Made with OpenClips.AI

Face down a charging attacker and turn them to stone with a curse, ending on a close-up of their petrified face. Upload TWO photos: the witch, and the one who gets cursed. 15s.

Generate a live football broadcast where the dance cam finds you and you steal the show.

2 steps13512.1K

VERTICAL 9:16 10 seconds. Premium lipstick commercial. Photoreal. Rose-gold studio. @image1 = CATE. Photocopy FACE and hair only, exactly as in @image1. Wardrobe is elegant dusty-rose silk or satin, delicate jewelry, polished shoes. NEVER the clothes from @image1. @image2 = the lipstick. Photocopy THIS tube exactly as in @image2: its case, collar, cap, any printed brand name and the exact bullet shade. Never a different shade. Sitting on the giant lipstick (0–1.5s): they perch SIDE-SADDLE, elegant, knees together, one hand on the giant tube for balance, torso upright, looking to camera. They are NOT straddling it, NOT sitting on it like a horse, NOT a weird squat. Beats: 0.0–1.5s HERO: Cate side-saddle on the giant matching lipstick, giant 3D LIP letters behind, script “one swipe color”. Subtle head turn. Dolly-in. 1.5–3.0s MACRO of @image2 rotating with water droplets. Icons: Creamy Texture, Vivid Color. 3.0–4.5s Beauty portrait: the same outfit, they hold the real lipstick, smile. 4.5–6.0s Lip macro: one swipe of THIS exact shade from @image2. 6.0–8.0s Wink, chin on hand, same lip color. 8.0–10.0s Swatch + “one swipe color” + the three icons. Push in. Same Cate. Same bullet. English only. Never a studio headshot as frame 0.

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.

4 steps34835.1K

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.

3 steps

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.

MELT — LIQUID CHROME Cornered in a rain-slicked neon alley, @image1 melts into mirror-bright liquid chrome, pours away to escape, then re-solidifies into themselves. Plug in ANY avatar. Music only, loud. See the video step for the full prompt.

2 steps

Photoreal live-action commercial, shot on a full-frame cinema camera with fast prime lenses: shallow depth of field, warm low sun raking across the frame, dust drifting in the light, true pore texture and true fabric behaviour, the camera handheld-steady with only small settling movements. Not illustration, not a 3D render, not stylised. @image1 is the reference plate and is an absolute lock for BOTH the person and the product. The face, build, apparent age, hair, garment and jewellery are taken from the large portrait in its left zone exactly, with no drift and no reinterpretation in any shot. The product is the object in its right zone, reproduced exactly — same container, same label artwork and lettering, never redrawn, substituted or mirrored. Only that product exists; no second container appears at any point. @image2 is the storyboard and is followed exactly, panel for panel: six shots in that order, matching its framing, subject scale, pose and composition. One character is on camera throughout. A second person is heard off camera and is never seen, except for one hand. Shot 1 — the character holds the product up beside their face and speaks to the lens in a warm, confident tone: "Everyone asks about my morning routine." A brief pause. The smile drops, the eyes roll, and they shrug through the next line: "Nobody asks, but I already rented the studio." Shot 2 — slow motion, close on the product standing upright. A hand enters from the edge of frame and slides a leafy branch in behind it, clumsily and in plain view. The character speaks off camera: "That's my friend holding a plant. We wanted it to feel natural." Shot 3 — the character holds the product casually at chest height, the face of the label squared to the lens, and says brightly: "It's part of my daily routine," then the tone drops to reluctance as the eyes flick up and away toward the top right, "The kitchen isn't," and the eyes come back to the lens for the flat, deadpan finish, "I can't afford this kitchen." Shot 4 — tight on the face. The character attempts a hair flip into a strong breeze and a leaf blows against their mouth. They pick it away with quiet irritation and ask: "Do we need the wind machine?" The second voice answers off camera: "You paid for it." The character shrugs and answers immediately: "Keep it on." Shot 5 — close on the product standing upright, warm sunlight, soft shadows, clean composition. A hand enters from above and clumsily rotates it until the face of the label squares to the lens. The character speaks in voiceover: "One simple part of my day." Shot 6 — the product alone, centred on a clean empty ground, lit softly, settling and holding with only the faintest drift of light across it. The second voice says off camera: "Studio time's up." The character replies: "Get the plant." End immediately. Understated lifestyle music runs throughout with the dialogue clearly audible above it, and the music stops briefly for the final exchange. No on-screen captions or subtitles are burned into the frame.

