Fast-paced, smooth luxury fashion editorial film. @image1 is an absolute character lock: face, body, hair, wardrobe, materials and colours are taken from it exactly and stay identical in every shot, at every distance, with no drift and no reinterpretation. @image2 is an absolute location lock: the wall, the height chart, the floor and the lighting are taken from it exactly. @image3 is the storyboard and is followed exactly — framing, body position, eyeline and prop placement match it. Storyboard panel 1 is shot 1, panel 2 is shot 2, panel 3 covers shots 3 and 4, panel 4 is shot 5, panel 5 is shot 6, panel 6 is shot 7. Performance throughout: playful, confident, slightly mischievous. Shot 1 The subject@image1 stands squared to camera in a full-body composition in front of the height chart, looking straight down the lens, then gives a single playful wink. Camera pushes in slowly and smoothly. Shot 2 The subject@image1 holds a hand-held placard reading 【WANTED FOR BEAUTY】 up toward camera and tilts it slowly forward with attitude. Camera holds steady. Shot 3 Rapid detail inserts in close framing: the mouth as the lips part into a smile, the painted nails, the lollipop lifted toward the mouth. Camera snap-zooms in on each detail. Shot 4 Rapid detail inserts continuing: the pile of the outer jacket, the metal neck chains, the sunglasses held in the hand. Camera whip-pans between each detail. Shot 5 The subject@image1 returns to the full standing composition, leans weight casually onto one side while holding a confident stance, puts on the sunglasses, looks over the top of them straight into the lens and smiles. Camera orbits smoothly around them. Bright flash bursts fire intermittently from off-frame, like photographers crowding in. Shot 6 Fast montage across the styling: the outer jacket, the cropped top, the belt and chains, the denim, the lollipop, the mouth, the eyes, the sunglasses. Sheets of newspaper fly across the frame between details. Camera moves continuously and smoothly through the sequence. Shot 7 The subject@image1 is back in the full mugshot composition, holding the placard forward toward camera. The placard now reads 【WANTED FOR BEING TOO BEAUTIFUL】. They raise one eyebrow and smile. Camera pushes rapidly toward the face. A sheet of newspaper sweeps across the lens and the frame cuts to black. Lighting and colour: hard institutional overhead light on the wide shots, clean even light on the inserts, glossy high-end editorial grade, rich blacks, true colour. Camera: one controlled move per shot — push-in, snap zoom, whip pan, orbit, or rapid push. Always fluid and deliberate, never handheld jitter. Editing: very short cuts throughout, seamless whip transitions, subtle speed ramps, newspaper wipes, beat-synced cutting rhythm. Fast but polished — never slow, never dreamy, never jittery, never chaotic. Visual style: glossy magazine fashion editorial crossed with a cinematic booking-room mugshot, playful troublemaker energy, fashion-editorial motion blur, premium campaign finish. Image quality: ultra photorealistic live action, realistic human anatomy, realistic fabric and metal, sharp and clean. Constraints: do not generate a logo. Do not generate a watermark. Do not generate any on-screen text other than the wording on the placard. Do not alter the wardrobe, the face or the location from the reference images.
