Watch a clip, steal the recipe, make your own — free. Every link is remixable in one tap.
NIGHTMARE — The Falling Dream @image1's floor gives way and they plunge through an endless dark void, tumbling past drifting doors and grasping shadow hands, then slam awake in bed gasping. One continuous dynamic cinematic nightmare, music only, loud. Plug in ANY avatar.
DISSOLVE — Sand & Reform @image1 dissolves into a swirling ribbon of glowing golden sand that sweeps sideways through the air and knits back together a few steps away, reforming in a new pose — a clean, magical teleport-style dissolve. Cinematic 15s, no ash, no gore. Swap in ANY avatar.
SANDSTORM SUMMON — Desert Vortex @image1 summons a colossal sandstorm in the desert — the camera sweeps 180° from their face around to behind them, revealing a towering vortex rising far ahead, which they conjure and then collapse with a clench of the fist. Epic, controlled, cinematic 15s. Swap in ANY avatar.
FLOWER MORPH — Petal Explosion Reveal @image1 claps and bursts into a huge cloud of colourful petals that fill the frame — then the petals rush back and reassemble them in a stunning floral gown for a confident final pose. Punchy, magical, cinematic 15s. Swap in ANY avatar.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character (the driver). Photocopy @image1 for face, hair, skin, identity, and the wardrobe on the still (burgundy long-sleeve V-neck satin dress, layered gold chain with a gold snake pendant, thin gold bangle). Do not restyle hair. Do not invent a different dress or jewellery. Ignore any beige pad around the still — that pad is not a set. If any other person appears (the tactical soldier), they are never named, aged or gendered in the text — described only by their role and what they do. Only @image1's face is locked as an identity. Extra people in this story are beats, not copies of @image1. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Create a cinematic photorealistic action-thriller sequence set in a modern downtown city at night, surrounded by tall skyscrapers, told as one clear cause-and-effect chain — not disconnected spectacle shots. SHOT 1 (0-4s): Close-up on the character driving, exactly as in @image1, one hand on the wheel, the other resting protectively on a small sealed metal case on the passenger seat. They glance anxiously into the rearview mirror, already uneasy — establishing that they are carrying something valuable and already suspect they’re being followed. Realistic skin texture, dramatic night lighting, tense expression. SHOT 2 (4-7s): Cut to a high aerial drone shot flying between the skyscrapers, following the character’s car through the busy night street below, then pulling back to reveal a heavily armored black tactical vehicle several cars behind, closing the distance with clear intent. The camera moves rapidly forward with cinematic motion blur, establishing that this vehicle is specifically hunting the character’s car. SHOT 3 (7-11s): Cut to a POV shot from inside the character’s car, focused on the rearview mirror. In the reflection, the tactical vehicle pulls up alongside, a tactical soldier visible inside, gesturing for them to stop. The character grips the case tighter and accelerates instead, confirming they won’t give it up. Keep the mirror reflection sharply detailed while the city blurs past. SHOT 4 (11-15s): Fast-paced aerial and street-level shots of the chase through downtown — the character weaving through traffic to shake the tactical vehicle, which rams a parked delivery truck while trying to cut them off, spilling cargo and forcing its own path toward a roadside fuel tanker idling at a loading zone. Realistic smoke, dust, and cinematic atmosphere. SHOT 5 (15-20s): The tactical vehicle, still trying to close the gap, clips the fuel tanker at speed. A powerful explosion erupts behind the character’s car — a bright orange fireball, thick gray smoke, sparks and debris — visibly caused by that collision, not appearing at random. The character’s car speeds clear of the blast radius; a final shot through the rearview mirror shows the fireball and stalled tactical vehicle receding into the distance as the character exhales, adrenaline still high but visibly safe. STYLE: Ultra-realistic physics, realistic vehicle movement, cinematic camera transitions, natural night lighting, shallow depth of field, high detail, realistic motion blur, blockbuster Hollywood action-movie cinematography, photorealistic, HDR, anamorphic lens, dramatic color grading, intense suspenseful atmosphere. AUDIO (native, synced, no BGM, no voiceover, no narration): engine roar and tire screech, wind rushing past the drone shots, the tactical vehicle’s engine snarling alongside, the crash into the truck, the tanker’s explosion with a deep boom and scattering debris, and the character’s tense breathing settling into relief in the final shot. No on-screen text, no subtitles, no watermark, no logos. Vertical 9:16. Exactly 20 seconds.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character. Photocopy @image1 for face, hair, skin, identity, and the wardrobe exactly as worn on the still. Add a simple day bag they carry. Do not restyle hair. Do not invent different clothing. Ignore any beige pad around the still — that pad is not a set. If any other person appears (the security guard, the HR associate, the department head), they are never named, aged or gendered in the text — described only by their role and what they do. Only @image1's face is locked as an identity. Extra people in this story are beats, not copies of @image1. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. SETTING & CAMERA: One continuous modern office: entrance → security desk → badge gate → glass corridor → open office → whiteboard aisle → the character’s own desk. Morning light, hard floors, realistic office furniture. A white PTZ security camera is already mounted above/right of their desk and must remain there throughout. 0-25.5s: continuous third-person tracking, usually 1.5m behind the character’s shoulder. Realistic follow-lag, whip-pans to threats, no hidden cuts or teleportation. 25.5s: hard cut to a fixed frontal medium close-up showing the character, their desk, and the PTZ camera. HUD: a simple colour-based detection indicator top-center (green → yellow → red, no numeric readout). Minimap bottom-left; STAMINA/COMPOSURE top-left; SPRINT/CROUCH/INTERACT/SLIDE bottom-right icons only, no numbers. Opening text: “LATE — 12 MIN” / “OBJECTIVE: REACH YOUR DESK UNDETECTED.” 0-7s — SECURITY GUARD: The character sprints through the entrance with their bag. The guard notices them. They hide behind a large planter instead of confronting the guard, dropping low as the guard approaches with a radio. The indicator flares toward red. When the guard looks away, they quietly slip out, badge through the gate, and continue. The guard notices the closing gate but does not chase. The indicator eases back toward green. 7-13s — HR CART: HR pushes a tall cart loaded with folders toward the character. They accidentally brush the glass, then quickly crouch behind the cart and move with it, staying hidden as HR checks both sides. They circle behind the cart when HR looks away, then break cover and run once the corridor is clear. HR never clearly sees them. The indicator peaks red, then drops back toward green. 13-18s — DEPARTMENT HEAD DISCOVERY: The department head appears at a T-junction and notices the character’s reflection through the glass. They turn toward the character. A solid red “!” flashes exactly twice above the department head. Only afterward, the indicator turns full red: “ALERT.” The department head calls, “Hey! Hold on!” The character turns and says, “Oh, crap!” The department head follows their route. 18-23.5s — WHITEBOARD ESCAPE: The character races through the open-office aisle, grabs a wheeled whiteboard, and pulls it diagonally across the department head’s path. The department head brakes before hitting it and immediately circles around. The character squeezes through the remaining gap between the whiteboard and a desk using a low side-slide, keeping their bag tight to their body, then immediately gets up and runs. The department head stays behind them. 23.5-25.5s — FALSE SUCCESS: The character reaches their desk, drops into the chair, puts the bag underneath, and starts typing while catching their breath. The department head searches the rear aisle but cannot see them. The indicator falls to green. Green “MISSION COMPLETE” appears. The character smiles with relief. 