3 steps030

Live-action UGC creator video. Fictional dramatization. Authentic social-media realism. @image1 is an absolute character and wardrobe lock — face, hair, body proportions and identity are taken from it exactly and never drift in any shot. It carries TWO looks: the everyday outfit in its upper row and the gift garment in its lower row, and both are reproduced exactly as they appear there. @image2 is the location lock — every interior in this video is that same apartment, with its furniture, wall colour, flooring, window placement and daylight direction unchanged throughout. @image3 is the opening frame — the video begins on it. @image4 is the storyboard — follow it exactly, matching shot order, framing, camera height and pose panel for panel. VISUAL CHARACTER Photorealistic live-action UGC. Authentic social-media creator aesthetic. Natural skin texture. Realistic clothing materials. Natural smartphone exposure. Subtle digital compression. Imperfect framing. Believable broadcast interface. It should feel like a genuine creator documenting a gift from one of their viewers rather than a professionally produced advertisement. STORY Selfie/webcam-style footage of the creator at their desk during a live broadcast. The broadcast interface sits over the footage. They read comments, smile and talk casually to viewers. A viewer sends a gift. A fictional username appears with a highlighted message: "Hope you like the surprise I sent you!" A gift notification appears beneath the message. The creator looks surprised. "Oh my God, you sent me something?" They laugh and thank the viewer. Two days later. Handheld smartphone footage at the apartment entrance. A delivery package is on the floor at the door. The creator picks it up and looks at the shipping label. They smile excitedly. They carry the package inside. The camera trails a step behind them at chest height, framed on their back and the box in their arms, so they stay visible in shot the whole way — this is not a first-person view and no one else walks ahead of them. They set the box down on the table. Natural handheld shake and imperfect framing. Close handheld phone footage. They cut the tape and open the cardboard box. Inside is the neatly folded garment wrapped in simple tissue paper. They react naturally: "No way…" They carefully lift the garment out of the box. They hold it up toward the camera, smiling, and look over the material and the details. Cut to a full-length bedroom mirror shot. The creator is now wearing the garment. The camera stays where it was set down, on a dresser. They turn slightly to show the fit and the way the fabric hangs. No sexualized posing. They adjust the garment at the neckline and smooth the fabric naturally. They look at themselves in the mirror and smile. They check the stitching and the material. "This is actually so nice." Handheld selfie shot. They hold the phone at arm's length while wearing the garment and give an honest excited reaction. "I genuinely didn't expect this." Quick cut back to the desk. They hold the garment up toward the camera while remembering the viewer's message. A small fictional comment overlay shows the same username. Selfie close-up. They look directly into the camera and say: "Thank you so much. I absolutely love it." They smile naturally. They set the phone down on the dresser. Full-room handheld-style composition. They give a final casual look toward the camera, adjust the garment once and laugh. The recording ends naturally. CAMERA Authentic creator-generated smartphone footage. A mix of webcam broadcast perspective, handheld selfie footage, rear-camera POV, delivery footage, close unboxing shots, a full-length mirror shot and a static phone-on-dresser shot. Natural handheld instability. Imperfect framing. Autofocus shifts. Occasional exposure changes. Realistic smartphone sharpening and compression. Natural motion blur. Slight lens distortion. Occasional camera repositioning. No cinematic gimbal shots. No polished commercial cinematography. No beauty-filter appearance. SOCIAL MEDIA INTERFACE The opening broadcast carries a believable fictional live-broadcast interface, vertical and full-screen: live indicator, viewer count, creator username and small profile image, a stack of short viewer comments along the lower left, a highlighted comment, a gift notification, simple controls along the bottom edge, and small hearts drifting up the right side. The interface stays flat and screen-locked, clearly part of the recording and clearly separate from the physical room. It never takes on perspective, never bends and never drifts off the screen plane. Use fictional platform branding and fictional usernames. Do not reproduce any real company's logo, wordmark, icon set or exact proprietary interface artwork. LIGHTING Natural apartment lighting. Soft daylight during the broadcast, natural daylight during the unboxing and the try-on. The ring light produces realistic soft illumination during the broadcast. No artificial cinematic rim lighting. No excessive HDR. No beauty lighting. PHYSICS Realistic package weight. Cardboard bends naturally. Tape tears realistically. Tissue paper folds naturally. The garment behaves like real fabric. Clothing responds naturally to movement. Hair responds naturally to body movement. All objects stay physically grounded. No floating objects. No impossible fabric movement. HUMAN PERFORMANCE Natural UGC personality. The creator speaks casually to their audience. Small pauses, smiles, laughter and spontaneous reactions. Their surprise at the gift feels genuine. They handle the package naturally. They look the garment over like a real customer. The try-on plays as an ordinary fashion review. The creator is clearly an adult. No exaggerated influencer acting. No theatrical reactions. No sexualized posing. AUDIO Authentic creator audio. Room ambience, laptop fan, keyboard sounds, notification sounds, the creator's voice, subtle broadcast audio compression, cardboard packaging sounds, tape ripping, tissue paper movement, clothing fabric sounds, apartment ambience. No cinematic music. No trailer effects. No artificial bass drops. WARDROBE They wear the everyday outfit from the upper row of @image1 for the broadcast, the gift, the delivery, carrying the box in, opening it and holding the garment up. They change into the gift garment from the lower row of @image1 only at the mirror shot, and wear it for the rest of the video. The gift garment is never seen on them before the mirror shot. CONTINUITY Exactly one person appears in this video, in every single shot. There is no second person, no bystander, no passer-by, no friend holding the camera and nobody else anywhere in the apartment at any point. Identical creator identity, face, hair and physical appearance across every shot. The same garment throughout — the one lifted out of the box is the one worn in the mirror. The same apartment, furniture, desk, bedroom, clothing rack and lighting environment throughout. The broadcast happens first; the package arrives two days later. The same fictional username and the same message appear in the broadcast and in the later callback. Each shot begins from the physical state the previous shot left behind. It should read as one continuous creator story: LIVE BROADCAST → GIFT → TWO DAYS LATER → DELIVERY → UNBOXING → TRY-ON → THANK YOU. End as authentic UGC rather than a polished commercial. Avoid: the gift garment worn before the mirror shot, a second person in frame, bystanders, a visible camera operator, any other figure in the apartment, CGI appearance, video-game aesthetics, plastic skin, beauty-filter faces, excessive HDR, perfect framing, cinematic camera movement, sexualized presentation, exaggerated body emphasis, nudity, transparent clothing, impossible fabric physics, fake-looking broadcast graphics, real celebrity likenesses, real usernames, official platform branding.

