Sign up and save up to 50% on a yearly plan.Sign up free →Black Friday: up to 50% off yearly plans.See the deal →
Back to the gallery
EN
Pricing, save up to 50% on yearly plans, Black Friday: up to 50% off yearly plans
Back to the gallery
Seedance 2.525s · 4:3

Drag the clip sideways

Up next
Day in the Life of a '90s Supermodel (Your Dress)

DAY IN THE LIFE OF A '90s SUPERMODEL. A glamorous montage made to look like a real 1990s home camcorder / VHS tape — a nostalgic vintage home-video look with soft jump cuts between short scenes, full realtime speed. AUDIO MIX (ranked, three separate layers): 1. MUSIC — loudest, dominant from the very first frame: an upbeat, glamorous, feel-good 1990s pop/house instrumental with a bright confident groove, building to a big triumphant beat on the runway finale; original, instrumental only. 2. SFX — quiet, under the music: popping camera flashbulbs, a wind machine, clinking glasses, crowd applause at the end. 3. VOICE — none; @image1 stays silent the whole clip. Audio suppressor: no voiceover narration, no dialogue, no spoken words, no singing vocals, no lyrics, no library audio bed, no muffled murmuring, no subtitles. The music resolves on a final hit and silence holds the final 0.5s. VINTAGE LOOK (apply throughout): authentic early-1990s camcorder footage — soft slightly-washed warm colours, fine analog video grain and gentle VHS tape noise, mild chromatic bleed, a little soft focus and light handheld sway, slightly blown highlights; nostalgic, dreamy, aspirational. Between scenes use soft home-video jump cuts, like clips from the same tape. TWO references with separate jobs: @image1 is THE SUPERMODEL and the star of every scene — identity kept EXACTLY from @image1 the whole time, the same face, hair and features in every scene; confident, radiant, effortlessly glamorous. Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 provides ONLY THE RUNWAY DRESS — take only the garment from @image2: its exact shape, silhouette, neckline, length, colour, fabric, finish and every detail exactly as shown — nothing invented or redesigned — fitted naturally onto @image1. If @image2 shows a model, that person is not used; the person is always and only @image1. In the earlier scenes @image1 wears other chic high-fashion looks; the @image2 dress is the show-stopper saved for the backstage reveal and the runway. SCENES (one glamorous fictional day), each a short glossy clip: 0–5s: THE ARRIVAL — @image1 steps out of a sleek black limousine onto a red carpet in a sharp tailored designer power-suit and huge sunglasses; paparazzi flashbulbs pop all around as @image1 smiles and glides forward like a star. 5–10s: THE EDITORIAL SHOOT — on a chic studio set, a wind machine lifts the hair as @image1 strikes bold high-fashion poses in a striking designer look styled to suit their gender presentation, flashbulbs firing; fierce looks, then a laugh between shots. 10–15s: LA DOLCE VITA — on a sunny café terrace on a glamorous boulevard, in an elegant summer outfit and jewellery that suits them, @image1 sips champagne with friends, tosses the head back laughing, sunglasses glinting. 15–20s: BACKSTAGE — THE DRESS REVEAL — backstage before the show, the @image2 dress hangs on a rail; stylists lift it down and help @image1 step into it, and the stylists fasten it so it fits perfectly, the dress falling exactly as its own cut and length allow; a stylist smooths the fabric; @image1 turns to the mirror in the @image2 dress, catching their breath, radiant and ready. 20–27s: THE RUNWAY — @image1 strides out onto a bright fashion-show runway in the @image2 dress, exactly as in the reference, a powerful confident catwalk straight toward the camera, the fabric moving with each step, as flashbulbs flare on both sides and the hair moves with each stride. 27–30s: THE FINALE POSE — at the end of the runway @image1 stops, pops a hip, throws a dazzling look and a hand to camera, then turns in a swirl of the @image2 dress as the crowd erupts in applause. Keep it glossy, glamorous and nostalgic throughout, clean frame with no on-screen text, captions, timestamps, logos or watermark.

