Exactly 15 seconds, 16:9. THIS IS A VIDEO GAME, not live-action, not a real camera, not a real person on a real street. Look: modern open-world crime-game cinematics. Pre-rendered game engine. Stylized PBR, slight subsurface on skin but clearly CGI characters, game anti-aliasing, in-game depth of field, game lighting, no film grain, no documentary shake. Think third-person console gameplay trailer — never photoreal street photography. @image1 is the playable character's FACE only — lock that face on a game-character body. Do not turn them into a real-world pedestrian. @image2 is the jacket they wear as in-game armor/clothing. Fit that exact jacket onto the game body. Do not change the jacket design, cut, colours or graphics. Only the drape. Frame 1 is already in-game, third-person camera behind the character on a New York–like city street. Never a studio portrait. Never a real iPhone clip. Camera: locked third-person follow, over-the-shoulder, typical game camera boom, slight analog stick drift, no handheld documentary. City: game-NYC — yellow taxi models, sidewalks, steam vents, crowds as NPCs (no readable faces), traffic AI, shopfronts, skybox. Optional simple game HUD: tiny minimap corner, no brand names, no titles. 0-4s — already walking. Game camera behind. Jacket fully visible. NPC traffic. 4-8s — cross the street on a walk light. Camera holds third-person. Jacket reads front and back. 8-12s — turn onto a wider avenue. Game sun, specular on the leather. Same face, same jacket. 12-15s — keep walking. Half-orbit game camera, then settle behind. Abrupt end. Audio: game-mix city bed, footsteps, engines. No music, no subtitles, no logos, no real-world film tone. No on-screen text except a tiny generic minimap. Duration: exactly 15 seconds. Aspect ratio: 16:9.
Drag the clip sideways
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, 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 reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. Create a 30-second 16:9 2D hand-painted storybook animation — not photoreal, not live-action, not 3D CGI. Visible brush, soft painted edges, night-forest colour. The person in the attached reference is the only person. They are a fairy in this scene: same face as @image1, plus delicate translucent wings. OPENING — MANDATORY: Frame 1 is already a close-up of a hanging bell-shaped glowing flower on a mossy log, bare feet stepping into frame. Handheld-feeling but painted. Do not open on a studio portrait, grey backdrop, still headshot, or the attached image as a plate. Wardrobe, locked, gender-neutral: hand-knitted blue tunic, loose dark trousers, plain blue wool cap, small brown leather pouch on a strap, barefoot, translucent fairy wings. Fit these clothes and the wings to the attached person's body. No dress, no skirt, no gown. Hair stays as in the attached reference — mist can dampen it, do not recut or recolour it. Setting: enchanted night forest. Deep blue trees, mossy log, many hanging bell-shaped flowers on thin vines, floating pink purple and blue glow-lights, fog, tiny sparkles. One person only. 0-6s — hook: Bare feet on wet moss. A large pale-lilac bell flower hangs in the foreground, glowing softly. They step along the log toward it. Wings flutter. 6-14s — approach: They walk the log in the knitted tunic, trousers and cap, pouch at their side. Painted bokeh lights behind. Slow move toward the hanging flower. 14-22s — the key: They crouch, open the pouch, take out a small ornate golden key. Look at the flower. Reach toward it. 22-30s — glow: They touch the flower with the key. The bell lights from inside, sways, brighter. Hold on the glowing flower as they watch. No on-screen text. Cut. Diegetic forest night only: soft wing flutter, faint chime when the flower lights, breeze. No music, no speech, no subtitles, no logos, no watermark. Duration: exactly 30 seconds. Aspect ratio: 16:9.