5 steps904.7K

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 their face or hair. No face changes, no identity drift. No other people share their face. @image1 is identity only — photocopy face, hair, eyes, skin and age. Do not wear the clothes or jewellery from the still. The still has no aqua park — wardrobe and setting come from this prompt. ASSET MAP: @image1 — the character. SINGLE SUBJECT: Only this one person appears. No other people in frame. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. STYLE: Vertical selfie-style UGC action-camera review, shot on iPhone front and back camera mix, natural daylight, handheld authentic energy, casual “showing a friend how I film everything” vibe, real skin tones, no filters. SETTING: A sunny outdoor aqua park — water slides, splash pools, palm-lined decks, bright open sky. Water spray and natural sunlight throughout. PRODUCT/OUTFIT (wardrobe/gear only, not identity): a lightweight quick-dry rash guard over swimwear. They hold a compact rugged action camera — small waterproof body, wide lens. No jewelry. Action and spoken dialogue (native sound, they speak these lines): 0.0-4.0s SHOT 1 — Front camera: They hold the action camera close to the lens, poolside spray drifting past, relaxed smile. They say: “Okay, I’ve been filming everything with this.” 4.0-8.0s SHOT 2 — Back camera: They walk along the aqua park deck toward a water slide, camera capturing stable forward motion despite the wet, busy surroundings. They say: “It stays smooth even when I’m moving.” 8.0-12.0s SHOT 3 — Neck-mounted POV: The camera now hangs from their neck, lens facing outward, capturing natural walking motion past pools and slides. They say: “I just wear it and film — even here.” 12.0-15.5s SHOT 4 — Medium-wide third-person: The camera is set on a poolside ledge. The action camera is visible neck-mounted on them as they walk toward frame, a light splash of water passing nearby. They say: “I don’t really think about it.” 15.5-18.5s SHOT 5 — Close-up back camera: They bring the camera close to the lens, showing buttons and lens detail, a few water droplets beading on the waterproof body. They say: “And it just shrugs off the water.” 18.5-22.0s SHOT 6 — Final front camera: They hold the camera beside their face, water slides and pool splashes behind them, calm confident smile. They say: “Yeah, I’m definitely bringing this everywhere I go.” Direct every second through 22.0s. Never freeze. Never cut to the attached still. Never open on a studio headshot. No on-screen text, no subtitles, no logos.

A product sits forgotten on a shop shelf. A mouth opens on its front and it quietly talks about being ignored, until a hand reaches in, lifts it off the shelf and finally uses it.

2 steps

Your dog goes on a one-take nighttime rampage through the house — knocking over a garbage can and scattering trash, tearing through the rooms — then stops and looks right into the camera. Upload your own dog and it stars, keeping its own breed.

Generate a live arena dance cam where you win a dance-off against a rival fan.

Your dog shows up on a motorbike to deliver a pizza — takes the cash, rides off… and leaves the box half-eaten. Upload your own dog and watch them run the scam.

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.

4 steps28629.7K

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.

6 steps721.3K

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.

2 steps

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.