Drag the clip sideways
CHARACTER LOCK — HIGHEST PRIORITY (applies separately to @image1 and @image2): Each character in every shot is exactly the character in their own reference image. Photocopy facial identity from the matching tag. Preserve 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. Refer to both only as they/them. Do not beautify, slim, de-age, restyle hair, or morph any face into another. Never swap the two identities. Do not invent extra leads. Do not describe the faces — follow the images only. @image1 is the younger sibling. Photocopy @image1 exactly: same child face, same hair, same skin, same body, same cream floral embroidered romper from the still. Clothing from @image1 stays on them the whole film. They do not hold the necklace from the still. @image2 is the older sibling. Photocopy @image2 exactly: same child face, same hair, same skin, same body, same cream short-sleeve mandarin shirt with blue geometric embroidery and matching cream trousers from the still. Clothing from @image2 stays on them the whole film. Never swap with @image1. Never recast either child as an adult. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. PROP CONTINUITY: the flashlight and the blanket are both present from Scene 1 onward — nothing new appears later that was not already established. CAUSALITY LOCK: the only light sources are the flashlight beam (held by @image2) and brief natural lightning flashes through the window — the wall shadow shapes only appear because of the flashlight beam directly shown causing them. PACING: despite the storm setting, all human motion stays calm, slow and reassuring throughout — no panicked or frantic movement; the only quick element is a single brief lightning flash. Never open on a studio headshot, grey seamless, white cyclorama, checkerboard cutout, or the attached photos as frame 0. First frame is already in the child’s bedroom, in-scene. 18 seconds. 9:16 vertical. Heartwarming cinematic 3D animated short film in a high-quality family-animation style — a cozy bedtime story moment during a nighttime storm. Premium animated-movie look, not live-action street photoreal. Expressive characters, realistic soft skin and hair on the locked faces, detailed facial expressions, physically accurate lighting, warm-to-cool nighttime color palette, soft shadows, realistic fabric and blanket textures, smooth natural body movement, cinematic depth of field, subtle camera motion, high-end animated movie quality, polished rendering, emotionally wholesome storytelling. AUDIO (native, synced, diegetic only): distant thunder, rain on the window, a flashlight click, quiet fabric, a small shared laugh, a goodnight hug. No BGM, no score, no songs, no on-screen text. SCENE 1 — 0–5s: A soft flash of lightning briefly lights the window as @image1 sits up in bed, startled by the thunder outside. @image2 quietly enters the room holding a flashlight and the blanket, sitting down beside the bed with a warm, reassuring smile. SCENE 2 — 5–10s: @image2 switches on the flashlight and gently shapes their hands to cast a butterfly-shaped shadow on the wall, moving it slowly and playfully. @image1 watches, curiosity replacing fear, a small smile appearing. SCENE 3 — 10–14s: @image2 shifts the flashlight to cast a second, different shadow shape — a hopping rabbit — gently moving across the wall. Both @image1 and @image2 smile and quietly laugh together, fully at ease now. SCENE 4 — 14–18s: The storm softens outside to a gentle, steady rain. @image2 switches off the flashlight, tucks @image1 in with the blanket, and gives a warm goodnight hug. Soft moonlight settles over the room as @image1 drifts off to sleep, calm and safe. CAMERA: Smooth cinematic camera movement, close-ups, medium shots, gentle push-ins, shallow depth of field, natural focus transitions. No text, no subtitles, no logos, no burned-in watermark, no BGM, no distorted anatomy, no extra fingers or limbs, no flickering, no sudden character or design changes, no studio grey still as frame 0, no necklace as a scene prop. NEGATIVE: identity swap, adult recast, extra people, live-action street photoreal that drops the 3D family-film look, on-screen type, score/BGM, checkerboard background.
THE SCULPTOR. @image1 (the sculptor) unveils a clay bust of @image2 (the woman he lost); touching her clay lips throws him into warm Super-8 memories of their love, then he returns and presses his forehead to the bust. Plug in ANY two avatars. Sound effects and four spoken lines only, no music. See the video step for the full prompt.
@image1 is an absolute character lock — face, hair, body, outfit, materials and colours are taken from it exactly, with no drift or reinterpretation in any shot. @image2 is an absolute product lock — the object carried and used throughout is exactly the one shown there, with consistent proportions, materials, finish and detail in every shot. @image3 is the location reference — the world of the film is those environments, with that architecture, palette and light progression. @image4 is the storyboard and is followed exactly: same shot order, same framing, same focal length, same pose and same staging, panel by panel. Premium product film and cinematic lifestyle advertisement, commercial grade, multishot. Look: photoreal cinema, slight filmic grain, mild halation on highlights, neutral-to-cool city tones, deep natural greens, warm skin, controlled blacks and natural environmental colour. Cinematic neutral-and-warm grade, greens restrained and natural, the product rich against neutral surroundings, golden rim on faces and product edges in sunlight, cool atmosphere at blue hour and night. Realistic skin tones throughout. No excessive saturation, no artificial HDR. Core concept: one person experiences a visually rich day through an