25.5-30s — CCTV TWIST: At 26.2s, the pre-installed PTZ camera physically whirs, pans and tilts toward the character, then its red indicator illuminates. They slowly look up toward it and freeze. Remove “MISSION COMPLETE.” Show “CCTV DETECTED,” followed by red “MISSION FAILED.” They mutter, “You’ve got to be kidding me.” Hold their defeated expression, the red-lit camera, and the failure HUD until the end. PHYSICS & RESTRICTIONS: real footsteps, shoe friction, breathing, bag movement, glass reflections, radio, badge gate, cart/whiteboard/chair wheels, keyboard sounds, and PTZ motor. No teleportation, clipping, frictionless movement, clones, identity changes, distorted hands, plastic skin, impossible reflections, or furniture hitting people. Only the department head pursues the character. The guard and HR associate never chase. The CCTV camera must physically turn; the HUD must not replace the physical camera action. AUDIO (native, synced, no BGM, no voiceover, no narration besides the spoken lines): hard-floor footsteps, bag fabric, radio chatter, badge-gate beep, cart wheels, glass tap, the department head’s “Hey! Hold on!”, the character’s “Oh, crap!”, whiteboard wheels, keyboard keys, PTZ motor whir, then “You’ve got to be kidding me.” No subtitles, no BGM, no extra logos. Vertical 9:16. Exactly 30 seconds.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character (the florist). @image1 is face, hair, skin and identity only. Wardrobe is florist-shop work clothes from the scene (simple work shirt or apron) — do not copy an olive-green quarter-zip, a white crew t-shirt, or the lounge interior from the still. SINGLE SUBJECT — HIGHEST PRIORITY: Only this one person appears throughout. No other people or hands ever enter the frame. CAUSALITY LOCK: The open shop door is already visible and slightly ajar from shot 1, so the gust of wind that swings it open further and scatters the stems has a clear, visible source. Nothing moves without a shown cause. PROP CONTINUITY: One partly-finished bouquet, one pair of shears, and one held stem all exist from shot 1. The loose stems and petals that scatter in shot 2 come only from the bouquet already established. Nothing new appears later. PACING: All human motion in this scene is unhurried and deliberate — no rushed, sped-up or frantic movement at any point, including while picking scattered items back up. Allow brief, natural pauses between actions. The gust of wind itself is a quick natural event, but the character’s own movements stay calm and controlled throughout, even during the recovery. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Tell the following story in exactly 3 shots, same character throughout, where shot 2 is a genuinely different event from shot 1 — not a bigger version of the same action. Clear visual beginning, twist and ending — never ambiguous or faded-out. STORY: The character is already at the counter, the shop door slightly ajar behind them, holding a single flower stem firmly in one hand at a marked length. They position the open shears around the stem, pause a beat, then close the blades slowly and deliberately, cutting cleanly through it in one visible, unhurried snip — the cut stem clearly falling free into their palm. They place it into the bouquet with calm, practiced care. A sudden gust swings the door open wider, and it visibly scatters several loose stems and petals off the counter onto the floor, knocking the bouquet slightly off-balance in its vase — a clear, different event from the calm cutting before. The character sets down the shears, kneels, and picks the scattered stems and petals back up one at a time, unhurried, straightening each one before returning it to the arrangement. They right the vase, step back, and take a slow, satisfied look at the finished bouquet. STYLE: Warm, grounded flower-shop realism, soft natural light from the doorway, shallow depth of field, camera close and steady on hands and face throughout, holding on the single deliberate cut in shot 1, a brief quick beat for the gust itself, then settling into an unhurried, steady pace for the calm recovery. Vertical 9:16. Continuous real motion, no freeze-frame, no cutaways, no time-lapse or sped-up motion anywhere. No on-screen text, no subtitles, no watermark, no title card. AUDIO (native, synced, no BGM, no voiceover, no narration): quiet shop ambience, the single clean snip of the shears through the stem, a pause, a sudden gust and the door swinging with a creak, stems and petals scattering onto the counter and floor, then calm, unhurried gathering sounds one stem at a time, the door clicking shut, and a slow, satisfied exhale. SHOT 1 (0-8s): Open already inside the work — no static establishing beat. Character holding a single stem firmly in one hand, positioning the shears around it, and cutting through it in one clear, deliberate, unhurried snip, then placing it into the bouquet. The stem must be visibly present and visibly cut, not an empty gesture. SHOT 2 (8-16s): The turn — a different event, not a repeat. A gust swings the door open wider, scattering stems and petals off the counter and onto the floor, knocking the bouquet off-balance. This is the one quick natural moment in the scene. SHOT 3 (16-24s): The resolution. Calm, unhurried gathering — the character kneels and picks up each scattered stem one at a time, straightens it, and returns it to the arrangement, then rights the vase. They step back and take a slow, satisfied look at the finished bouquet. A clear, decisive ending, not a fade-out.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character (the barista). @image1 is face, hair, skin and identity only. Wardrobe is café barista clothes from the scene (simple dark shirt, apron) — do not copy a corduroy jacket, olive t-shirt, gold bar pendant, or a studio checkerboard/beige seamless from the still. SINGLE SUBJECT — HIGHEST PRIORITY: Only this one person appears throughout. No other people, hands, carts or props ever enter or move in the frame except the two cups named below. CAUSALITY LOCK: Nothing in this scene moves unless this character’s own hand is directly throwing, tossing or catching it in that same continuous motion. No object drifts, rolls, slides or moves on its own at any point. PROP CONTINUITY: Exactly two empty ceramic cups exist in this scene, both already on the counter in shot 1. No other cup or prop appears later. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Tell the following story in exactly 3 shots, same character throughout, with a real physical risk and a real, visible recovery. Clear visual beginning, twist and ending — never ambiguous or faded-out. STORY: The character is already mid-flair behind the counter, one empty cup in hand, tossing it up in a smooth arc and catching it behind their back without looking — clearly practiced, confident, having fun with it. Feeling good, they pick up a second empty cup from the counter with their free hand and toss both cups into the air at once, raising their own stakes. One cup spins cleanly — but the other tumbles off-axis mid-air, wobbling badly, about to be missed. Their eyes widen, focus sharpens instantly, and in one fast, decisive motion they dart both hands out, catching the wobbling cup at the last possible moment in one hand while the other cup lands cleanly in their other palm at the same time. They straighten up, both cups secured, and break into a proud, relieved grin. STYLE: Energetic handheld café realism, bright natural window light mixed with warm counter lighting, shallow depth of field, camera tracking the tossed cups closely, a quick snap-focus on the wobbling cup at the moment of risk, settling into a steadier frame for the triumphant finish. Vertical 9:16. Continuous real motion, no freeze-frame, no cutaways. No on-screen text, no subtitles, no watermark, no title card. AUDIO (native, synced, no BGM, no voiceover, no narration): café ambience, the soft whoosh of the first toss and catch, a confident exhale, the second double-toss, a sharp intake of breath as the cup wobbles off-axis, a fast decisive catch sound in both hands at once, then a relieved laugh. SHOT 1 (0-6s): Open already inside the flair — no static establishing beat. Character tossing one cup up and catching it behind their back, confident and fluid, clearly a practiced skill. SHOT 2 (6-11s): The turn. They pick up the second cup and toss both at once — a bigger, riskier move. One cup wobbles badly off-axis mid-air, visibly about to be missed. Their expression sharpens with focus. SHOT 3 (11-16s): The resolution. In one fast, continuous motion, both cups are caught — the wobbling one saved at the last instant, the other landing clean at the same moment. They straighten up with a proud, relieved grin. A clear, decisive ending, not a fade-out.