2 steps

CHARACTER LOCK — HIGHEST PRIORITY (applies separately to @image1 and @image2): Each person in every shot is exactly the person 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 gender presentation exactly as shown. Do not beautify, slim, de-age, restyle hair, or morph the two faces into each other. Do not invent a third lead. Do not describe the faces — follow the images only. @image1 is the first person. @image2 is the second person. Never swap them. WARDROBE (scene clothes, not the stills): @image1 wears an ivory evening dress throughout. @image2 wears an elegant black outfit throughout. Hair stays as in each reference. Clothing and hair stay consistent for the whole 30 seconds. PRODUCT LOCK — @image3 is the jewelry piece. Photocopy it exactly as shown: same metal, stones, design and any box exactly as shown. Do not regenerate, restyle, recolor, or invent a different jewel. Whenever the piece is on screen it must match @image3. BRACELET WEARER: the piece from @image3 is worn only on @image1's wrist. Never on @image2. @image2 may open the box or offer it; @image1 receives it and wears it. His wrists stay bare. HANDS: anatomically correct, five fingers each, naturally proportioned, when they appear. During the dance they are not the subject. Never open on a studio headshot or the attached still as frame 0. First frame is already on the terrace, in-scene. 30 seconds. 9:16 vertical. Photorealistic luxury jewelry commercial. Elegant seaside terrace at blue hour: ocean view, wooden terrace, dinner table, premium dinnerware, flowers, subtle warm decorative candlelight as scene dressing only (not the product). Cool blue-hour ambient mixed with warm golden candlelight. Premium full-frame camera, shallow depth of field, natural bokeh. Realistic skin, ocean, wind, jewelry sparkle, food, glass reflections, fabric movement. AUDIO (native, synced): original elegant instrumental — soft piano and strings at the start, slightly more emotional during the dance, soft premium finish. Subtle realistic ocean waves, breeze, glass clinks, and the soft click of a jewelry box opening. End with a sophisticated voice-over, spoken clearly once: “Make every moment unforgettable.” 0-5s: Close-up of hands opening a small velvet box, revealing the jewelry piece exactly as @image3, glinting in warm candlelight. Reveal the romantic seaside dinner setup around it. 5-12s: @image1 and @image2 enjoy dinner, natural smiles and eye contact. @image2 presents the open box; the piece is fastened onto @image1's wrist. A short macro of the jewelry on her wrist is allowed here only — gemstone facets, metal shine. Faces match their tags. Not on his wrist. 12-20s DANCE — NO HERO HAND: After dinner they slowly dance beside the table. Camera is a medium or full two-shot of the couple: faces, bodies, dress, ocean behind them. Ocean breeze moves hair and dress. The bracelet stays on @image1's wrist as a small detail on her arm, never large, never in the middle of the frame, never a foreground blur occupying center. Do not cut to a wrist. Do not put any hand, palm, or bracelet close-up in the center of attention. His hands stay at her waist or in a normal dance hold, small in frame. 20-25s: Camera leaves the dance and moves to the jewelry piece on the dinner table (in or beside its open box) — the table product, not a wrist. The couple recedes / softly blurs. Do not fill the frame with a hand. 25-30s: Completely separate premium hero shot of the jewelry piece alone on the dinner table (in or beside its open box), ocean softly blurred behind it. Slow camera push-in, realistic light catching every facet. No logo, no brand marking. Voice-over lands here. No on-screen text, no subtitles, no watermark, no logos, no brand name in frame. No plastic skin, distorted hands, changed product design, unrealistic dancing, excessive lens flare, CGI look, or impossible camera moves. NEGATIVE: giant hand in the center during the dance, extreme wrist close-up during the dance, bracelet on @image2, studio grey headshot, swapped identities, extra third lead, different bracelet, navy plaid suit, white crew-neck tee, on-screen type.

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 their face or hair. No face changes, no identity drift. No other people share their face. @image1 is identity only — photocopy face, hair, eyes, skin and age. Do not wear the black studio top, gold snake necklace or gold bracelet from the still. The still has no gym set — wardrobe and setting come from this prompt. ASSET MAP: @image1 — the character. SINGLE SUBJECT: Only this one person appears. No other people in frame. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Hands never hold a phone, never hold a camera, never hold a speaker. Empty hands, laces, barbell, plates, or a water bottle only. NO PHONE — HIGHEST PRIORITY: There is no phone anywhere on this person. No phone in either hand, no phone at the ear, no phone in a selfie grip, no phone on a selfie stick, no phone in a pocket being pulled out. The camcorder is already rolling on a rack or mirror — they never film themselves with a device in hand. A small speaker can sit on a bench in the background, untouched. UNBRANDED SNEAKERS — HIGHEST PRIORITY: The training sneakers are plain, generic, unbranded. No logos, no wordmarks, no letters, no numbers, no swoosh, no stripes that read as a brand, no heel tabs with type, no recognizable designer marks. Same pair, clearly visible, every shot. CAMERA/LOOK: Authentic DV/16mm camcorder POV, already propped on a mirror or rack — never held as a phone. Shaky framing, imperfect focus, clumsy zooms, occasional face cutoffs, soft tape blur, subtle tape noise, bloomed gym lights, flickering exposure, muted contrast, realistic skin. Sweat gradually increases. Music plays throughout from the off-screen speaker. STYLE: Playful new-sneakers intro → rising tension before the squat PR → quiet focus during the lift → energetic triumphant ending. Fast handheld cuts with natural gym ambience. PRODUCT (wardrobe/gear only, not identity): a new pair of unbranded training sneakers, worn with their regular gym clothes, no jewelry. The sneakers are the featured product — kept clearly visible and consistent in every shot. SETTING: Early-evening gym with mirrors, squat rack, barbell, weight plates, a speaker on a bench (not in their hands), water bottle, soft overhead lighting. Any numbers or labels on the plates stay soft and unreadable — amounts are described in speech only, never as on-screen text. 30s / 12 CUTS: 1. 0-3s: Mirror shot. Empty hands. The character poses excitedly, lifting one foot to show off the new unbranded sneakers: “Okay guys, new kicks — check these out!” 2. 3-5.5s: Close on the sneaker details as they adjust the laces and flex their foot — blank tongue, blank sides, no marks: “So comfy, and the grip is amazing.” 3. 5.5-8s: Bodyweight squats and lunges to warm up. Hands free or on hips. Speaker already playing on the bench, not held: “Playlist’s locked in, let’s get moving.” 4. 8-10s: Quick playful dance between warmup reps, laughing, empty hands. Music only. 5. 10-12.5s: At the squat rack, they load a heavier plate onto the bar: “Okay... today’s the day I try a new squat PR.” 6. 12.5-14.5s: Macro shot of the unbranded sneakers planting firmly and gripping the gym floor as they set their stance, metal clink from the plates, no dialogue. 7. 14.5-17s: Nervous close-up, shaking out their legs, no phone: “Okay. Okay. Deep breath.” 8. 17-19.5s: Side angle as they unrack the bar onto their shoulders, feet set wide and stable in the sneakers. Music lowers; breathing becomes prominent. 9. 19.5-22.5s: They descend into a deep squat, then drive back up with visible effort, heels planted and stable throughout: “Come on—come on—” 10. 22.5-24.5s: Bar racks. They stand up, stunned, breathing heavily, legs slightly shaking. Empty hands after the rack. 11. 24.5-27s: Close reaction, huge grin, hand over mouth: “Wait—I actually did it!” 12. 27-30s: Sweaty look into the propped camcorder, glancing down at the sneakers, triumphant fist toward camera — no phone in frame: “New squat PR! Okay, best gym shoes ever. See you guys!” No on-screen text, no subtitles, no watermark, no logos.