energetic but natural sequence of movement, city life, architecture, food, people and landscape — captured through the product they carry. The film reads as a flagship product campaign crossed with an elite cinematic travel film. The product is always physically present and naturally used throughout the journey. Every location feels photographed rather than generated. Music drives the edit, but the footage keeps the imperfections and spontaneity of real travel photography. The person carries the product naturally throughout. The locations connect as one continuous journey and give them real reasons to photograph, record and experience the world with it. CLOSE-UP HOOK — 85mm close-up of the product resting beside a window in soft early-morning sunlight. Light travels naturally across the glass and metallic edges. They reach into frame, pick it up and look toward the bright city outside. The finish catches a subtle warm reflection as the first beat begins. MORNING CAPTURE — 24mm wide as they walk a lively city street in early morning. Sunlight breaks between the buildings. They raise the product naturally and capture the moment. Cut briefly to the display showing the same scene being framed. They lower it and keep walking. Cut precisely with the music. MOVEMENT — 35mm handheld follow as they move through a busy intersection. Real pedestrians cross naturally. Bicycles, taxis and buses move through the background. They begin recording while walking. The camera follows slightly behind rather than framing them perfectly. They turn toward a passing subject while keeping the product in use. STREET LIFE — 50mm observational. They move through a crowded neighbourhood while a food vendor prepares steaming food nearby. They stop briefly, raise the product and record the preparation. Steam passes across the foreground. They check what they captured, smile naturally and move on. HUMAN MOMENT — 50mm close-up. They meet a local person at a café and naturally raise the product to capture a portrait. Cut briefly to the captured image on the display. Natural skin texture, realistic hair strands and soft environmental separation. They lower it as the other person laughs naturally. Shallow depth of field, warm skin tones, authentic background activity, subtle handheld movement. LANDSCAPE REVEAL — 24mm deep focus. They climb a long stone staircase through dense greenery, camera following from behind. As they reach the top a vast landscape emerges through cool atmospheric mist. They raise the product and frame the whole valley. A brief display perspective reveals the landscape composed naturally before returning to the real-world wide. PRODUCT MOMENT — 50mm side-tracking in golden sunlight. They walk the elevated viewpoint holding the product naturally at their side. Golden rim light catches hair, shoulders and its metallic edges. Natural wind moves the clothing. The finish contrasts against deep green vegetation without feeling artificially highlighted. ACTION CAPTURE — 24mm wide from a realistic elevated platform as a high-speed train begins moving through the scene. They raise the product and record the passing train. Cut briefly to the display as the train moves rapidly through frame. Reflections slide across the train windows while realistic motion blur follows the movement. Return to them as the train disappears into the distance. NIGHT TRANSITION — 50mm handheld street shot at blue hour. They enter a lively nighttime district. Warm lanterns, cool ambient light, scooters and pedestrians create layered depth. They raise the product to photograph the illuminated street. Music increases in intensity while authentic street ambience stays underneath. LOW-LIGHT MOMENT — 35mm tracking as they walk beside a modern riverside district. Reflections ripple across the water. Modern towers illuminate behind them while boats move naturally through frame. They stop briefly and capture the skyline. The product catches small reflections from the surrounding city lights. CITY ENERGY — 50mm close-up as they check the captured images while walking through the nighttime district. Screen light subtly illuminates the face. They smile naturally, lock the product and keep walking. Camera moves alongside them as practical lights, pedestrians and reflections create layered cinematic depth. FINAL REVEAL — 24mm wide from behind. They stop briefly at the riverside and raise the product toward the illuminated skyline. Camera moves slowly backward rather than flying upward. They capture one final image, lower it and continue walking as the music reaches its final beat. The product stays naturally visible in hand as the city fills the background. CAMERA — 35mm and 50mm for portraits and human moments, 24mm for landscapes, architecture and movement, occasional 85mm compression on faces and product details. Shallow depth of field on close-ups, deep focus on landscape wides. Handheld and physically motivated tracking movement. Natural camera micro-movement, imperfect framing, subtle autofocus adjustment, realistic exposure adaptation and occasional foreground obstruction. No impossible camera movement, no floating drone aesthetic. MOTION — 180-degree cinematic shutter, natural motion blur on hair, clothing and moving vehicles, 24fps. No soap-opera 60fps look. Movement keeps the subtle imperfections of real location photography. Interaction with the product must feel physically accurate, with believable hand movement, weight and momentum. LIGHTING — Natural daylight, soft overcast city light, warm direct sunlight, golden-hour rim light, cool atmospheric light, practical lanterns and nighttime city illumination. Lighting originates naturally from the environment. Reflections on the product respond naturally to the surrounding light sources. AUDIO — Premium contemporary