30 seconds, 16:9. Travel vlog. Handheld. Photoreal. ONE continuous take, no hard cuts. LANA LOCK: @image1 is Lana — photocopy their FACE, hair and features exactly as in @image1, adult. IGNORE whatever clothes are in @image1. OUTFIT from the film: white crop top, loose blue jeans, brown shoulder bag. Same look the whole clip. Modern commercial airplane cabin. Background passengers ok. 0–7s Lana walks the aisle. Medium close-up tracking from slightly in front and to the side. Hair moves. Overhead bins, seats, windows visible. 7–13s Lana reaches their seat, stops. Camera pans as they put the brown bag under the seat in front. Hands interact with bag, seat, floor. 13–19s They stand, casually adjust their hair with one hand. Subtle tilt and gentle push-in. Relaxed. 19–26s They turn and sit. Realistic body, clothing folds, hair, weight. Passengers still moving slightly. 26–30s Lana settles, looks at the window, then briefly at the camera, relaxed vlog look. HOLD. AUDIO: cabin rumble, quiet. No speech. No songs. NEGATIVE: the clothes from @image1, overlay type, extra hero faces, 9:16, mustard sweater.
15 seconds, 1:1. Photoreal night Shibuya. Hard cuts. Cinematic. ELARA LOCK: @image1 is Elara on the STREET — photocopy their FACE, hair and features exactly as in @image1. IGNORE the background of @image1. STREET OUTFIT: charcoal blazer, white shirt, dark mini skirt, black pumps. Same person in the crowd shots. POSTER LOCK: @image2 is the ONLY billboard ad — Elara exactly as pictured in @image2. Photocopy that poster onto the giant screen. Do not redesign. Night city, crowds glance and point. Elara walks, confused, looks UP. 0.00–1.70 High angle sidewalk, Elara walking. HARD CUT. 1.70–3.30 Side follow. Passerby turns, someone points. HARD CUT. 3.30–4.90 Front face CU, slight confusion. HARD CUT. 4.90–6.60 High oblique, more looks. HARD CUT. 6.60–8.50 Follow. Elara checks left/right, then looks up. HARD CUT. 8.50–10.80 Face closer. Gaze UP. HARD CUT. 10.80–15.00 Building-wall digital billboard showing @image2. FIRST the full @image2 poster fills the screen. Camera PUSHES IN continuously to a CLOSE-UP of their made-up face. Then the person ON THE POSTER winks once and freezes. HOLD. AUDIO: city, cinematic BGM. No speech. NEGATIVE: character-sheet text, overlay captions, the @image1 background, extra hero faces.
@image1 (the room untidy and dirty) is the opening frame and @image2 (the same room clean and tidy) is the closing frame. Together they fix the space, the fixtures, the furniture, the lighting and the framing for the whole film; nothing is redesigned, re-lit, re-proportioned or rebuilt at any point, and every change between the two is one that tidying and cleaning could actually produce. One continuous locked-off timelapse, no cuts. The camera holds the opening framing for the whole film and breathes only with the faintest drift, arriving on the closing framing exactly. Time runs fast: hands and cleaning tools sweep in and out of frame in short bursts of motion blur, never settling long enough to resolve, while the room itself stays sharp between passes. The film opens on the room as it is, held just long enough to read the clutter and the dulled, grubby surfaces. Then the reset runs. Loose clutter is gathered and carried out of frame in armfuls, the surfaces emptying one after another. Cloths sweep across worktops, shelves and sills, lifting the dull film so the finish comes up bright behind each pass and dust stops sitting in the edges. Textiles are pulled free, shaken out and dropped back, billowing once and settling flat and square. Glass and metal are wiped and buffed until they hold a clean highlight again. The remaining items travel back to their places in quick hops and line themselves up square and evenly spaced. Last the floor is worked over: a tool passes across it, grey suds and lifted dirt rolling ahead of the head while the clean surface opens behind, the water thinning and running clear and then sheeting away. Finally everything comes to rest. The last wet surface dries, the bursts of motion stop, and the room holds still and clean in the settled light. Physical realism throughout: real weight in what is lifted and carried, real fabric behaviour in the textiles, real fluid behaviour in the foam and the running water, clutter and dirt physically removed from the room rather than fading out on the spot, accurate reflections on the cleaned surfaces, natural light response, real camera capture.
10 seconds, 9:16. Beauty transformation. TikTok influencer energy. She MOVES the whole time — shoulder rolls, head tilts, a little bounce, looking at the lens like a trending audio. Photoreal. ELARA LOCK: @image1 is Elara — photocopy her FACE, hair and eyes exactly as in @image1, adult. She wears the top from @image1 in EVERY shot, before AND after. IGNORE the background of @image1. Never change the top. SAME person. Hair colour exactly as in @image1. 0.0–2.0s SETUP. Natural makeup from @image1, the same top, already moving — small dancey head/shoulder beat toward camera. Lifts a LIGHT BLUE makeup brush between her face and the lens, still grooving. 2.0–3.0s RACK FOCUS. Framing locked but SHE still sways. Face blurs, bristles snap sharp. 3.0–4.0s TRANSITION. She flicks the brush ON THE BEAT. Sparkling glowing dust flies into the lens and clouds the frame. 4.0–10.0s REVEAL. Dust hides a hard cut. Rack focus back. SAME top from @image1. Instant GLAM MAKEUP: smokey eye, glossy lined lips, blush. Hair still its own colour from @image1, now styled in crimped waves. Large silver hoop earrings. She hits a confident TikTok pose — slow head tilt, a little body roll, smile at camera. HOLD. AUDIO: upbeat wordless groove, brush tap, sparkle whoosh. NO lyrics. NO famous songs. NEGATIVE: a top different from @image1, a hair colour different from @image1, overlay type, extra people, the background from @image1, still/frozen face, copyrighted lyrics.
Generate a live basketball Kiss Cam where your partner surprises you with a kiss on the cheek.
Generate a live football broadcast where you snap your fingers, freeze the whole stadium and walk to your seat.
Generate a live basketball broadcast where the courtside camera catches you on the big screen and you react shyly.
TROPICAL BEACH TRAVEL FILM @image1 walks a breathtaking turquoise beach at golden hour in a premium travel-film, carrying the bag/product from @image2 naturally as part of the look. Plug in ANY avatar and ANY bag/product. Music only, 15s.
25 seconds, 16:9. Photoreal daytime bedroom. No on-screen subtitles. ENGLISH dialogue only. LANA LOCK: @image1 is Lana — photocopy their FACE, hair and features exactly as in @image1, adult. IGNORE the clothes in @image1. WILLIAM LOCK: @image2 is William — photocopy their FACE, hair, facial hair and features exactly as in @image2. IGNORE the clothes in @image2. OUTFITS from the film: Lana in a dark grey tank, denim shorts, white sneakers. William in a light denim shirt, blue jeans. Same clothes the whole clip. Warm bedroom: pale wall, small sofa, bed with beige linens. Wall → sofa → bed. Side-window daylight. 0.0–2.8s William at the wall. Lana steps in, right palm on the wall beside his head (kabedon). William stays against the wall. Lana, smug: "I just tried it. That bed of mine is really soft." 2.8–6.4s Lana holds the pose, leans in. Lana: "Want to... try it tonight?" Pause. "With me." 6.4–8.0s William, calm: "Sure." He leaves the wall. Lana's smile flickers, surprised. 8.0–11.2s He steps toward her. She drops her hand, steps back toward the sofa. William: "If we're testing how soft the bed is, why wait until tonight?" 11.2–14.0s She sits on the sofa edge. Lana, quieter: "I was kidding." He leans, palm on the sofa beside her. William: "I'm serious." 14.0–17.0s She shy-smiles, puts her hands on his shoulders. No new lines. 17.0–20.0s He lifts her properly — arm behind her back, other under her knees. She holds his neck. He turns toward the bed. 20.0–25.0s Two steps to the bed. He sets her down gently: hips, then legs, then back on the pillows. They smile. HOLD. AUDIO: English speech, palm-on-wall tap, footsteps, fabric. Soft music, no lyrics. No Chinese. No overlay type. NEGATIVE: Chinese dialogue, subtitles, clothes copied from @image1 or @image2, overlay captions, extra people, gore.