1 step10
Seedance 2.530s · 4:3
Still Live

THE STORY: residents on the east side say the new streetlights are watching them, and the council insists the lights are only lights THE DISMISSAL: They're lights. They're just lights. THE RELATIVE: parent Those three lines are the joke. Change them and nothing else — their values are never restated below. ASSET MAP — every reference is bound here and cited by tag below: @image1 — the first frame. The person in it is THE PERSON for this entire take. CHARACTER LOCK — HIGHEST PRIORITY: The person 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, from first frame to last. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. Use they / their / them only. No face changes, no identity drift. No other people on screen. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame is the person and the set. The attached image outranks every word written below it: wherever the image and this text disagree, follow the image. A single continuous take on the floor of a television news studio — exactly the set of @image1, with the studio camera in the left foreground. PRIORITY 1 — SPOKEN LINES, in English, in their own natural speaking voice. 0 to 5 seconds — polished broadcast delivery, perfect diction, looking straight into the studio camera's lens. They read THE STORY as a news item, then hand off, verbatim: "Let's go to the report." 5 to 11 seconds — they believe they are off the air. Quiet, tired, speaking sideways to someone off camera, not to the lens. First, verbatim: THE DISMISSAL. Then, after a short beat: "My THE RELATIVE called me about this one. My own THE RELATIVE." 11 to 13 seconds — a calm, flat voice from off camera, unhurried, simply stating a fact, verbatim: "We're still live." PRIORITY 2 — THE JOLT. At 13 seconds their head snaps back toward the camera lens and their eyes widen. They say nothing more. PRIORITY 3 — PERFORMANCE. Keep it small and contained. The instant the handoff ends at 5 seconds their shoulders drop and they settle back into the chair, turning slightly away from the lens toward the off-camera voice. They look down at the desk. They rub one eye with their fingertips. They are weary, not disdainful — this is someone fond of the person who believed it. Do not throw the head back, do not mug, do not play it broad. PRIORITY 4 — THE STUDIO CAMERA. The broadcast camera in the left foreground stays absolutely motionless on its pedestal for the entire take, lens trained on them, never repositioned and never switched off. It is visible in the frame from the first second to the last. PRIORITY 5 — OUR CAMERA. Locked off on a tripod. No movement, no zoom, no cuts, no close-ups, no change of framing at any point. One continuous take from first frame to last, held at the framing of @image1. IF THE TAKE RUNS LONGER THAN 15 SECONDS: hold on them after the jolt. They do not speak again. They straighten slowly, square their shoulders, touch the knot of their tie or their collar once, and settle back into exactly the posture they held in the first five seconds — the professional mask going back on, far too late. The take ends there, still at the same framing. Hands keep five fingers. No text, lettering, captions or station graphics anywhere on screen.

3 steps
Seedance 2.515s · 9:16
The Silent Scream

A single unbroken pull-back from an extreme close-up of your face mid-scream out to a wide of the whole office, revealing you sealed inside your booth while nobody reacts. Upload your face and your booth. With sound, at the length you choose.

