sweat visible on their brow. WOW MOMENT — TIME FREEZE + ORBIT (4-6.5s): On the final, hardest strike, a bright shower of sparks bursts upward. At the instant the sparks reach their peak height, everything suddenly FREEZES. Dozens of glowing sparks hang suspended in mid-air around the subject, who is frozen mid-swing with the hammer raised. The camera performs a slow, cinematic 180-degree orbit around the frozen subject and sparks, revealing the full workbench layout and the giant book stack from multiple angles, shallow depth of field. This freeze holds for roughly 2 seconds. 6.5-7s: TIME RESUMES at full speed — sparks shower down and fade out, the hammer completes its strike with a final ringing clang. 7-9.5s: The subject sets down the hammer, picks up the now-finished tiny piece — a small gleaming gear or medallion — with miniature tongs, and holds it up to inspect it against the lamp light. 9.5-12s: They walk it over and place the finished piece down directly beside the giant book stack, creating a clear side-by-side size comparison against the book spines and page edges, then step back, wipe their brow, and give a satisfied nod and thumbs-up toward camera. SCALE REALISM: The workbench grain, the miniature tools and the books’ cloth spines, paper edges and cover boards must all read at true scale relative to the tiny subject — every texture enormous next to them. Match lighting and color grade between the subject, the sparks and the desk throughout so the whole shot reads as one real photograph, not a composite. Frame wide enough that the establishing shot, the hammering, the freeze-orbit, and the final side-by-side reveal all stay clearly visible. AUDIO: Generate synchronized natural audio for this scene — ambient workshop quiet, rhythmic metallic hammer clangs, a sharp sizzle with each spark, near-silence during the freeze, then a whoosh as sparks shower down, and a satisfied exhale at the end. No music, no voiceover, no narration. No on-screen text, no watermark, no subtitles.

1 step
Seedance 2.512s · 9:16
One Hit Fashion LookbookMiniMax H3 Max (references) · 9:16 · 15sRecrear el flujo