Generate a live rally broadcast where a car showers you in dust at a gravel hairpin.

@image1 is the opening frame of the film and the single source of truth for everything in it: the round turntable with its brass rim, the three wedges it is divided into, the colour of each wedge, the three products standing on them, every small object beside them, and the collection bar at the top. Nothing is added, removed, redrawn, recoloured or relabelled. The turntable stays divided into exactly the three wedges shown in @image1 for the whole film — the same three seams meeting at the centre, the same three colours, never a fourth wedge. Each product keeps its exact shape, colours, cap and every mark it carries, as shown in @image1, and always stands upright on its wedge. One continuous 16-second take, 9:16 vertical, premium studio product film. THE POINT OF THE FILM: the turntable presents the three products one by one. Each product in turn is carried by the turning disc into a hero spot right in front of the lens, where it is seen big, sharp and upright at its own height, while the whole studio behind it takes on that product's colour. Then the disc carries it away and brings the next one. TWO THINGS MOVE, NEVER AT THE SAME TIME: 1. THE CAMERA moves only once, in the first three seconds, while the disc is still: from the high view of @image1 it glides down and forward to the HERO POSITION — low, at the height of the products, slightly above them, 50 mm look, facing the front edge of the disc, so the product standing on the front wedge fills the lower middle of the frame, big and sharp, with the studio wall behind it and the neighbouring products soft at the left and right edges. From the third second to the last frame the camera is locked in that hero position on a tripod and never moves again — no orbit, no pan, no drift, no zoom. The camera never travels around the disc. 2. THE DISC turns only from the third second on: it spins around its own centre at one slow, steady speed, a third of a turn every four seconds, clockwise as seen from above. It is the disc that carries the products past the lens: each wedge, with its upright product and its small objects, rides round from the right side of the frame into the hero spot at the front, holds the spotlight there, and rides on out to the left, while the next wedge comes in from the right. The seams visibly sweep past the front as the wedges change. Every product is always solid, upright and on its own wedge, never sliding, fading, doubling or lying down. THE COLOUR RULE: the seamless studio wall behind the turntable and the light in the studio take the colour of whichever product is in the hero spot — a soft, lighter tone of that product's own dominant colour on the wall, a deeper tone of it in the shadows — and flow smoothly to the next product's colour as the next one arrives. THE COLLECTION BAR: the bar at the top of @image1 is a fixed on-screen overlay. It stays exactly as in @image1 in every frame — same position, same size, the same three tiles in the same order — and nothing in it ever lights up, moves or changes. TIMELINE: [0–3 s] Opens on @image1. The disc is still. The camera glides down and forward in one smooth move into the hero position; the product on the front wedge grows big and sharp in the lower middle of the frame, and the wall behind it takes on its colour. [3–7 s] Camera locked. The disc starts turning: that first product rides slowly through the hero spot and out to the left, and the next product rides in from the right into the hero spot, big and sharp; the wall flows to its colour. [7–11 s] Camera locked. The disc keeps turning: the next product rides in from the right into the hero spot, big and sharp; the wall flows to its colour. [11–15 s] Camera locked. The disc keeps turning: the third product rides in from the right into the hero spot, big and sharp; the wall flows to its colour. [15–16 s] Camera locked, the disc still turning slowly; the film ends on that product in the hero spot. NOTES: one turntable divided into exactly three wedges, one take, no cuts. The camera moves only in the first three seconds and is locked after that; after that only the disc turns. Exactly three products, each always on its own wedge, never duplicated, swapped or merged. Nothing in the frame carries text. No people and no hands. AUDIO: a soft, minimal instrumental pulse under the whole take, the quiet smooth hum of the turning disc, and a faint airy whoosh each time the colour flows to a new product. No subtitles.

2 steps281.5K

Cup your hands, conjure a glowing orb — and watch a living black cat take shape from the magic and settle on your shoulder beside the raven. Upload your photo to become the sorceress. 15s.