1 step
Seedance 2.518s · 9:16
Bottle Roll

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, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. Use they / their / them only. ATTACHED IMAGES ARE MANDATORY AND FINAL: The attached images outrank every word written below them — including the product’s exact shape, features and proportions. ASSET MAP: @image1 — the tiny living person. Photocopy face, hair, skin, and the clothes on the still, exactly as photographed. Ignore the grey studio pad around @image1 — that pad is not a set. Never freeze on the attached still as frame 0. Never keep the crossed-arms studio pose. Never show a checkerboard or transparency grid. @image2 — the product, exactly as shown, unchanged and not regenerated — same shape, colour, materials, label and hardware in every shot it appears. No invented branding or text added. Ignore the grey studio pad around @image2 — that pad is not a set. Keep @image2's real label as the product's own label — do not replace that label with @image1's face. SUBJECT LOCK — HIGHEST PRIORITY: @image1 is a three-dimensional tiny living person only a few centimetres tall — same face, features and proportions, just shrunk in scale — already physically inside @image2's own real interior cavity, visible through the real material of @image2, with real volume and depth. Not a doll, not a statue, not a posed still, not a printed portrait, not a sticker, not a 2D face on the label. Soft living micro-motion the whole time — blinks, breath, weight shifting. They are inside the real hollow of @image2 itself — not inside any invented box, wrapping, capsule, shell or added packaging of any kind. @image2 keeps its own real shape, material and finish exactly as shown throughout, including after it breaks open — nothing about its appearance is invented or changed. Do not beautify, restyle or redesign either subject. FORBIDDEN CAMERA / TREATMENT: never print @image1 onto @image2's label. Never treat @image1 as label art, a mugshot on the label, or a picture glued to the product. From frame 1 the tiny person must read as a real body inside @image2. HANDS: if @image1 has hands, they are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. SINGLE SUBJECT: only @image1 appears as a person — no other people, figures or hands enter frame. PHOTOREAL LIVE-ACTION: real camera, real surface, real impact — not CGI, not an animated illustration. Match grain, colour and lighting between @image1, @image2 and the surface so the whole shot reads as one photograph. SCALE REALISM: @image1 is a few centimetres tall relative to @image2, which is at its true full size. Match lighting and colour grade throughout so the whole shot reads as one real photograph, not a composite. The scale contrast is clearly visible in the very first frame: a tiny living three-dimensional person inside the full-size product, seen through @image2. PROP CONTINUITY: the real surface @image2 is rolling along, and the edge or drop it is heading toward, are both visible from frame 1 — nothing new appears later unexplained. CAUSALITY LOCK: every event has a shown, physical cause — @image2 is already rolling when the shot opens, not starting from stillness; it falls because it reaches the edge of the surface it was rolling on, visibly; it is fragile and cracks the instant it first touches the ground, at the exact point of contact, not after a bounce or a delay; it breaks open immediately because that first-contact crack gives way at once; @image1 tumbles free only because the opening is now physically there. FORBIDDEN: a slow spiderweb crack over several seconds; staying intact after landing; bouncing then cracking later. PACING: real, continuous motion for nearly the whole duration — no calm establishing pause longer than 1 second except the brief settled beat at the very end. Each beat below must read as a distinct, clearly readable event, not a blur. Do NOT default to a calm, mostly-still shot. Shot 1 must open already in motion — @image2 is already rolling, not sitting still. Never freeze on the reference still. SCENE: a real tabletop or shelf at warm indoor light, shallow depth of field, whimsical live-action macro realism. @image2 is already rolling along the surface, @image1 a tiny three-dimensional living person visible moving inside its real interior cavity, when the shot opens. Tiny real person — not a doll, not a statue, not a picture on the label. 0–2s: Already rolling fast along the surface, @image2 approaches the edge, @image1 clearly visible as a tiny 3D body inside @image2. 2–4s: It rolls off the edge and falls, tumbling as it drops, @image1 still inside the cavity. 4–5s: The instant @image2 first touches the ground it cracks at that contact point and breaks open there — fast, easy, no delay. 5–8s: @image1 tumbles free through the opening, landing clear of the broken pieces on the ground. 8–12s: @image1 sits up or steadies themself amid the broken pieces of @image2, the full scale of both clearly visible in this final frame. STYLE: photoreal live-action macro, warm indoor light, shallow depth of field. Vertical 9:16. Tiny real three-dimensional person inside a towering full-size product — not a doll, not a statue, not a posed still, not label art. AUDIO: natural foley only — a rolling sound building speed, a whoosh during the fall, a sharp impact thud and an immediate crack as @image2 hits the ground, a tumble as @image1 comes free, a soft settling sound at the end. No music, no BGM, no voiceover, no narration. No on-screen text, no watermark, no subtitles.

1 step
Seedance 2.512s · 9:16
Day in My Life — NYC (Your Jacket)