SEEDANCE 2.5 | TEXT TO VIDEO | SINGLE CONTINUOUS TAKE | 22s | 1080x1920 | 9:16 | 30fps | 1080p SCENE AND LOCATION A hidden desert oasis slot canyon deep in a red sandstone plateau on a bright midday. A narrow, deep gorge with steep, very high walls of warm red-orange sandstone, wind-carved into smooth ripples and streaked with dark desert varnish, with hardy green shrubs and small palms clinging to ledges. At the bottom is a crystal-clear natural oasis pool. The shallow edges glow bright turquoise and aqua, fading to deep sapphire blue in the center. The water is so transparent that the bottom is fully visible: pale sandy floor, smooth boulders, and two long sun-bleached driftwood logs lying diagonally across the bottom. One spring-fed waterfall pours from a crack high on the canyon wall into the pool, making white foam where it hits the water. Tall date palms and desert scrub line the canyon rim. Above is a vivid clear blue desert sky with a few small white clouds. Hard, bright midday sunlight with strong contrast, heat-shimmer in the far distance, and sun sparkles on the water. THE JUMPER A person seen only from their own first-person view. Tanned bare feet and athletic shins, and loose terracotta-orange swim shorts with a simple cream geometric pattern and white drawstrings. No shirt, no shoes, no gloves. Their hands and forearms appear naturally in frame when they move. CAMERA AND REALISM First-person POV from a GoPro strapped to the forehead. It looks like real action-cam footage, not a cinematic camera. 16mm-equivalent ultra-wide lens with slight barrel distortion, and saturated but natural color. Use real action-cam behavior throughout: small head bob and micro-jitter from breathing and body weight, rolling-shutter wobble on fast moves, quick auto-exposure shifts between bright sky and the shaded canyon, a small sun flare on upward tilts, light sensor noise in the shadows, and wind buffeting that shakes the frame during the fall. The cliff is about 35 meters high. Gravity, body motion and water physics are fully realistic. 0-2s | THE EDGE (real time) POV looking straight down from the top of the sandstone cliff. Bare feet stand on the rough, warm rock ledge at the bottom of frame, with the shorts visible at the lower edge. Both hands hover forward at the sides of frame. The turquoise pool, the driftwood logs and the waterfall are far, far below. Toes curl over the edge and small grit crumbles off. A hand tosses an orange-and-white striped inflatable tube out over the drop; it tumbles down and lands as a tiny speck on the water far below. Wind, distant waterfall roar, upbeat chill electronic music starts. 2-4s | THE COUNTDOWN (real time) A quick nervous tilt down at the drop, a sharp exhale, then two fast steps back from the edge, with the ledge bouncing in frame. A hyped voice: “Three, two, one!” 4-7s | THE TAKEOFF (natural slow motion, about 50% speed) Two running steps forward, then the last foot pushes off the ledge in slow motion. Rock grit kicks up and floats in the sunlight, the cliff edge slides away underfoot, arms swing forward and out wide, and the whole turquoise oasis opens up below. The slow motion looks like a real high-frame-rate action-cam clip, not a frozen hang. Deep bass swell, stretched wind. 7-13s | THE FALL (real time, fast and continuous) The speed ramps smoothly back to normal and the stomach drops. 7-9s: The frame dips and wobbles, arms flail slightly for balance at the edges of frame, feet kick at the bottom of frame. A loud yell: “Woooooo!” 9-11s: The sandstone wall, its ripples and streaks, and clinging desert shrubs streak upward past the lens, and the waterfall rushes by with spray catching the sun. Wind roars louder and the frame shakes from air buffeting. 11-13s: The glowing turquoise water rushes up and fills the frame, and the orange tube and driftwood logs grow fast. Arms snap tight to the body and legs lock straight for a feet-first pencil dive. The music builds to the drop. 13-14s | IMPACT A hard feet-first hit into the water and a white explosion of bubbles swallows the lens. Loud plunge splash, deep impact whoosh, and the music goes heavily muffled underwater. 14-17s | UNDERWATER (short, energetic, real time) A violent swirl of silver bubbles clears to reveal crystal-clear blue water, bright sun shafts cutting down from the surface, the sun-bleached driftwood and pale sandy bottom below, and small fish darting away. Hands push into frame for one strong breaststroke pull, then fast kicks straight up toward the bright glowing surface, with bubbles streaming past the lens. No slow sinking. 17-19s | SURFACE BREAK The camera bursts through the surface, water droplets sliding across the lens, and bright sunlight floods in. The music snaps back to full clarity on the beat drop. A hand grabs the orange-and-white tube floating right beside it. 19-22s | THE REWARD POV bobbing on the turquoise water holding the tube, then a sharp tilt up revealing the towering sandstone cliff, the tiny ledge jumped from far above, the palm trees on the rim and the vivid blue sky, with the waterfall splashing to one side. An out-of-breath, triumphant voice: “Yeah, that was insane!” Faint distant cheering. Music plays clean to the final frame. AUDIO Continuous upbeat chill electronic track: a bass swell on takeoff, a fast build through the fall, muffled underwater, then a clean drop on surfacing. Real ambient layers: wind that grows with speed, fabric flapping, heavy breathing, waterfall roar, splash, bubbles. Dialogue clear over the music. KEEP One continuous take, first-person only. The same shorts, feet and hands throughout, and the same canyon layout with one waterfall, turquoise pool and submerged logs. The slow motion lasts only 3 seconds at takeoff. The fall is fast, real time and builds speed without pausing. Every beat is quick and punchy. AVOID Extra slow motion beyond the takeoff, hovering or floating mid-air, smooth cinematic gimbal movement, cuts to third person, showing the jumper’s face, extra people, distorted hands or extra fingers, morphing cliffs, changing water color, text, subtitles, watermarks.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. ASSET MAP: @image1 — the character. @image1 is face, hair, skin and identity only. Do not copy a black V-neck long-sleeve top, a gold snake pendant, layered gold chains, a gold bangle, a crossed-arms studio pose, or a white seamless backdrop from the still. WARDROBE (locked for the whole clip): a fitted black tank top and heather-gray sweatpants. Bare arms. No gold jewelry. SET: a real lived-in bathroom, waist-up. Soft daylight from a window or vanity. A mirror off-camera, a simple sink edge, a toothbrush cup, a small hand towel. Stable objects. Natural smartphone exposure, realistic skin texture, no cinematic grading, no beauty filter. CAMERA: real smartphone beauty UGC. Waist-up, eye-level, very subtle natural handheld movement only. Face sharp and stable. One continuous take. No cuts. PRODUCT: one mascara wand and matching tube, generic black, consistent shape and size. No brand marks, no readable label. HANDS: only the visible hand holding the mascara wand. Always anatomically correct with five fingers, naturally proportioned. Do not create another hand, arm or additional limb. Do not duplicate the wand. START: already in the bathroom from frame 0, already holding the mascara wand near their upper lashes, already speaking. Never a frozen studio pose. Never the attached still as an opening plate. Never cut to the attached still. Tell the following story in exactly 10 seconds, same person throughout. 