[PROJECT TYPE] Text-to-video. 30-second cinematic action sequence. High-altitude mountain adventure. [GLOBAL SETTING] Vast snow-covered alpine landscape. Mix of massive slopes, rocky outcrops, sparse alpine vegetation. Golden hour or dramatic daylight lighting. Clear sky, distant peaks. Cold, pristine atmosphere. [ACTION & PROGRESSION] 00-06s: Drone POV — Wide establishing shot of vehicle launching down massive slope. Fast acceleration, spray, power. 06-12s: Rider POV — Close follow, technical driving through tight terrain. Speed + precision. Spray catches light. 12-18s: Ground-level tracking — Low angle, vehicle charging past camera. Terrain detail visible. 18-24s: Aerial arc — High drone swooping over open white landscape, vehicle small against scale. 24-30s: Final descent — Silhouette against sunset sky, vehicle carving final turn, momentum and mastery. [TECHNICAL] Seamless transitions between camera angles. No cuts, flowing motion. Cinematic color grade. Snow/dust spray glistens. Clean, athletic, powerful energy.
Exactly 15 seconds, 16:9. ONE CONTINUOUS UNBROKEN TAKE. Live-action fantasy comedy, 35mm grain, bright noon daylight, saturated but natural skin. Same world palette as before: floating grass islands, red-and-white mushrooms, green pipes, gold coins, waterfalls, pink-roofed castle, red-and-white curb, blue sky with big clouds. @image1 is GREEN — lock this exact face 100%. Dark bob, green cap, denim overalls, cream top, white gloves, brown boots. Green kart. @image2 is RED — lock this exact face 100%. Light brown hair, red cap, denim overalls, cream top, white gloves, brown boots. Red kart. Do not swap faces. Do not open on a studio portrait; frame 1 is already racing. Prince at the finish line, slightly to one side of the checkered stripe: blond curls, gold crown, pink costume, arms open. Directly BEHIND him, not beside: Bront the teal-scale copper-shell horned creature, white crest, brown eyes. Bront is clearly behind the prince. 0-2s — Already racing, side by side. RED shouts, exact lip sync: "My prince!" GREEN: "No! MY prince!" 2-6s — GREEN steers hard into RED and SHOVES her completely off the track. RED's red kart leaves the road entirely — over the curb, off the floating island, falling away. GREEN stays on the racing line and keeps going. This is a full knockout, not a bump. 6-10s — GREEN alone, full speed, drifts the last bend, crosses the finish line still in the green kart. Prince is ahead with arms open. She does NOT stop in front of him. She drives past him, around his left side, and brakes behind him next to Bront. 10-13s — GREEN jumps out, ignores the prince, runs around him and throws her arms around Bront. Tight hug. Bront grins. Prince turns, confused. 13-15s — Prince drops to his knees and sobs, kicking. GREEN keeps hugging Bront. RED is gone off-track. Abrupt end. One uninterrupted shot. No cuts. Audio: engines, a hard kart impact, wind, two spoken lines, hug, prince sobbing. No music, no subtitles, no logos. No on-screen text. Duration: exactly 15 seconds. Aspect ratio: 16:9.
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, 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 reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. The avatar reference shows their face and build, not this outfit — put the outfit on them. Fit each garment to the character's body naturally without altering its design, cut, proportions or colour — the garment is fixed, only its drape adapts. VISUAL CONSISTENCY: the person in the attached reference, frost-dusted face, tattered pale-blue and silver samurai armor, ice katana — adapt only pose, lighting, and surroundings. Do not alter their facial structure. STYLE: Highly realistic dark fantasy, brutal close-quarters combat, subterranean glacial cavern, falling ice crystals, cinematic wide scale, dramatic chiaroscuro lighting, deep atmospheric depth. 0–5 SEC — DESCENT INTO THE ABYSS Ice-lit subterranean ruins → obsidian-blue frost-demons scale massive frozen pillars → ice crystals fall heavily → camera tracks downward rapidly → the fighter plunges into the abyss, hair whipping, pale armor glowing in the ambient cold → rapid cinematic tracking dive directly toward the demonic swarm. 5–10 SEC — IMPACT The fighter crashes onto a shattered frozen platform → cracked ice, frost shards, and snow explode outward → fierce shockwave scatters the nearest demons → camera circles rapidly as they rise from the crater → katana drawn, gleaming with reflected glacier light → they dash forward as demons lunge from the shadows. 