DAY IN MY LIFE — realistic personal NYC vlog, one continuous 30s piece, photoreal lifestyle. Two people: @image1 (the vlogger) and @image2 (the friend). Keep each exact face, hair, freckles and body proportions from their own reference the whole time; two clearly different people. Preserve their gender presentation exactly as shown. Use they / their / them only. @image2 appears only in the café and park. THE PRODUCT — @image3 is the jacket: @image1 wears exactly the jacket from @image3 over simple plain basics for the ENTIRE clip, from the very first frame to the last, in every scene — take only the garment from @image3 (its exact shape, colour, material, collar, fastening, pockets, cuffs, fit and details) and keep it identical in every shot; if @image3 shows a model, only the jacket is used and the person is always @image1. Sneakers and a tan shoulder bag complete the outfit. The jacket is clearly visible and naturally featured throughout, never covered for long. Three motivated camera perspectives: @image1's front selfie, @image1's rear-camera detail shots, and short third-person shots by @image2 or a propped phone. Transitions motivated by a palm over the lens, a fridge door, jacket fabric, a passing yellow taxi or pedestrian, a shopping bag across the lens, a whip pan. TIMELINE (30 s): 0–3.5s: morning selfie — @image1, already wearing the @image3 jacket, holds the phone at arm's length, smiles, gives a small wave, starts walking to the kitchen. 3.5–6.5s: kitchen — hand dropping spinach, banana, mango into a blender; close-up of pale green smoothie pouring into a glass; selfie raising the finished drink, one real sip and an approving nod, the jacket sleeve in frame. 6.5–9s: JACKET MOMENT — phone propped waist-height facing a full-length mirror; @image1 checks the @image3 jacket in the mirror — straightens the collar, fastens it as its own design allows, turns once to show the back, then slides the tan bag over the shoulder, checks keys, picks up the phone; a close detail shot of the jacket's texture and fastening fills the lens as a transition. 9–12.5s: bright Manhattan sidewalk selfie walk in the jacket, red-brick buildings, cafés, a yellow taxi passing, green trees, natural gait. 12.5–16s: a taxi wipes into a bright clothing store; @image1 browses a rack, a full-length mirror shot of the whole outfit with the @image3 jacket, holds a pale blue shirt up, leaves with one small kraft-paper bag. 16–19.5s: third-person sidewalk shot ahead as @image1 walks in the jacket carrying the bag, checks phone, a pedestrian wipes the frame, then opens a café door. 19.5–23s: inside the café @image2 sits by the window; a brief hug, @image2 touches the jacket sleeve and nods approvingly; two coffee cups arrive; overhead of the bag by the chair; both laughing. 23–26.5s: the kraft bag wipes the lens into a sunny city park; @image2 films @image1 walking backward laughing, the jacket moving naturally; cut to @image1's selfie as @image2 steps in beside. 26.5–30s: the two share a warm hug, sit on a bench side by side; @image1 looks to camera content, the jacket clearly visible; @image2 waves; @image1's palm fills the frame to end. Performance: conversational, natural pauses, real blinking, small imperfect gestures, hair moving in wind; not exaggerated influencer energy. Camera: realistic smartphone dynamic range, slight handheld, smooth stabilization, consistent screen direction, natural autofocus, cuts motivated by gestures and wipes; steady real-time. Lighting: bright natural late-spring daylight, natural skin tones, real material and fabric texture. Leave clean lower-frame space for captions to be added later. Clean frame with no baked-in text or logos. Audio: (a soft original acoustic-pop instrumental under the montage) plus realistic vlog ambience — light natural chatter between @image1 and @image2, room tone, brief blender, city traffic, café murmur, park wind; clear and pleasant.