cinematic soundtrack with subtle modern electronic textures. Music drives the transitions and rhythm. Keep authentic location sound underneath: footsteps, traffic, train ambience, station announcements, bicycles, vendors, cooking sounds, crowd chatter, wind, birds, distant city noise and riverside ambience. Environmental sound occasionally becomes prominent during intimate moments. Subtle natural handling and shutter sounds may accompany key captures without becoming exaggerated. EDITING — Music-synchronised commercial editing without excessive effects. Cuts are motivated by movement, reflections, steam, hand gestures, architectural shapes, walking direction and changes in light. Clean match cuts and occasional speed changes only where physically believable. Avoid generic AI transitions, artificial zooms, excessive whip transitions and over-edited montage pacing. CONTINUITY — The person stays identical in every shot: face, hair, overshirt, trousers, sneakers and bag. The product stays identical throughout, with consistent proportions, materials, finish and detail. Weather and lighting progress realistically from daylight to golden hour to blue hour to night. Each location reads as part of one continuous journey, and every interaction with the product stays physically and visually consistent. BRAND CONTROL — The only branding visible is whatever already exists on the product in @image2. Invent no additional branding, advertisements, storefront branding or branded products. Add no fictional accessories, no random interface, no watermarks and no random text. Preserve the product's finish and identity exactly, consistent across the whole film. REALISM — No CGI look, no plastic skin, no beauty-filter smoothing, no extra fingers, no warped product geometry, no changing hardware, no artificial crowd synchronisation, no impossible reflections, no floating objects, no exaggerated depth of field. Realistic skin pores, hair strands, fabric texture, glass reflections, metallic surfaces, screen brightness, water reflections, atmospheric perspective and human movement. The product behaves like a real physical object with believable weight, grip, reflections and interaction with light. FINAL QUALITY TARGET — The film should look like genuine footage captured by an elite commercial filmmaker for a major product campaign, not a collection of AI-generated beauty shots. The product should feel like a real object being naturally used to experience and capture the world, rather than something inserted into every shot. Realism comes first; the commercial polish comes from cinematography, product design, colour, music, editing and art direction.
An extremely fast-paced luxury fashion editorial film. High-fashion magazine campaign look, cinematic overhead photography, dramatic hard sunlight and deep black shadows, glossy beauty lighting, realistic skin and hair, deep red accents, restrained luxury editorial grade. Constant visual movement and very quick cuts throughout, cut tightly to a punchy fashion beat, with speed ramps, whip transitions, snap zooms and real motion blur. Photographic throughout — not illustration, not animation, not a 3D render. @image1 is the character sheet and is an absolute character lock: face, build, hair, the garment, the sunglasses, the pearl earrings, the red nails and the red lip are taken from it exactly, with no drift and no reinterpretation in any shot. @image2 is the set board and is an absolute set lock: the newspaper carpet, the hard raking sunlight, the deep shadows and the petals are taken from it exactly. @image3 is the storyboard and is followed exactly: six shots in that order, matching its framing, subject scale and composition. POSE — the person lies on their back on the newspaper for the entire film and the pose of the body never changes: no standing, no walking, no sitting up, no rolling over, no change of how the torso, hair or legs are placed. The arms and hands move, the hair and the paper move, the camera moves, the light moves. The body holds its placement while everything around it moves. Shot 1 — the full overhead of the figure lying among the newspaper. A rapid push-in straight down toward them, then an immediate hard cut to a macro of the mouth as a lipstick bullet is drawn across the lower lip. Shot 2 — a burst of ultra-fast beauty cuts, each on screen for a fraction of a second: lips, the lipstick stroke, the sunglasses, the nails, an earring, the eyes. Snap zooms into each and whip transitions between them. Shot 3 — back to the full overhead composition. One hand comes up and pushes the sunglasses straight while loose sheets of newspaper fly rapidly across the frame, and the camera arcs fast around the figure in a quick circular move. Shot 4 — a faster macro montage, harder cuts again: the lipstick closing, light across the lips, sunlight catching a lens, the nails gripping and bending a curled edge of paper, an earring swinging clear of the neck, hair shifting across the newsprint. Aggressive editorial cutting, speed ramps and flash transitions. Shot 5 — return to the overhead. The lipstick is drawn across the lips again, unhurried, while the newspaper swirls rapidly around them and red rose petals fall from above, layering movement around a pose that does not change. Shot 6 — a last rapid run through the eyes, the lips, the sunglasses, the nails and the earrings, then a sudden overhead pullback that opens out to reveal the entire newspaper-covered composition. Sheets fly directly across the lens and carry the final cut. Audio is a punchy fashion beat driving the edit, with the cuts landing on it. No voice, no dialogue, no narration. No subtitles, captions, on-screen text, logos or watermark are burned into the frame. No legible headlines or readable words on the newspaper.