Asset referencing: @image1 is the FIRST FRAME of this video. It defines the kitten chef and its markings, its oversized white toque and white apron, the pale oak counter, THE PRODUCT standing open on the left with its label facing the camera, the miniature cooking station on the right, the warm defocused kitchen behind, the lighting and the opening framing. ATTACHED IMAGE IS MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. THE PRODUCT IS FIXED — the single most important rule of this film: THE PRODUCT stands upright on the counter in the left of frame exactly where @image1 has it, and it NEVER MOVES. It never tips, never rotates, never slides, never leaves the counter, and nothing ever covers it. In every wide shot it is WHOLE AND UNCROPPED inside the frame, never cut off by the left edge, with its labelled front squarely towards the camera, sharp and fully readable, carrying exactly the words, layout, typefaces and colours @image1 gives it. No word on it changes or re-spells itself. No new lettering, logo, sticker or label appears anywhere else in the film. PAWS, NEVER HANDS — absolute, every frame: the kitten has plain rounded cat paws, no fingers and no thumbs. Every tool is gripped in the crease of a paw, exactly the way @image1 shows it held. No human hand and no finger appears at any moment. SCALE LOCK: THE PRODUCT is full human size and everything else on the counter is a real miniature at about one fifth of kitchen scale. The pan is smaller than the kitten's head, and the small coins lying on the wood stay coin-sized beside it. This contrast holds in every shot, including the finished plate. Summary: a miniature-cooking film in which a kitten chef makes a small stack of pancakes with THE PRODUCT on a doll-sized cooktop, with THE PRODUCT standing full-size beside it the whole time. FORMAT: timed multishot, 8 shots, HARD CUTS at 0:01.2, 0:02.6, 0:04.5, 0:06.6, 0:08.2, 0:10.6 and 0:13.0. No dissolves and no fades — every transition is a hard cut. The same kitten, the same counter, THE PRODUCT in the same place and the same warm light across every cut. Only three camera setups are used, and every shot is locked off — no pans, no dollies, no zooms, no handheld drift. The cuts do all the movement. SETUP A — wide frontal at counter height, the framing of @image1: the kitten centred from the chest up, the counter across the lower third, THE PRODUCT whole, uncropped and sharp in the left third of frame, the cooking station lower right. SETUP B — macro looking down at the small STAINLESS STEEL pan from above and slightly in front, the pan filling the frame. THE PRODUCT is outside this framing. SETUP C — the finished plate large in the foreground lower centre, the kitten behind it and slightly soft, and THE PRODUCT still standing in the left third, WHOLE AND UNCROPPED and in focus, its whole label inside the frame. Frame wide enough that none of the pack is cut off. Timeline: 0:00–0:01.2 — SHOT 1, SETUP A, the exact framing of @image1. The kitten tips the measure it is holding and a clearly visible fall of THE PRODUCT drops into the little white mixing bowl — a pale cascade of powder, a thick ribbon, a stream, whatever the product is. This fall is plainly visible for the whole shot. THE PRODUCT stands sharp on the left. 0:01.2–0:02.6 — SHOT 2, SETUP A. The kitten sets the measure down on the counter and works the slim wooden whisk in the bowl in quick small circles; the batter turns smooth and pale gold. THE PRODUCT has not moved. 0:02.6–0:04.5 — SHOT 3, SETUP B. A paw tips the mixing bowl and the batter pours into the hot buttered STAINLESS STEEL pan and spreads out into one clean round disc. The melted butter hisses around its edge and a thin curl of steam lifts. 0:04.5–0:06.6 — SHOT 4, SETUP B, a little closer, the same STAINLESS STEEL pan. Bubbles rise up through the batter and pop one after another across the surface; the rim sets, goes matte and lifts very slightly from the pan. Steam curls upward. 0:06.6–0:08.2 — SHOT 5, SETUP B, the same STAINLESS STEEL pan. A tiny steel spatula held in a paw slides under the pancake; the pancake flips over and lands flat with a soft slap, its deep golden side now facing up. 0:08.2–0:10.6 — SHOT 6, SETUP A. The kitten lifts three finished golden pancakes one onto the other on a coin-sized white plate on the counter in front, and lays a small pat of butter on top; the butter begins to slide and melt down the side of the stack. THE PRODUCT is whole and sharp on the left, label to camera. 0:10.6–0:13.0 — SHOT 7, SETUP C. A thin glossy ribbon of pale golden syrup pours slowly down over the stack and runs off its sides onto the plate. THE PRODUCT still stands in the left third, complete and uncropped and in focus, its entire label inside the frame. 0:13.0 to the end — SHOT 8, SETUP C, held completely still. The finished stack glistens, the butter still melting. The kitten raises one front paw, holds it up and looks straight into the camera. THE PRODUCT stands beside them, whole, uncropped, sharp and fully legible. Hold this shot, unchanged and unmoving, to the very last frame of the film, however long the film runs. Notes: the kitten's markings, its oversized white toque and its white apron stay exactly as @image1 has them for the whole film, with no drift between shots. The pan is the same stainless steel pan of @image1 in every shot and never becomes a dark non-stick pan. The warm amber LED strip and the softly defocused wooden kitchen stay behind the kitten in every wide shot. Nothing on the counter changes position between shots except the food being cooked and the tools the kitten picks up. No subtitles. No on-screen text of any kind. No logo anywhere other than THE PRODUCT's own label. Audio: a soft, light, playful melody kept low under everything, and close, present, dry foley on top of it — the fine dry whisper of the measure falling into the bowl, the quick tick of the whisk against the china, the batter hitting the hot pan and the butter hissing, the small wet pops of the bubbles, the soft slap of the flip, a light clink of the spatula on the plate, the slow thick drip of syrup, and the quiet room tone of a warm kitchen under it all to the last frame. No voices, no dialogue, no narration.