0.0–2.0s HOOK. Waist-up. Wand already at the upper lashes. They speak immediately, casual and unscripted, exact lip sync: "Okay wait, I actually really love this one." Tiny handheld sway. 2.0–5.5s APPLY. They lightly brush the wand along the upper lashes, slow and careful. Exact lip sync: "It lengthens my lashes so easily, it doesn't clump at all." Natural blink. Face stays @image1. 5.5–8.0s CHECK. They lower the wand a little, glance at the result in a small hand mirror or just off-camera, then look back to camera. One deliberate slow blink. Exact lip sync: "And it makes my eyes look way more awake" 8.0–10.0s APPROVE. Small pleased expression, slight nod. Wand still in the same hand, tube stable. Exact lip sync: "without looking overdone." Hold. Designed end, not a fade. PERFORMANCE: casual beauty-creator recommendation. Slightly persuasive but still natural. Subtle, confident, pleased. Small natural head motion. Normal irregular blinking. Minimal gestures. AUDIO (native, synced speech, no BGM, no voiceover, no extra narrator): they speak the lines above in a natural speaking voice, plus quiet bathroom room tone. Accurate mouth movement. REALISM: natural pores and skin texture, realistic hair strands, natural lash movement, no clumped or spider lashes, accurate eyelid and blink mechanics, natural lip sync, stable bathroom objects, no object duplication, no changing anatomy. NEGATIVE: duplicate hand, extra arm, extra fingers, floating hand, malformed hand, duplicated product, identity drift, altered face, changing hairstyle, changing clothing, gold snake necklace, black V-neck long sleeve, crossed-arms studio pose, white seamless backdrop, warped anatomy, mirror artifacts, beauty filter, plastic skin, AI glow, robotic movement, exaggerated gestures, flickering, CGI, clumped lashes, spider lashes, distorted eyes, smudged eye makeup, on-screen text, subtitles, watermark, logos, extra people.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character (the florist). @image1 is face, hair, skin and identity only. Wardrobe is florist-shop work clothes from the scene (simple work shirt or apron) — do not copy an olive-green quarter-zip, a white crew t-shirt, or the lounge interior from the still. SINGLE SUBJECT — HIGHEST PRIORITY: Only this one person appears throughout. No other people or hands ever enter the frame. CAUSALITY LOCK: The open shop door is already visible and slightly ajar from shot 1, so the gust of wind that swings it open further and scatters the stems has a clear, visible source. Nothing moves without a shown cause. PROP CONTINUITY: One partly-finished bouquet, one pair of shears, and a small pile of loose stems and petals on the counter all exist from shot 1. Nothing new appears later. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Tell the following story in exactly 3 shots, same character throughout, where shot 2 is a genuinely different event from shot 1 — not a bigger version of the same action. Clear visual beginning, twist and ending — never ambiguous or faded-out. STORY: The character is already mid-work at the counter, the shop door slightly ajar behind them, trimming stems for a bouquet with fast, confident, practiced snips of the shears — no measuring, clearly skilled, placing each stem into the arrangement in one fluid motion. A sudden gust swings the door open wider, and it visibly scatters the loose stems and petals on the counter, sweeping several off onto the floor and knocking the bouquet slightly off-balance in its vase. The character’s hands move quickly and precisely — completely different motion than the cutting before — gathering the scattered stems and petals off the counter and floor in fast, sure sweeps, tucking them back into the arrangement and straightening the vase, finishing with the bouquet looking fuller and better than before. They push the door shut with one hand, step back, and smile at the finished arrangement. STYLE: Warm, grounded flower-shop realism, soft natural light from the doorway, shallow depth of field, camera close on hands and face throughout, a sudden gust of motion for the scatter, settling into a steady frame for the recovery. Vertical 9:16. Continuous real motion, no freeze-frame, no cutaways. No on-screen text, no subtitles, no watermark, no title card. AUDIO (native, synced, no BGM, no voiceover, no narration): the snip of shears, quiet shop ambience, a sudden gust and the door swinging with a creak, the scatter of stems and petals hitting the counter and floor, quick decisive gathering sounds, the door clicking shut, and a satisfied exhale. SHOT 1 (0-6s): Open already inside the work — no static establishing beat. Character trimming stems with fast, confident snips and placing them into the bouquet, door slightly ajar behind them. SHOT 2 (6-12s): The turn — a different event, not a repeat. A gust swings the door open wider, scattering stems and petals off the counter and onto the floor, knocking the bouquet off-balance. SHOT 3 (12-18s): The resolution. Quick, precise gathering — a different hand motion than the cutting — restores the scattered stems to the arrangement, the vase is straightened, the door is pushed shut. They step back and smile at the finished bouquet. A clear, decisive ending, not a fade-out.
15 seconds, 4:3. Photoreal. Sunny water-park TV show. SET LOCK: @image5 is the LOCATION — photocopy the runway, pool, stands and backdrop exactly as shown in @image5. Do not invent a different park. PANEL LOCK: @image3 is the PANEL — the board and its TWO-PERSON CUTOUT exactly as shown in @image3. Photocopy that hole. POSE LOCK: @image4 is the POSE — copy the body pose only, not the figures. BOTTOM person STANDS, arms straight up. TOP person is UPSIDE DOWN, legs together pointing up. They hold hands. NOT a back-lying Romero. NOT a sitting stack. LANA LOCK: @image1 is Lana — face and hair exactly as shown. IGNORE the clothes in @image1. White tee, pink shorts, black choker. She is the TOP inverted partner. CATE LOCK: @image2 is Cate — face and hair exactly as shown. IGNORE the clothes in @image2. Same athletic kit. She is the BOTTOM standing partner. 0.0–3.5s They stand on the runway facing the panel in the distance. Handheld wide of the SET. 3.5–9.0s They form the @image4 pose: Cate stands, arms up; Lana goes inverted above, legs vertical, hands clasped. Panel rolls toward them. They wobble, slightly off the hole. 9.0–12.0s Panel hits. They tumble into the pool. Splash. 12.0–15.0s In the water. Lana frustrated. Cate laughs. HOLD. AUDIO: crowd, splash, yell, laugh. No overlay type. NEGATIVE: Romero on-the-back pose, clothes from @image1 or @image2, overlay captions, extra hero faces.
10 seconds, 16:9. Photoreal jungle-temple. Handheld. Fast continuous combat. NO gore. NO blood. Smash cut before impact. MATEO LOCK: @image1 is Mateo — photocopy their FACE, hair, facial hair and features exactly as in @image1, adult. IGNORE the clothes in @image1. OUTFIT from the film: dark navy-black combat tunic with blue wrap at the head/neck. Same look the whole clip. Ancient wet stone temple, moss, roots, waterfalls. Five armored extras attack. Water orbits Mateo as one moving mass. Ice shards split off and fly. No neon, no anime aura. 0.0–2.5s Mid-fight. Mateo pivots under a strike. Water orbits, deflects. Ice shards fire. Handheld lateral track. 2.5–5.0s Enemy from behind. He ducks, spins. Water whip. More ice shards. Quick pans. 5.0–7.5s Lateral water strike knocks an enemy onto wet stone. He turns to the next threat. 7.5–10.0s Circular footwork. Ice from the leading edge. An enemy charges. He accelerates the water mass toward them. END BEFORE IMPACT. Smash cut. AUDIO: footsteps, armor, water, ice, jungle. No music. No speech. NEGATIVE: the clothes from @image1, overlay type, extra hero faces, 9:16, gore.