Cinematic luxury fashion commercial. Concept: FROM EVERYDAY TO ICON. STYLE: photorealistic luxury fashion campaign, cinematic 35mm photography, premium editorial lighting, realistic skin and fabric texture, subtle atmospheric haze, shallow depth of field, physically accurate fabric movement, elegant restrained camera choreography, a sophisticated visual evolution from bright and pale to dark and rich. One person, held completely consistent from first frame to last: the same face, hair, body proportions and identity throughout, with no drift and no reinterpretation at any point. They begin in an everyday outfit in a bright modern interior and end in a black couture gown and heels in a dark fashion studio. One continuous forward walk in one continuous shot. No cuts, no teleportation, no sudden camera changes. They stand in the bright interior and begin walking forward with calm confidence, expression natural and unforced. Camera follows smoothly on a cinematic 35mm lens, holding a full-body or near-full-body composition. They keep walking through the beam of daylight and the fabric of the everyday outfit starts to change, the weave becoming progressively finer and more lustrous, the lower garment gaining richer texture and a more refined surface. The change happens continuously while they move, never as an instant swap. They keep walking and the garments continue evolving toward couture, the upper garment becoming a couture top, the lower garment opening into a flowing skirt, the footwear resolving into refined heels. Fabric holds realistic weight, folds, tension and movement throughout. They keep walking and the space itself changes around them, the walls, furnishings and windows darkening and dissolving into a dark fashion studio, soft light and delicate haze taking over. The room transforms around them; they are never teleported into it. They reach the centre of the studio and slow to a stop, now fully in the couture gown and heels. Camera eases from tracking into a subtle elegant arc as the skirt flows around them, and they turn slightly toward camera with a calm, confident editorial expression. Camera settles and slowly pulls back into a refined hero composition, rim light outlining hair, shoulders and silhouette. STRICT CONSISTENCY: same face, same hair, same body proportions, same identity throughout. One continuous forward walk. The wardrobe change is gradual and physically believable. The location change is gradual and seamless. Correct anatomy, two arms, two hands, two legs and realistic feet. No flickering, no disappearing clothing, no clipping, no extra limbs.
DRONE TO PLANET IN HAND. A fast FPV drone flight through a city at golden hour zooms out until the whole Earth shrinks to a tiny glowing miniature planet held in @image1's palm as they look at it with wonder. Plug in ANY avatar. See the video step for the full prompt.
16:9 30-second AT HOME ad. English only. Adults. NO high school, NO sailor uniforms, NO Japanese campus, NO Chinese or Japanese on-screen text. @image1 = ELARA. Photocopy FACE and hair exactly as in @image1, at their own age, day makeup (foundation, mascara, blush, lipstick). Outfit: metallic gold tank, grey pleated mini over black shorts, grey slouch socks, white high-tops, silver necklaces. She is walking home from dance rehearsal. Never a grey studio as frame 0. @image2 = ERIC. Photocopy FACE. Grown man in a European club football jersey, shorts, socks, boots. Rec/pro practice, not a school kit. @image3 = the bottle. Photocopy THIS bottle exactly as in @image3 — liquid colour, cap, logo and every printed word exactly as shown. Never a different bottle. SETTING: European football pitch in late afternoon. Adult team training in the background. Chain fence, grass, a vending machine or cooler by a low wall on the path. Elara walks that path. TONE: flirty ad. Looks, smirks, the nutmeg as a wink. Chemistry you can see. MUST: she kicks the ball BETWEEN HIS LEGS (a nutmeg). One continuous shot of trap → push → ball rolling through his stance. He clamps late. NO spoken dialogue. Light upbeat ad music ok plus ambient. 0:00–0:04 Elara on the path, cold @image3 bottle to her cheek, post-rehearsal glow. A football rolls out the gate, taps her calf. 0:04–0:08 Eric jogs over in the club jersey, apology that turns into a flirty smirk and a “kick it back” flick. She matches the look. 0:08–0:14 She sets the bottle down. Side-front 35mm: she nutmegs him — ball on the ground, through his legs, he reacts late. Flirty eyebrow. 0:14–0:18 He laughs, beaten, into her. She picks her bottle up, proud little smile. 0:18–0:22 He buys/grabs the SAME @image3 bottle and offers it. Flirty, sincere. 0:22–0:26 She clinks her bottle to his. They hold eye contact. Caps twist. 0:26–0:30 HERO: two @image3 bottles on the wall, labels readable. Soft background: she sits; he glances over. On-screen English, clean sans-serif: AT HOME Hold to 30s. No other languages. Same Elara. Same Eric. Same bottle.