1 step
Seedance 2.530s · 4:3
The Grandparent Interview

ASSET MAP — every reference is bound here and cited by tag below: @image1 — the identity anchor from step 1. This is the person: it defines face, build and identity. Referred to below as @avatar. CHARACTER LOCK — HIGHEST PRIORITY: @avatar 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. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Use they / their / them only. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. The grandparent described below is the ONLY other person inside the room. Every reference to the candidate in this prompt is @avatar — no pronouns, no description. ATTACHED IMAGES ARE MANDATORY AND FINAL: @image1 is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached image outranks every word written below it: wherever the image and this text disagree, follow the image. SPOKEN LANGUAGE: ENGLISH. Every spoken word is in English, exactly as written in the DIALOGUE block. The grandparent speaks fluent, precise, professional English with a thick Eastern European accent. @avatar speaks native English. Deadpan office comedy, documentary realism. One locked camera, no cuts. PRIORITY 1 — THE ORDER OF THE LAST BEAT, NEVER CHANGE IT: @avatar FIRST asks the question while sitting upright and facing the grandparent, looking straight at them — and ONLY AFTER the question is finished does the searching begin. The search is the consequence of the question, never before it and never during it. PRIORITY 2 — THE SEARCH: once the question is out, @avatar searches the room for a hidden camera with big visible movements while the face stays toward the camera. @avatar leans far SIDEWAYS out of the chair to look past the monitor, tips the head back to scan the two upper ceiling corners, cranes toward the potted plant, scans along the glass wall — then snaps back upright. @avatar leans and twists but NEVER turns away from the camera; the face is visible the whole time. PRIORITY 3 — THE CONTRAST: an old village grandparent is conducting a job interview inside a sleek modern high-tech software company office. Their village clothing and the glass-and-monitor tech office are BOTH clearly visible in the same frame from the very first second. The first beat opens on this, already in progress — no establishing shot, no empty room. They are already speaking when the video starts. PRIORITY 4: the grandparent is completely serious and professional, like a veteran HR director. Calm, unhurried, authoritative. They read from a sheet of paper and take a note. They never smile, never wink, never play folksy or comic, and they never once look up at what @avatar is doing — not even during the search. PRIORITY 5: one locked camera position, identical framing for the whole take. No camera movement, no zoom, no reframing, no second angle, no cuts. THE GRANDPARENT: village grandparent, about 72, sturdy and solidly built, broad shoulders, calm imposing presence, deeply weathered face, black headscarf tied under the chin, dark grey hand-knitted wool cardigan over a dark floral house smock, heavy worn hands. They sit behind the desk in a modern black mesh ergonomic office chair, holding one printed sheet of paper and a cheap pen. Fully inside the frame with space around them, never cropped by the frame edge. LOCATION: small glass-walled meeting room inside a modern software company. Behind them through the glass: an open-plan office, people at standing desks, exposed ceiling, soft daylight. Inside the room: a light oak desk, a closed slim laptop, a monitor showing a plain dark screen with no text, a glass of water, a potted monstera in the corner. NO readable text, NO letters, NO logos, NO visible user interface anywhere. FRAMING: wide locked two-shot, both people centred with air on both sides. The grandparent on the left behind the desk, fully visible. @avatar on the right, seated facing the grandparent. DIALOGUE — in English, in this exact order: (0:00-0:04) GRANDPARENT, already mid-interview and already speaking as the video opens, reading from the sheet, calm and professional: "Walk me through the difference between a monolith and microservices." (0:04-0:07) @avatar, upright, hesitant but polite: "Microservices... deploy independently." (0:07-0:11) GRANDPARENT, writing a note, not looking up: "Good. What was your p99 latency in production?" (0:11-0:14) @avatar, still sitting perfectly upright and looking straight at the grandparent, polite and careful: "Sorry — is this a hidden camera?" (0:14-0:20) ONLY NOW the search begins: @avatar leans sideways to look past the monitor, tips the head back at the ceiling corners, cranes toward the plant, scans the glass wall — face still toward camera. Over the top of this, GRANDPARENT, flat, never looking up from their sheet: "No. And that is not an answer." @avatar keeps searching one more beat, then settles back into the chair, defeated. (0:20 to the end of the take, only if the take runs longer than 20 seconds) Nobody speaks again. The grandparent writes one more note, still not looking up. @avatar sits still, glances once more at the ceiling corner, then back at the grandparent. Hold that silence, unchanged, to the last frame. SOUND: quiet open-plan office hum, distant keyboards, faint air conditioning. Calm, flat, conversational delivery. No music, no laugh track.

2 steps
Seedance 2.520s · 9:16
Printer Boss Fight

CHARACTER LOCK — HIGHEST PRIORITY: @avatar is the person in the attached first frame, exactly as shown. Preserve 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, body proportions and gender presentation exactly as shown. Do not beautify, slim, de-age or restyle. Preserve their gender presentation exactly as shown. Use they / their / them only. Every reference to the person in this prompt is @avatar — no pronouns, no description. The shot continues from the attached frame and never leaves that office. The machine @avatar faces is the one already in frame: keep it exactly as shown, in shot the whole time, never replaced and never redressed. A 1990s Hong Kong martial-arts film homage, played completely straight — no winking at the camera. Single continuous take. PRIORITY 1 — SPOKEN DIALOGUE, these exact lines, natural office voices, English: 0.5-3s — a seated colleague, not looking up from a monitor: "Is it jammed again?" 3-6s — @avatar, settling deeper into the stance: "I don't speak to it anymore." 9-11s — @avatar, catching the sheet one-handed without looking: "Double-sided." PRIORITY 2 — THE AUDIENCE: four colleagues roll their office chairs backwards to clear a circle around @avatar and watch like spectators. They stay visible in frame throughout and never leave the shot. PRIORITY 3 — CHOREOGRAPHY, performed with total seriousness, every move a precise and controlled gesture: 0-3s @avatar holds the stance and rolls the neck once. 3-6s one flat palm sweeps across the front of the machine in a single motion. 6-9s @avatar turns, and at the top of a jump the sole of a shoe closes the machine's lid. Lands. Holds a still pose, one arm extended toward it. 9-12s the machine feeds out one clean white sheet; @avatar catches it one-handed without looking. 12-15s @avatar bows to the machine. Hold on the bow. PRIORITY 4 — AUDIO ARC: a low ceremonial gong and taiko drums build from 3s and peak at the jump. The instant the sheet appears at 9s everything cuts to silence — the line lands inside that silence, and the bow plays with nothing but room tone. Camera: slow arc around @avatar for the stance, steady wide for the choreography, push in for the bow.