2 steps

Asset referencing: @image1 is the FIRST FRAME of this video. It defines THE PET dressed as a chef, its coat, markings, ears and eyes, its white toque and white apron, the pale oak counter, the black pan standing EMPTY AND DRY on the lit gas hob, the bowl of eggs, the warm defocused kitchen behind, the lighting and the framing. @image2 is the LAST FRAME of this video: the same scene, the same camera, the same animal — and the pan now holding clear turquoise seawater with tropical fish, a small golden sand island with one palm, a tiny wooden sailing boat and a little sea turtle swimming. ATTACHED IMAGES ARE MANDATORY AND FINAL: the two attached frames outrank every word below them. The film begins on @image1 and ends on @image2, and everything between them is the journey from one to the other. THE PAN STARTS EMPTY: at 0:00 the pan is completely empty, clean and dry — no butter, no oil, no fat, no water, nothing. Everything that ever appears in the pan arrives out of an eggshell, and nothing in the pan ever vanishes once it has arrived. THE SEA ONLY EVER GROWS, THEN STOPS: water enters the pan three times and only three times, once out of each shell. After the third shell is empty NO more water arrives, and the level stays exactly where it is for the rest of the film. THE ISLAND NEVER SINKS — it never shrinks, never flattens and is never submerged. From the moment it forms until the last frame it stands clear of the surface with its palm upright. COAT NOTE — written separately because this is what drifts: in every single second of this film, including the last, THE PET's coat keeps exactly the texture it has in @image1. If that coat is wiry, broken and scruffy it stays wiry, broken and scruffy and never becomes smooth, sleek or short-haired. Its muzzle keeps its length, its markings keep their places, its ears keep their shape. PAWS, NEVER HANDS — absolute, every frame: THE PET has its own plain animal paws, no fingers and no thumbs. The eggs and the shells are gripped in the crease of a paw. No human hand and no finger appears at any moment. ONE UNBROKEN TAKE: a single continuous shot from a locked-off camera in exactly the position @image1 gives it. No cuts, no dissolves, no fades, no pans, no zooms, no dollies, no handheld drift. The camera does not move once. THE MIRACLE — what this film is about: when a shell opens, what comes out of it is not egg. It is the sea, and the things that live in the sea. This happens as a plain physical event, photographed straight, with no sparkle, no glow and no magic effect of any kind. The pan simply holds an ocean. THE WATER STAYS IN THE PAN: it never rises over the rim, never spills onto the hob or the counter, and never floods the kitchen. The kitchen around it stays an ordinary dry kitchen. Timeline: 0:00–0:01.5 — Exactly the framing of @image1, the pan empty and dry. THE PET brings the egg down and taps it against the rim; a fine crack runs across the shell. 0:01.5–0:05.0 — The paw opens the shell over the empty pan. Instead of white, CLEAR TURQUOISE SEAWATER pours out in ONE single smooth unbroken stream — not in spurts, not in bursts — and the pan fills continuously and evenly to a shallow depth. The surface settles into moving ripples and the sunlit ripple-net plays across the dark metal below. Tiny bright tropical fish — orange, yellow, electric blue, some striped — come out with the water and begin to swim, each casting a small shadow on the bottom. 0:05.0–0:07.0 — The yolk falls out of the shell immediately after the water and drops into the middle of the pan exactly where a yolk would land. For a moment it IS the yolk — round, golden, sitting in the water — and only then does it settle and open out into A SMALL GOLDEN SAND ISLAND: a low round dome of warm sand standing clear of the surface, a darker wet rim where the water laps it, a tuft of green grass, and ONE small palm tree that unfurls its fronds as it rises. Rings of ripple run out to the edge of the pan. 0:07.0–0:09.0 — NOTHING ELSE HAPPENS IN THIS SHOT. No new water, no new object, no new egg. For two full seconds the only thing that moves is THE PET: it sets the empty shell down on the counter, its ears come up, and it leans in and tilts its head slowly to one side, looking at the island. This pause is deliberate and must not be filled with anything else. 0:09.0–0:10.5 — THE PET takes a second egg from the bowl with a paw and taps it on the rim. 0:10.5–0:13.0 — The second shell opens. More clear seawater pours in in one smooth stream and the level rises a little, and instead of a yolk A TINY WOODEN SAILING BOAT drops out — a simple little boat with a pale varnished hull, a short mast and a small white sail. It lands with a soft splash, rocks, rights itself and settles upright on the water beside the island. 0:13.0–0:14.5 — THE PET takes a THIRD egg from the bowl and taps it on the rim. 0:14.5–0:17.5 — The third shell opens. A last smooth pour of seawater comes out, and instead of a yolk A LITTLE SEA TURTLE slides out of the shell — a small green-brown turtle with a patterned shell, about the size of a walnut. It drops into the water, sinks a little, rights itself, spreads its front flippers and begins to swim, head up just breaking the surface, leaving a soft V of ripple behind it. This is the last water that ever enters the pan. 0:17.5–0:20.0 — No more water. The level is fixed and the island stands full with its palm upright. The turtle swims a slow arc past the island on one side while the boat drifts on the other, both leaving faint wakes; the fish dart underneath them; the palm sways very slightly; thin curls of steam rise where the water meets the hot rim. The film comes to rest on exactly the picture of @image2 and holds there, still, to the last frame. Notes: the pan, the hob and its lit flame, the counter, the bowl of eggs, the background kitchen and the light stay exactly as @image1 has them for the whole film. The sea, the fish, the island, the boat and the turtle are filmed as real physical things sitting inside a real pan, in the same light as the rest of the kitchen. Each egg is opened over the pan and its shell set down on the counter; the eggs in the bowl go from three to two to one to none. No subtitles. No on-screen text of any kind. No logo anywhere. Audio: no music. Generate only close, present, dry environmental and action sound — the small dry crack of each shell against the metal rim, the pour and splash of water running into the pan, the gentle lapping of a shallow lagoon, the soft plop of the island settling and the ripple that follows, the light splash and wooden creak of the boat landing and righting itself, the small wet slither and splash of the turtle sliding out and the soft paddle of its flippers, the faint hiss where water meets the hot rim, one distant gull far away, and the quiet room tone of a warm kitchen under it all to the last frame. No voices, no dialogue, no narration.