CHARACTER LOCK — HIGHEST PRIORITY (applies separately to @image1 and @image2): Each character in every shot is exactly the character in their own reference image. Photocopy facial identity from the matching tag. Preserve 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 the parent’s gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it — refer to them only as they/them. Do not beautify, slim, de-age, restyle hair, or morph any face into another. Never swap the two identities. Do not invent extra leads. Do not describe the faces — follow the images only. @image1 is the child. Photocopy @image1 exactly: same face, same hair, same skin, same body and the same clothes as in the photo, at their own age. This is the child in the photo, not a recast. Clothing from @image1 stays on them the whole film (visible at the neckline above the blanket). They hold nothing from the still — in this film they hold the stuffed toy. @image2 is the parent. Photocopy @image2 exactly: same face, same hair, and the same clothes and jewellery as in the photo. Never swap with @image1. Never recast @image2 as a child. PROP LOCK — @image3 is the stuffed toy only: the toy exactly as shown in @image3 — its shape, colours, material and face detail come only from @image3. Same shape, colour and knit design in every shot it appears. Ignore any stacking rings, cubes, rattles or teething rings around the bear in the still — those are not in the film. The picture book is a simple unmarked children’s picture book (no logos, no readable type). Both the picture book and the stuffed toy (@image3) are present from Scene 1 onward — nothing new appears later that was not already established. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. CAUSALITY LOCK: the only “magical” element is the soft glow coming from the picture book’s pages, established in Scene 1 as the sole light source for the wall shadows — nothing moves or glows without that shown cause. PACING: all motion stays calm, slow and gentle throughout — no rushed or sped-up moments anywhere in the video. Never open on a studio headshot, grey seamless, white cyclorama, or the attached photos as frame 0. First frame is already in the child’s bedroom, in-scene. 20 seconds. 9:16 vertical. Heartwarming cinematic 3D animated short film in a high-quality family-animation style — a cozy bedtime story moment. Premium animated-movie look, not live-action street photoreal. Expressive characters, realistic soft skin and hair on the locked faces, detailed facial expressions, physically accurate lighting, warm golden-to-cool-blue color palette, soft shadows, realistic fabric and blanket textures, smooth natural body movement, cinematic depth of field, subtle camera motion, high-end animated movie quality, polished rendering, emotionally wholesome storytelling. AUDIO (native, synced, diegetic only): a parent reading a picture book softly, a page turn, fabric and blanket, a small sleepy breath, a forehead kiss, a bedside lamp click. No BGM, no score, no songs, no on-screen text. SCENE 1 — 0–6s: @image2 sits on the edge of a child’s bed at night, reading a picture book aloud to @image1, who is tucked under the blanket hugging the stuffed toy (@image3). The book’s pages softly glow with a warm golden light. Cozy nightlight, moonlight through the window, soft shadows. Faces match their tags. The toy is the one in @image3. SCENE 2 — 6–12s: As @image2 turns a page, the glow from the book gently casts soft, slow-moving silhouette shapes (a bird, a tree, gentle waves) across the bedroom wall, as if the story is coming alive in light and shadow. @image1 watches, eyes wide with quiet wonder, holding the stuffed toy (@image3) close. SCENE 3 — 12–17s: @image1's eyes grow heavy and they slowly settle deeper into the pillow, still holding the stuffed toy (@image3). @image2 gently closes the book, the glow fading softly, and pulls the blanket up. SCENE 4 — 17–20s: @image2 leans in and gives a tender goodnight kiss on the forehead, then quietly reaches to turn off the bedside lamp. The room settles into soft blue moonlight as @image1 drifts off to sleep, peaceful and calm. CAMERA: Smooth cinematic camera movement, close-ups, medium shots, gentle push-ins, shallow depth of field, natural focus transitions. No text, no subtitles, no logos, no burned-in watermark, no BGM, no distorted anatomy, no extra fingers or limbs, no flickering, no sudden character or design changes, no studio grey still as frame 0, no extra toys from the still besides the @image3 toy, no bracelet as a scene prop. NEGATIVE: identity swap, adult recast of @image1, child recast of @image2, extra people, live-action street photoreal that drops the 3D family-film look, on-screen type, score/BGM.
Generate a live arena dance cam where a shy fan suddenly nails a pro dance routine.
The Ocean EggRecreate workflow