2 steps
Seedance 2.515s · 9:16
Becoming Merfolk — The Transformation, Step by Step

BECOMING MERFOLK — THE TRANSFORMATION, STEP BY STEP. One continuous cinematic take, full realtime speed, a magical transformation shown clearly and in order, each stage given its own time. AUDIO MIX (ranked, three separate layers): 1. MUSIC — loudest, dominant from the very first frame: an enchanting, shimmering orchestral instrumental with harp, celesta, soft strings and a wordless dreamy synth, rising to a magical swell; original, instrumental only. 2. SFX — quiet, under the music: gentle waves, a soft splash, deep underwater bubbles. 3. VOICE — none; @image1 stays silent the whole clip. Audio suppressor: no voiceover narration, no dialogue, no spoken words, no singing vocals, no lyrics, no library audio bed, no muffled murmuring, no subtitles. The music resolves on a final hit and silence holds the final 0.5s. @image1 keeps the exact same face and features as the reference the whole time — same eyes, same nose, same skin, only what is present in the reference. Preserve their gender presentation exactly as shown. Use they / their / them only. SETTING: a hidden turquoise lagoon at golden hour, rocks rising from the water, then the glowing world below the surface — coral, shafts of sunlight, shoals of fish. BEATS (25s): 0–5s: @image1 sits on a flat rock at the edge of the lagoon in a simple white swimsuit, feet dipped in the glowing water; the water around the ankles begins to sparkle. Camera: slow push-in. 5–11s: THE TAIL — starting at the feet, shimmering iridescent teal-and-violet scales spread up the legs, the legs drawing together and joining into one long powerful merfolk tail, a wide translucent fin unfolding at the end with a flick that sprays water. Camera: following the scales up the tail from fin to hips. 11–15s: delicate scales trace up along the waist and shoulders, delicate shell-and-pearl adornments form across the collarbones, and tiny pearls weave into their own hair, its length, colour and texture exactly as in @image1. Camera: rising up to the face. 15–19s: @image1 looks down at the new tail in wonder, smiles, and dives off the rock into the lagoon in one graceful arc. Camera: following the dive into the water. 19–25s: UNDERWATER — @image1 swims through glowing coral and sun rays with powerful strokes of the tail, hair floating like silk, fish swirling around, then turns to the camera with a radiant smile. Camera: gliding alongside underwater, holding on the smile to the last frame. LOOK: ultra-photorealistic cinematic fantasy, luminous turquoise-and-gold grade, real water, scales, hair and skin, natural motion blur, film grain, clean full frame.