30 seconds, 16:9. ONE continuous shot. Photoreal. No people as heroes. CAR LOCK: @image1 is the hero car — photocopy this exact machine: same body, livery, colours, number, lights and markings as shown. Do not redesign the car. Rivals: black-and-red interceptor ahead, silver-blue pursuer behind. 0–4s Start from a rear three-quarter of the hero car, centimeters above wet road. Spray at lens. Camera matches speed, sweeps rear-left to side track. The hero car drifts. Silver-blue bursts from behind. 4–8s Jungle root tunnel. Camera around left front, low frontal retreat. Giant tree falls; the hero car threads the gap. Waterfall sheet drift, rolling orbit around the car. 8–12s Collapsing elevated causeway. Camera dives under the car, gap jump onto a hauler, land, track right flank. Rainburst. 12–16s Flooded valley, hydroplane, three cars toward lens. Temple arch; collapse behind; shoulder-hit sparks. 16–20s Sinkhole outer ring, overhead spiral. Inner route collapses. Ram, ramp, airborne over the outflow. Camera under then beside mid-flight. 20–24s Cliff road by a huge waterfall, rolling orbit. Three-wide. Cave behind the fall, then jump through a water curtain onto a hanging bridge. 24–27s Bridge tearing. Wheel-height backward fly. Launch to a moss terrace. 27–30s Corridor of roots, rock ramp, all three airborne. Full orbit around the hero car. Land first on flooded stone runway. Low frontal retreat, three cars charging into the basin. HOLD. AUDIO: engines, rain, water, collapse. No speech. No overlay type. NEGATIVE: overlay captions, identity drift of the car, extra heroes, 9:16.
26 seconds, 16:9. Cinematic. No dialogue. LANA LOCK: @image1 is Lana — photocopy their FACE, hair and features exactly as in @image1, adult. IGNORE any clothing in @image1. WILLIAM LOCK: @image2 is William — photocopy their FACE, hair, facial hair and features exactly as in @image2, adult. IGNORE any clothing in @image2. Cabin clothes (0–10s): William in a dark charcoal oversized hoodie with chest charms. Lana in a slightly unbuttoned cream silk blouse and flowing white skirt. Meadow clothes (11–26s): Lana white dress/blouse in the wind. William light blue shirt. 0.0–4.0s Dim rustic cabin. Close-up WILLIAM crying, tears. William holds a black pistol, hand trembling, grief — then the barrel lowers. Not a shootout. 4.0–7.0s Medium: LANA in the cabin kitchen, wooden shelves, metal pots. Fierce rage, brows furrowed, eyes locked on him. 7.0–10.0s William crying harder, lowers the pistol fully, arms open in surrender. Extreme close-up wet face, eyes shut, tears. HARD SMASH CUT. 11.0–16.0s Golden hour. Same couple tumbling into tall grass and yellow wildflowers, embracing, petals flying. Warm flares. 16.0–20.0s They roll laughing. Lana's smile. His hand cups her cheek. He smiles eyes closed as she leans over him. 20.0–23.0s They run hand-in-hand away from camera through green hills at sunset. Her white skirt, his light blue shirt in the wind. 23.0–26.0s Hilltop, his arm around her, orange sun. He kisses the top of her head. Final wide: two small silhouettes against pink-orange dusk, wildflowers. HOLD. AUDIO: breathing, wind, distant birds. No speech. No songs. NEGATIVE: clothing from the face photos, extra people, overlay type, 9:16, gore.
10 seconds, 9:16. Nail transformation. STATIC close-up on HANDS only. No faces. Photoreal salon table. MATCH CUT rhythm: a manicurist's PINK LATEX GLOVED hand holds the client's hand, then PULLS DOWN out of the bottom of the frame, then SWEEPS BACK UP to catch the same hand in the next stage. Fluid, one continuous camera. Client: adult woman's left hand, light skin. Manicurist: pink glove only. 0.0–2.5s BEFORE. Pink-gloved hand holds the client's hand. Nails have GROWN-OUT old polish, chips at the cuticle. Glove pulls down, exits bottom of frame. 2.5–5.0s DURING. Glove sweeps up, catches the hand. Nails are now BARE, filed, clean, no polish. Glove pulls down again. 5.0–7.5s PROCESS. Glove sweeps up. Nails now have a fresh PINK BASE COAT, even and wet-looking. Glove pulls down. 7.5–10.0s AFTER. Glove sweeps up last time, holds the hand. Final design: pink base plus BUTTERFLY DECALS on the nails. HOLD. AUDIO: quiet salon. No speech. No songs. NEGATIVE: faces, overlay type, extra people, feet, nude, blood.
Generate a live baseball broadcast where a home run turns you from bored to screaming.
DISSOLVE — Butterfly @image1 stands serene, then gently breaks apart into a swarm of glowing butterflies that scatter toward the camera and sweep up into the sky. A magical, beautiful cinematic 15s dissolve — no ash, no gore. Swap in ANY avatar.
TORNADO — Summon & Hurl @image1 pulls a small swirling vortex of wind into their hands, compresses it into a glowing storm-orb and hurls it toward the horizon — where it erupts into a colossal towering tornado. A dynamic, powerful cinematic 15s take. Swap in ANY avatar.
@image1 is the opening frame of this film and @image2 is the closing frame. The film travels from one to the other as a single unbroken take. @image3 is the storyboard and sets the order in which the change arrives. Absolute continuity lock: the room's shell never changes across the whole take. The ceiling line, the wall positions, the floor plane and every window and door opening hold exactly where they begin, at the same size and in the same place, from the first frame to the last. Nothing about the structure moves, widens, closes, vanishes or is added. Camera: it holds its position for the entire take. No pan, no tilt, no zoom, no push in or pull back, no orbit, no handheld swing, no reframing of any kind. Allow only the faintest living breath in the frame so the picture never reads as a frozen still. Everything that changes does so in place — materialising, healing and settling within the frame — rather than being carried in or out from offscreen. There are no cuts, no dissolves between shots and no transitions; the whole film is one continuous piece of time. The change arrives in this order, each stage taking about as long as the last: The scattered debris and the broken rubble lift away from the floor, and the ruined furnishings thin out and are gone, leaving the floor clear. The damaged wall surfaces heal, the blotched and peeling patches closing over into smooth sound plaster, and the floor settles into one clean continuous surface. The rug unrolls itself into the centre of the floor and the wide framed picture resolves onto the far wall above where the bed will stand. The bed builds itself in place against the far wall, headboard first, then the frame, then the bedding and pillows, with the bench settling at its foot. The bedside tables arrive on either side and their lamps come on warm, the smaller pictures resolve beside the wide one, and plants and baskets settle into the corners. A soft vertical wipe of light crosses from left to right, daylight blooms through the far opening, and the whole image warms into its final grade. The film settles on the finished room and holds there, breathing, to the last frame. Photorealistic throughout, matching the two pinned frames exactly in material, colour and light. Do not include any people, animals, text, captions, logos or watermarks.
HEARTBREAK TO GOLDEN LOVE @image1 tearfully aims an old pistol at @image2 — who has turned — but can't pull the trigger; then a smash-cut to a golden-hour memory of the two, alive and in love in a wildflower meadow. Plug in ANY two avatars. Music only, one flowing 25s take.
