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.
Drag the clip sideways
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.
CHARACTER LOCK — HIGHEST PRIORITY (applies separately to @image1, @image2, @image3): 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 each parent’s gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age, restyle hair, or morph any face into another. Never swap the three 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. This is the child in the photo at their own age, not a recast, not a different kid. Clothing from @image1 stays on them the whole film. @image2 is the first parent (sleeping, then waking). Photocopy @image2 exactly: same face, same hair, same features. Never swap with @image3. @image3 is the second parent (pickup at the door). Photocopy @image3 exactly: same face, same hair, any facial hair, and the same clothes as in the photo. Never swap with @image2. Ignore any checkerboard behind @image3 — that is not part of the set. HANDS: always anatomically correct with five fingers each, naturally proportioned, including the child’s hands, in every shot they appear. Never open on a studio headshot, a garden still, a checkerboard, or the attached photos as frame 0. First frame is already in the bedroom, in-scene. 19 seconds. 9:16 vertical. Heartwarming cinematic 3D animated short film, high-quality family-animation style (premium animated-movie look, not live-action photoreal street). Expressive characters, realistic soft skin and hair on the locked faces, detailed facial expressions, physically accurate lighting, warm golden color palette, soft shadows, realistic cloth and blanket textures, smooth natural body movement, cinematic depth of field, subtle camera motion. AUDIO (native, synced): quiet morning household only — soft breathing, bed sheets, small feet on wood, a gentle door, a warm parent laugh. No BGM, no score, no songs, no on-screen text. SCENE 1 — 0–5s: Warm cozy bedroom. The child (@image1) sits behind the sleeping parent (@image2) on a comfortable bed and gently touches and plays with their hair. @image2 sleeps peacefully, head on a soft pillow. The child smiles mischievously, looking at them with curiosity. Warm golden morning sunlight through sheer curtains. Cozy wooden bed, bedside lamp, soft blankets. Cinematic close-ups, shallow depth of field, soft volumetric lighting. Faces match their tags. SCENE 2 — 5–9s: The child slowly crawls over the bed toward the edge. @image2 begins to wake, looking surprised as they realize the child is moving away, raising their head and reaching toward the child. The child continues crawling with an excited expression. Natural character movement. Faces still match @image1 and @image2. SCENE 3 — 9–13s: The child carefully climbs down from the bed and crawls across the bedroom floor toward the open doorway. Camera follows from behind at the child’s eye level. Warm wooden flooring, soft morning light, cozy home interior, cinematic tracking shot. The child is still @image1 in the same clothes. SCENE 4 — 13–16s: The child crawls through the hallway toward the entrance of the home, camera smoothly following from behind across the polished wooden floor. Tiny hands and knees move naturally. Emotional, playful family atmosphere. SCENE 5 — 16–19s: @image3 appears and picks up the child, smiling warmly and looking at them with affection. The child happily touches @image3's face and gives a gentle kiss on the cheek. Warm indoor lighting, emotional close-up, beautiful family moment. Both faces photocopy their tags. CAMERA: Smooth cinematic camera movement, close-ups, medium shots, low-angle child perspective, gentle tracking shots, 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 changes, no garden terrace from @image1, no checkerboard from @image3. NEGATIVE: age recast of @image1, swapped parents, third invented adult, studio grey still as frame 0, live-action street photoreal that drops the 3D family-film look, on-screen type.
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.
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.
FIRE — WALK THROUGH FLAMES @image1 walks calmly toward camera down a dark corridor as a wall of fire erupts and rolls behind them, unburned, ending on a hero close-up. Plug in ANY avatar. Music only, loud. See the video step for the full prompt.
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.
Generate a live arena dance cam where a shy fan suddenly nails a pro dance routine.
MMA — THE UNDERDOG. @image1 (Ria, the underdog) is dominated by @image2 (Brecka, the favorite) in an octagon cage, then lands a knockout counter and stands over her as the crowd erupts. Plug in ANY two avatars. Music only, loud. See the video step for the full prompt.
FIRE — SPARK TO FIRESTORM @image1 snaps a flame onto a fingertip, unleashes a swirling firestorm around them like a fire-bender, then gathers it into a glowing fireball. Plug in ANY avatar. Music only, loud. See the video step for the full prompt.
Newspaper Fashion EditorialRecreate workflow