1 step
Seedance 2.525s · 9:16
Dramatic Zoom — The Last Slice

ASSET MAP — the attachment is bound here and cited by tag below: @image1 — the opening frame. The office kitchen, the open fridge, the plate, the cake and the person are already in this exact position, and this is also the identity source for the person in every single shot. ATTACHED IMAGE IS MANDATORY AND FINAL: The person in @image1 is the person in this film. Reproduce them exactly, in every frame they appear in, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached image outranks every word written below it: wherever it and this text disagree, follow the image. CHARACTER LOCK — HIGHEST PRIORITY: 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, phase to phase. Preserve their gender presentation exactly as shown. Do not beautify, slim, de-age or restyle them. Their wardrobe and eyewear stay identical from the first frame to the last. PROPS — PRIORITY 1: There are exactly three objects in this entire film and no others ever appear: the white side plate, the single slice of chocolate cake on it, and the one yellow sticky note. No other food, snack, wrapper, chocolate bar or item enters the frame at any point, in any hand, on any surface. Nothing in frame is ever swapped for something else. The yellow sticky note exists in every phase of this film — it is on the plate at the start and in their fingers at the end, and it NEVER disappears, is never put down and is never out of the film. The cake slice only gets smaller as it is eaten; it never grows back, changes shape or becomes a different food. EYES — PRIORITY 1: Their eyes stay exactly as in @image1 for the whole film. Iris colour never changes, the whites stay white and clear, and the eyes never glow, redden or take on any colour or light of their own. Nothing supernatural happens in this film. LIGHTING IS CONSTANT: The kitchen lighting never changes. It stays exactly as it is in @image1 from the first frame to the last — nothing dims, brightens or flickers, and the room never goes dark. THE COLLEAGUE IS NEVER SEEN. The other voice belongs to a colleague standing behind the camera. They never enter the frame, not a hand, not a shoulder, not a reflection. The person in @image1 is the only human being in the film. THE ENGINE OF THIS FILM IS THE ZOOM. Three hard mechanical snap zooms, each tighter and faster than the last, each landing on a new piece of information. Between them the camera holds nearly still with a faint handheld drift. The joke is that a slice of cake is being filmed like a murder investigation and nobody finds this strange. The escalation lives in the camera and the sound, never in an effect on the person. THE FILM HAS THREE PHASES OF EQUAL LENGTH, whatever the total running time. Divide the duration into three equal parts and play one phase in each. The beat timings below are written for a fifteen second film — five seconds per phase — and scale proportionally if the film is shorter or longer. Never drop a phase and never add one: all three always happen, in this order, and the final line always lands at the very end. PHASE 1 — the first third. Begin exactly on @image1. The person is frozen mid-bite, plate in one hand with the yellow sticky note on its rim, cake raised in the other. They chew once, slowly. ZOOM 1 — a fast punch-in to a chest-up shot. It lands hard and stops dead. They stop chewing. COLLEAGUE (off camera, completely calm): "Is that mine?" The person swallows with effort. PERSON: "...Is it?" PHASE 2 — the middle third. COLLEAGUE (off camera): "It has my name on it." A clock that was not audible before begins to tick. The person peels the yellow sticky note off the plate rim and brings it up in front of their face. They read it. Their expression moves toward outrage, not guilt. ZOOM 2 — a violent snap zoom onto the sticky note held between their fingers, filling the frame: a plain square yellow note, held rock steady, a short handwritten first name in blue ballpoint ink in clear block capitals across the middle. Hold on the note for a full second without drifting. PHASE 3 — the final third. ZOOM 3 — a snap zoom back out to a chest-up shot, lit exactly as in the opening frame. The ticking stops dead. The sticky note is still in their hand, visible in frame. They look straight into the lens, not guilty any more at all. They take one enormous unhurried bite of the same cake slice, still staring down the lens, and chew it with complete composure. PERSON (flat, almost cheerful, straight to camera): "Never mind, now it's mine." That line is the last thing in the film. They hold the look for a beat, then hard cut to black. Nothing happens after the line and nobody answers it. AUDIO: Quiet office kitchen room tone throughout — a fridge hum, a distant corridor. Each of the three zooms carries a sharp low whoosh and a deep bass thud on landing, each louder than the last. From phase 2 a slow clock tick creeps in and stops dead in phase 3. The dialogue is only the four lines above, delivered flat and unhurried, never shouted. One unhurried chewing sound before the final line, and the final line is the last human sound in the film. No music, no laugh track, no narration. HANDS: Exactly five fingers per hand, correct anatomy, no fused or extra digits, a clean natural grip on the plate, the cake and the sticky note.