FLOWER MORPH — The Bush Becomes a Person @image1 walks up and touches a big flowering bush — and the blossoms spiral upward and knit into @image2, who steps out in a flowing gown. A magical two-avatar transformation, cinematic 15s. Plug in ANY two avatars.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character (the frightened protagonist). Photocopy @image1 for face, hair, skin, identity, and the wardrobe on the still (burgundy long-sleeve V-neck satin dress, layered gold chain with a gold snake pendant, thin gold bangle). Do not restyle hair. Do not invent a different dress or jewellery. Ignore any beige pad around the still — that pad is not a set. If any other person appears (the tactical soldier), they are never named, aged or gendered in the text — described only by their role and what they do. Only @image1's face is locked as an identity. Extra people in this story are beats, not copies of @image1. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Create a cinematic photorealistic action-thriller sequence set in a modern downtown city surrounded by tall skyscrapers, at dusk with the city lights just coming on. SHOT 1 (0-3s): Extreme close-up of the character’s frightened face — the person exactly as in @image1 — wet eyes, realistic skin texture, dramatic dusk lighting, intense emotional expression. SHOT 2 (3-7s): Cut to a high aerial drone shot flying between dense skyscrapers, looking down at a busy city street with cars, pedestrians, traffic markings and realistic urban detail. The camera moves rapidly forward between the buildings with cinematic motion blur. SHOT 3 (7-12s): Cut to a dynamic POV shot from inside a moving dark sedan, focusing on the side-view mirror. In the mirror reflection, a heavily armored futuristic black tactical vehicle drives aggressively alongside the car, with a tactical soldier visible inside — described only by role and action, never named or identified. Keep the mirror reflection realistic and sharply detailed while the surrounding city moves with natural motion blur. SHOT 4 (12-16s): Fast-paced aerial and street-level shots showing the armored vehicle chasing the sedan through the downtown streets, including a brief stretch through an underpass tunnel lit by sodium lights. Realistic smoke, dust, damaged vehicles and cinematic atmosphere. SHOT 5 (16-20s): End with a dramatic top-down aerial shot looking directly at a city intersection as the sedan moves through traffic and a powerful explosion suddenly erupts nearby, producing a bright orange fireball, thick gray smoke, sparks and debris. STYLE: Ultra-realistic physics, realistic vehicle movement, cinematic camera transitions, natural lighting, shallow depth of field, high detail, realistic motion blur, blockbuster Hollywood action-movie cinematography, photorealistic, HDR, anamorphic lens, dramatic color grading, intense suspenseful atmosphere. AUDIO (native, synced, no BGM, no voiceover, no narration): engine roar and tire screech, wind rushing past the drone shots, the tactical vehicle’s engine snarling alongside, distant sirens, the explosion’s deep boom with debris scattering, and the character’s frightened breathing in the close-up. No on-screen text, no subtitles, no watermark, no logos. Vertical 9:16. Exactly 20 seconds.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character. @image1 is face, hair, skin and identity only. Wardrobe is a fitted olive-green utility jacket, brown trekking trousers, sturdy hiking boots, and a small tan canvas backpack. Hair and jacket move naturally with the mountain wind throughout. Do not copy a black V-neck top, a gold snake pendant, layered gold chains, a gold bangle, a crossed-arms studio pose, or a white seamless backdrop from the still. SINGLE SUBJECT — HIGHEST PRIORITY: Only this one person appears throughout. No other people, faces or hands ever enter the frame. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. ENVIRONMENT: a dramatic high-altitude mountain landscape — misty granite ridgelines, alpine meadows dotted with wildflowers, a still turquoise alpine lake, distant snow-capped peaks, and thin cloud drifting across the rock faces. Crisp, elevated, adventurous atmosphere. LIGHTING AND CINEMATOGRAPHY: warm golden-hour sunlight cutting through drifting mist, soft highlights on rock and water, natural shadows, realistic skin texture, cinematic depth of field, subtle lens flare, smooth camera movement, natural motion blur, high-end travel-film color grading. Tell the following story in exactly 15 seconds, same character throughout, already in motion from frame 0 — never a frozen studio pose. Clear visual beginning, middle and ending. SHOT 1 (0.0-3.0s): RIDGELINE. Open already in motion — no frozen pose. Aerial wide of a misty mountain ridge, fog already drifting across the rock, wind already moving the character’s jacket and hair as they stand at the edge of an overlook, back toward the camera, looking out over the peaks. The camera slowly descends and moves closer. SHOT 2 (3.0-6.0s): RIDGE TRAIL. Smooth tracking shot as they walk along a narrow rocky trail through an alpine meadow, boots finding footing on stone, wildflowers brushing past their legs. Jacket and hair move naturally in the wind. Camera follows from behind and slightly to the side. SHOT 3 (6.0-9.0s): CLOSE-UP. Intimate close-up as they turn toward the camera with a soft, natural smile, windblown hair across the face. Warm sunlight on the skin, misty peaks blurred behind. Photocopy @image1 face. SHOT 4 (9.0-12.0s): LAKESIDE. Side-profile beside the still alpine lake, looking toward the distant snow-capped peaks, eyes gently closing to feel the mountain wind. Camera slowly circles as sunlight creates a soft golden rim light on the hair. SHOT 5 (12.0-15.0s): ENDING. Wide shot walking toward a scenic rocky viewpoint over the mountain range as the sun sets in soft golden, peach and pink tones. Camera pulls backward and upward, revealing the full ridgeline and valley below. End on a peaceful, dreamy frame — a clear last beat, not a fade-out. MOOD AND STYLE: dreamy, peaceful, adventurous, elegant, premium cinematic travel-film atmosphere. Ultra-realistic, photorealistic, cinematic 1080p, realistic human anatomy, consistent facial identity, natural facial expressions, realistic mist and cloud movement, realistic wind, natural lighting. No artificial CGI appearance, no distorted anatomy, no identity changes, no unnatural movements. AUDIO (native, synced, no BGM, no voiceover, no narration): wind gusting across the ridge, distant faint bird calls, boots on rock and gravel, fabric moving in the wind. No on-screen text, no subtitles, no watermark, no logos. Never cut to the attached still.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character (the skater). @image1 is face, hair, skin and identity only. Wardrobe is casual outdoor skate clothes from the scene (fitted hoodie or tee, loose skate pants, sneakers) — do not copy a navy plaid turtleneck dress, gold chain necklaces, a snake pendant, a gold bangle, crossed-arms studio pose, or a beige/white seamless from the still. SINGLE SUBJECT — HIGHEST PRIORITY: Only this one person appears throughout. No other people, hands or vehicles ever enter the frame. CAUSALITY LOCK: The skateboard only ever moves because this character’s own feet or hands are directly acting on it in that same continuous motion. It never moves, flips or rolls on its own. PROP CONTINUITY: Exactly one skateboard exists in this scene, already under the character’s feet in shot 1. Nothing new appears later. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. Tell the following story in exactly 3 shots, same character throughout, as one continuous, physically clear chain of action — never vague or chaotic motion. Clear visual beginning, twist and ending — never ambiguous or faded-out. STORY: The character is already rolling through an outdoor plaza on their skateboard, casually popping a simple, practiced flick trick and landing it clean without breaking stride — confident, relaxed, clearly a personal signature move they’ve done a thousand times. Feeling good, they line up toward a low ledge ahead and push into a bigger, more ambitious version of the same trick — a higher pop, a faster flip. Mid-air, the board spins a fraction too far, tilting off-axis, clearly about to slip out from under them on landing. Their eyes lock onto it, legs adjusting instantly, and in one sharp, continuous motion their foot catches the board’s tail just before it would have shot away, snapping it level and stomping the landing clean. They roll out of it smoothly, glancing back at the ledge with a satisfied grin. STYLE: Energetic outdoor realism, natural daylight, shallow depth of field, camera tracking alongside the character at skate height, a quick tight focus on the board during the wobble, smoothing out into a steady tracking shot for the clean rollaway. Vertical 9:16. Continuous real motion, no freeze-frame, no cutaways. No on-screen text, no subtitles, no watermark, no title card. AUDIO (native, synced, no BGM, no voiceover, no narration): the rattle and roll of wheels on pavement, a clean pop-and-catch of the first trick, ambient outdoor sound, a sharper pop as they push into the bigger attempt, a tense scrape as the board tilts off-axis, a fast decisive foot-catch, the clean snap of landing, and a satisfied exhale. SHOT 1 (0-6s): Open already inside the ride — no static establishing beat. Character rolling through the plaza, popping their casual signature trick and landing it clean without stopping. SHOT 2 (6-12s): The turn. They line up toward the ledge and push into a bigger version of the same trick. Mid-air, the board spins too far, tilting off-axis, clearly about to slip out on landing. SHOT 3 (12-18s): The resolution. One sharp, continuous foot-catch snaps the board level; they stomp the landing clean and roll away smoothly, glancing back with a satisfied grin. A clear, decisive ending, not a fade-out.