3 steps

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.

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.

3 steps

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.

2 steps

CHARACTER LOCK — HIGHEST PRIORITY (applies separately to @image1 and @image2): Each person in every shot is exactly the person in their own reference image. 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. No face changes, no identity drift between the two of them. ATTACHED IMAGES ARE MANDATORY AND FINAL: The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the first character. Photocopy face, hair, makeup, jewelry and the outfit they are wearing in @image1. @image2 — the second character. Photocopy face, hair, makeup, jewelry and the outfit they are wearing in @image2. SCENE vs STILL: @image1 and @image2 are the two people only. The colourful backstage room, clothing racks, vanity bottles, oval frame, extra figures, and the plain studio backdrop in the stills are NOT the set. The set is a real independent art gallery opening night. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. OTHER PEOPLE: background gallery guests and a photographer may appear but are never named, aged, or described by ethnicity/gender — only by role and action. They never share a face with @image1 or @image2. 10-second photorealistic live-event footage at an art gallery opening night. @image1 and @image2 walk together through the gallery space toward a wall of large abstract paintings, where a small cluster of guests and a photographer are gathered. Unbranded: no logos, no brand names, no visible labels, monograms, gallery names or readable signage anywhere in frame — walls show only abstract artwork, no text. The atmosphere feels like a real independent gallery opening: soft track lighting on the paintings, ambient chatter, occasional camera flashes, natural crowd movement in the background. 0–3 seconds: @image1 and @image2 walk side by side through the gallery, relaxed and elegant, natural synchronized movement, outfits moving naturally with each step. They occasionally glance at each other and smile. 3–5 seconds: They arrive near the artwork wall, stop, turn toward the photographer, and naturally adjust their poses. @image1 gives a playful, charming smile while @image2 poses confidently beside them. 5–8 seconds: A handheld camcorder approaches from among the guests, slightly shaky and imperfectly framed, like authentic behind-the-scenes footage. @image1 and @image2 notice the camera, look directly into the lens, smile, wave casually, and pose together. 8–10 seconds: The camera moves closer and slowly pans from @image1 to @image2. They lean slightly toward each other and start laughing naturally and playfully, genuine spontaneous expressions. End on both of them smiling toward the camera, abstract paintings visible but unreadable in the background. CAMERA / REALISM: real handheld camcorder, documentary event footage, slightly shaky operator movement, imperfect framing, subtle autofocus hunting, natural exposure shifts, realistic motion blur, slight lens breathing, authentic camera sensor noise, occasional guest flash photography, practical gallery lighting, realistic skin texture, natural hair movement, realistic fabric physics, candid event photography, no overly smooth gimbal movement. FACIAL PERFORMANCE: natural eye movement, subtle smiles, spontaneous laughter, genuine interaction between the two of them, no frozen expressions. Do not generate any duplicated people, extra limbs, distorted hands, artificial beauty filter, plastic skin, exaggerated body movement, cartoon/anime appearance, or slow-motion effect. No subtitles, no BGM, no watermark, no logos, no brand names or readable text anywhere. Overall feeling: an authentic candid recording from a real gallery-opening photographer, elegant but imperfect, spontaneous and believable. AUDIO: native gallery-opening ambience only — soft chatter, distant footsteps, occasional camera shutter/flash. No music, no voiceover, no lyrics.

A 30-second vertical UGC video of one person showing off their everyday bag, filmed the way a real creator films it: phone at arm’s length, natural daylight, handheld, no music and no captions. Six beats — they hold the bag up to the camera, turn it over, pack their laptop and everyday things into it, check how it sits in the mirror, walk out with it, then sit in a café and pack up again before signing off to the lens. The bag and the person both come from the photos you upload, and they stay identical from the first shot to the last.

3 steps19623.9K

Generate a glossy music video of two people strutting down a white corridor in giant puffy suits.

2 steps19520K