2 steps
Seedance 2.515s · 9:16
Nina

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. Do not beautify, slim, de-age or restyle them. No other people in frame. Use they / their / them only. ATTACHED IMAGES ARE MANDATORY AND FINAL: The attached images outrank every word written below them — including @image2's exact shape, features and proportions. ASSET MAP: @image1 — the tiny living person. Photocopy face, hair, skin, and the clothes on the still. Ignore the grey studio pad around @image1 — that pad is not a set. Never freeze on the attached still as frame 0. Never show a checkerboard or transparency grid. @image2 — the product, exactly as shown, unchanged and not regenerated — same shape, colour, materials, hardware in every shot. No invented branding or text. There is only ONE @image2 in the entire scene, at its TRUE FULL SIZE. Never a second copy. Never a miniature replica. TINY SCALE — HIGHEST PRIORITY, MUST READ FROM FRAME 1: This is a MACRO shot. @image1 is a living person only a few centimetres tall. Their whole body would fit in a teacup. They stand or perch ON the surface of @image2 itself, working on @image2's own surface. @image2 is architecture — true full-size, same shape as the photo. It fills most of the frame like a hillside, its own surface, details and any hardware towering like terrain, exactly as shown — same shape, colour, materials, label and logo; nothing invented or redesigned. They work on its SURFACE. They are smaller than the smallest detail on @image2. They could not reach the far end of @image2 even with a ladder of fifty of themselves. Frame 1 MUST show: tiny full-body (or head-to-waist) person standing ON @image2's own surface AND the rest of true-size @image2 filling the frame around them. If the person and @image2 look like a normal adult standing next to a normal-size object, the shot is WRONG. There is never a second @image2 at any other scale. They polish, wipe, or fix a tiny loose part ON this one object — never on a separate miniature, never on a workbench copy. FORBIDDEN CAMERA — instant fail: - Never a seated or standing adult whose body is similar in height to @image2. - Never a studio two-shot of a person beside a tabletop object of similar scale. - Never giant-hands POV / giant fingers / giant face filling the frame. - Never a socked ankle, a second foot, a second person, or a second @image2. - Never a miniature replica of @image2 anywhere in frame. If a hand appears it is THEIR tiny hand, matching their tiny body, five fingers, naturally proportioned. They are a tiny living person — not a doll, not a statue, not a posed still pasted onto @image2. Soft living micro-motion the whole time — blinks, breath in the shoulders, weight shifting. HANDS: tiny, anatomically correct, five fingers, same scale as their body. SINGLE SUBJECT: only @image1 appears as a person — no other people, figures, ankles, socks or giant hands enter frame. Only one instance of @image2 exists in the scene. SCALE REALISM: Match lighting and colour grade between @image1 and @image2 throughout so the whole shot reads as one real photograph, not a composite. The scale contrast between @image1 and @image2 is clearly visible in the very first frame. PHOTOREAL LIVE-ACTION MACRO: real camera, real light — not CGI. Match grain, colour and lighting between the tiny person and towering @image2 so the whole shot reads as one photograph. PROP CONTINUITY from frame 1: true-size @image2 filling the frame, a pin-scale cloth or tool in their hands, and the surface @image2 rests on. Nothing new appears later unexplained. CAUSALITY LOCK: every action has a shown, physical cause — they spot a smudge or mark on @image2's surface, lean toward that exact spot, and work on it; the cloth or tool catches on a ridge, stitch, or piece of hardware of @image2, causing a visible pause, not without reason; they adjust grip and continue, a direct cause and effect. PACING: real continuous motion almost the whole duration — no calm pause longer than 1 second. Shot 1 opens already in motion. Never freeze on the reference still. SCENE: a warm-lit wooden corner, @image2 at true full size filling the frame like terrain, soft lamp glow, shallow depth of field, whimsical live-action macro realism. Tiny @image1, already mid-task on @image2's own surface, is working a section of it when the shot opens. 0–2s: Already at work at insect scale — whole upper body visible on the surface of towering @image2 — they run the cloth along its surface, spotting a stubborn mark. 2–4s: The cloth catches on a ridge or piece of hardware of @image2 — they pause, steadying their footing on its surface. 4–6s: They adjust their grip and press on, working the mark carefully. 6–8s: They step back along @image2's surface to check their work from a different angle. 8–10s: Satisfied, they give the spot one last wipe until it gleams. 10–12s: They stand back on @image2's surface, small against its true full-size form, admiring the finished result. @image2 still fills the frame around them. STYLE: photoreal live-action macro, warm lamp, shallow depth of field. Vertical 9:16. Insect-scale living person on the surface of silo-sized @image2 — not a doll, not a statue, not a full-size adult. AUDIO: natural foley only — soft wiping/polishing sound, a small catch-and-pause sound, quiet resumed polishing, a satisfied exhale at the end. No music, no BGM, no voiceover, no narration. No on-screen text, no watermark, no subtitles.

1 step
Seedance 2.512s · 9:16
The Gatsby Party Host — A 1920s NightSeedance 2.5 · 4:3 · 25sRecreate workflow