30 seconds, 9:16. ONE continuous take. action-cam forehead POV then selfie. Photoreal. Adult man. WILLIAM LOCK: @image1 is William — photocopy his FACE, hair and facial hair exactly as shown. IGNORE whatever clothes are in @image1. Face only appears in the last 8 seconds. OUTFIT the whole clip: BLACK tank, RED swim shorts with WHITE FLOWERS and white drawstrings, barefoot. Not navy. Not mustard hibiscus. Canyon: PNW pine forest, basalt hexagonal cliffs, turquoise spring pool, two waterfalls, submerged logs, pink-and-white tube. 0–2s POV looking down from the cliff. Bare feet on the ledge, RED floral shorts at the bottom of frame. Hands at sides. Toes curl. Right hand tosses the pink-and-white tube; it falls to a speck on the water. 2–4s Nervous tilt down, exhale, two steps back. Spoken, hyped: "Three, two, one!" 4–7s Slow-mo takeoff. Two running steps, last foot leaves the ledge. Arms out. Canyon opens below. 7–13s Real-time fall. Frame wobbles. "Woooooo!" Walls streak. Water rushes up. Pencil dive. 13–14s Feet-first splash. Bubbles swallow the lens. 14–17s Underwater, sun shafts, logs, one breaststroke, kick up. 17–19s Surface. Grabs the tube. 19–22s Bobbing, tilt up at the cliff. Spoken: "Yeah, dude! That was insane!" 22–30s Still in the water, he TURNS the camera around to himself, holding it like a selfie. WILLIAM's face now in frame, wet, excited, same energy. He looks into the lens. Spoken, excited: "Have to try this again!" HOLD. AUDIO: wind, waterfall, splash, spoken English. Chill electronic without lyrics. No overlay type. NEGATIVE: navy shorts, mustard flowers, clothing from @image1, overlay captions, extra people, 16:9.
30 seconds, 16:9. Premium headphone commercial. Photoreal. Cinematic. CATE LOCK: @image1 is Cate — photocopy their FACE, hair and features exactly as in @image1, adult. IGNORE any clothing and bags in @image1. OUTFIT from the film, not the still: black fitted top, oversized beige trench/neutral jacket, wide-leg trousers, sneakers. SAME outfit every shot. HEADPHONES: compact white/silver in-ear earbuds. Same design every shot. No morphing. 0.0–6.0s Noisy modern city street. Cate walks, takes the earbuds out, puts them on. City noise fades. 6.0–14.0s Cate walks; traffic lights pulse, lights glow with the beat. Tracking shots, face CU, earbud detail. 14.0–22.0s Subway: footsteps and trains blend into the music. Cate enjoys it. Wide, track, CU. 22.0–28.0s Exits into golden hour. Rooftop. Adjusts the earbud. Overlooks the city, eyes closed, immersed. 28.0–30.0s Hero close-up of the earbuds. HOLD. VOICEOVER, spoken English: "Some sounds demand your attention. Others deserve to disappear. ECHO brings you closer to what matters, with immersive sound, powerful clarity and lasting comfort. Block out the noise. Feel every detail. Find your own frequency." AUDIO: city then immersive music under VO. No songs with lyrics. No overlay type. NEGATIVE: clothing from @image1, overlay captions, identity drift, extra hero faces, 9:16.
@image1 (product plate) is the absolute product lock: silhouette, proportions, structure, materials, finish, colour and every existing marking are taken from it exactly and must not drift, restyle, recolour or change in any shot. @image2 (storyboard) is to be followed exactly — same shot order, same framing, same camera position and same staging in every beat. Photorealistic cinematic product-detailing film, filmed as authentic first-person footage. Realistic wide-angle action camera around 18mm equivalent with subtle optical distortion, natural handheld walking motion, tiny wrist corrections, realistic autofocus breathing and physically accurate motion blur. Begin extremely close on one corner of the product, completely buried under thick dried brown grime. The contamination has irregular texture, cracked areas, wet streaks and heavy buildup packed into every recess, seam and lowest surface. Gloved hands enter naturally from the bottom of frame holding professional cleaning equipment. Slowly step backward to reveal how dirty it is. Then the operator raises a professional foam cannon and sprays intensely saturated pink cleaning foam across the upper surface and the nearest corner. Show the liquid leaving the nozzle as real atomized spray. Foam gradually accumulates instead of appearing instantly. Pink cleaner mixes with brown dirt, becomes darker in contaminated areas, drips downward under gravity and splashes onto the tiled floor. Then move quickly but naturally in toward the most intricate part of the product. Capture an intimate close view as a detailing brush scrubs into a tight recess. Thick pink foam moves around the brush fibers, dirty liquid runs down the lowest surfaces and small droplets hit the camera lens. Preserve realistic hand pressure, brush deformation and imperfect human movement. Then pick up a pressure washer and begin rinsing the product from close range. The water jet physically cuts a clean path through the brown and pink foam, revealing the product's own untouched finish and true colour underneath. Follow the cleaning line across the upper surface and around to one side. Water sheets over the surface, beads along edges and explodes into fine mist where it strikes. Dirty runoff spreads naturally across the floor drain. Then a smooth handheld orbit around the nearest corner as the last foam is rinsed away. Bright rectangular ceiling lights stretch as realistic reflections across the newly clean wet surface. Water droplets remain across the product. Daylight from the open entrance softly mixes with the neutral white indoor lighting. Finish with a clean wide hero view of the pristine product from a low three-quarter angle. The operator lowers the pressure washer into the foreground while water continues dripping. Hold briefly on the transformation with no artificial camera flourish. Give all six beats equal screen time. Prioritize physical realism above spectacle. Accurate water physics, changing foam density, believable reflections, natural shadows, correct hand anatomy, consistent product geometry, stable proportions and unchanged surface detail from first frame to last. Include tiny lens droplets, subtle camera exposure adjustment when turning toward daylight, slight footsteps and restrained handheld shake. No morphing, no floating tools, no impossible liquid behaviour, no changing the product's design or colour, no fake glossy CGI surfaces, no text, no logos, no captions. Audio uses an energetic modern electronic percussion track with a deep clean rhythm that builds with the transformation. Integrate realistic foam cannon hiss, brush scrubbing, water splashes, pressure washer impact, dripping water and wet floor footsteps into the music mix. Make the pressure wash reveal land strongly with the main musical beat. No dialogue.
10 seconds, 9:16. Hair transformation. Static medium shot. Bright bathroom. Photoreal adult woman, FULLY CLOTHED in a white tank top and jeans. SAME woman both halves. Very long thick BROWN hair. Back to camera. Medium shot from the waist up. Hair is ALWAYS moving. Smooth, continuous. 0.0–4.5s BEFORE. Back to camera. White tank. Hair long, thick, BROWN, frizzy, straight, unstyled. She WAVES it — slow head turns, long swinging arcs, another wave. Fluid. 4.5–5.5s Soft HARD CUT on a matching hair-swing: frizz in motion becomes curls in motion. Same pose, same tank. No freeze, no flash, no overlay. 5.5–10.0s AFTER. Same back-to-camera angle, same white tank. Voluminous bouncy DEFINED CURLS. She RUNS BOTH HANDS through the curls, lifting and fluffing, then shakes her head so they bounce. HOLD. AUDIO: quiet bathroom, hair whoosh. No speech. No songs. NEGATIVE: overlay type, extra people, nude, lingerie, frozen stills, blonde, red hair, face-only.