10–18 SEC — THROUGH THE HORDE The fighter slices through the horde with fluid, brutal precision → katana severs frost-black limbs, spraying glittering ice-blood → sparks and ice shards burst from sword clashes → aggressive tracking and rapid whip pans follow each strike → brief slow-mo captures flying shards, falling snow, and their unyielding expression → they push deeper without losing momentum. 18–24 SEC — THE PLUNGING STRIKE The fighter leaps off a crumbling ice pillar high into the cavernous airspace → camera follows vertically through cold shimmer → a towering ice beast emerges from the frozen lake below → they grip their katana with both hands, cyan energy building rapidly along the blade → they dive downward into a devastating plunging strike. 24–27 SEC — FROST ERUPTION Katana pierces the ice beast's chest → massive burst of cyan and silver energy erupts → shockwaves shatter surrounding ice pillars → lesser demons disintegrate into snow → ice splashes, shattered frost, and glowing shards fill the frame → camera pulls rapidly backward and upward revealing the immense destruction. 27–30 SEC — VICTORIOUS ENDING Remaining demons crumble to dust → smoke and snow drift slowly → the fighter stands at the center of the shattered platform → hair and tattered garments move naturally in the rising icy winds → frost-stained katana rests at their side → camera pulls back into a final wide aerial shot → they stand alone and victorious amidst the glowing rivers of ice. CAMERA & MOTION: Rapid cinematic movement, rapid whip pans for impacts, smooth aerial tracking, realistic motion blur, natural camera inertia, no random teleportation. PHYSICS & VFX: Cold shimmer, realistic snow and cloth interaction, believable ice-blood, grounded creature movement, controlled energy blasts, large-scale shockwaves integrated into the environment. QUALITY: Photographic skin, detailed weathered metal, glowing glacier lighting, cinematic depth of field, high dynamic range, epic fantasy realism. NEGATIVE: No cartoon, no anime style, no plastic armor, no modern objects, no inconsistent character design, no deformed anatomy, no extra limbs, no random costume changes, no text, no watermark.
Create a 15-second 9:16 ultra-realistic cinematic video of a three-tier matchstick cake. a three-tier matchstick cake is the enormous three-tier celebration cake from the storyboard, sculpted entirely from wooden matchsticks, red match heads as frosting. Same three-tier cake every frame. Life-sized on a white table, dark studio, 85mm, shallow depth of field. OPENING: Frame 1 is already the cake on the table, sharp. No grey still. 0–3s: a three-tier matchstick cake stands still. Soft haze. Two hands enter with a match, strike it. Realistic match-strike sound. 3–8s: The lit match touches the bottom tier. Fire spreads naturally across the matchsticks. Crackling wood, popping match heads. Cake stays standing. 8–13s: Flames climb all three tiers. Orange glow from inside, sparks, smoke. No explosion. 13–15s: Fully charred black 3-tier silhouette still standing. Embers. End hold. AUDIO required: match strike, crackle, pops, flame. No voiceover. No on-screen text. Hands only, no faces. Duration 15s. Aspect 9:16.
Animate this ink painting. 15 seconds, one continuous shot, no cuts, the camera never moves. Real-time speed, no slow motion. @image1 is the first frame - figure, garment, pose and style are already set. Continue directly from it. She is already dancing and never stops - turning, arms sweeping wide, hair whipping, the painted fabric flaring. Fast and fluid throughout. THE GARMENT KEEPS ITS OWN COLOUR. It is never recoloured or repainted. Ink follows her. Brushstroke ribbons fly off her sleeves and hem in wide arcs and dissolve. Wet spatter flicks onto the paper and pools where her feet land. Colour builds in three ways. First in the air: the trailing ribbons turn crimson, then gold, then violet and blue. Then on the fabric: blooms of those same colours soak into the garment in irregular patches, bleeding at the edges, never covering it evenly. Finally downward: in the last seconds long coloured drips run from the hem onto the paper. By five seconds the paper is already stained with layers of brushwork. Hand-painted throughout - wet ink, soft bleeding edges, visible paper grain. Never photoreal, never 3D. Audio: soft slow instrumental music, a single stringed instrument. No voices.
Ink Sleeve DanceRecreate workflow