Made with OpenClips.AI

CHARACTER LOCK — HIGHEST PRIORITY: The character in every shot is exactly the person shown in @image1, shown at miniature scale throughout — same face, facial features, hairstyle, skin tone, build and gender presentation in every shot. No identity drift between shots. Do not beautify, slim, de-age or restyle the face or hair. @image1 is identity only — face, hair, skin — not any studio backdrop, not a frozen headshot, not any specific outfit as locked wardrobe; outfit, hair and accessories are exactly whatever the uploaded photo shows, only the scale changes. Photocopy the person from @image1, shrunk to a few centimetres tall, into the garden scene below. No other people in frame. ASSET MAP: @image1 — the character. Tell the following story in exactly 3 shots, same miniature character throughout, facing an oversized everyday environment as the world of the adventure. Clear visual beginning, twist and ending — never ambiguous or faded-out. STORY: At dawn on a windowsill garden, the character — a few centimetres tall — picks their way between fallen leaves and blades of grass, each dew drop looming overhead like a giant glass orb. They notice a discarded bottle cap lying nearby, its curved underside catching the light like a small hull. Without warning, the first fat raindrops of a sudden shower begin to strike the ground around them like small explosions, sending up splashes taller than they are. They scramble into the bottle cap for cover just as a fast-running stream of rainwater sweeps it off the ledge, spinning and rocking through the current as sheets of rain hammer down on every side. The current slows and the cap runs aground in a shallow puddle at the base of a potted plant; they climb out onto dry ground, soaked but grinning, and duck under the shelter of a broad overhanging leaf to watch the rain fall harmlessly around them. STYLE: Whimsical live-action macro realism, overcast silver-grey storm light giving way to soft ambient glow under the leaf shelter, shallow depth of field, rain-streaked textures and splashing droplets caught in motion, gentle handheld camera energy with a fast tracking glide during the rainwater ride. Vertical 9:16. Continuous real motion. Never freeze on the reference still. No on-screen text, no subtitles, no logos, no title card. AUDIO (native, synced, no music, no voiceover, no narration): birdsong cutting off as rain begins, the growing patter of raindrops, a startled gasp as the current sweeps them off the ledge, rushing water and rain hammering around them, a soft splash as the cap runs aground, and a relieved, delighted laugh at the end. SHOT 1 (0.0-6.0s): Establish the scale clearly. Handheld macro, low angle looking up so blades of grass and dew drops tower overhead. The character, a few centimetres tall, steps between fallen leaves, notices the bottle cap resting nearby and crouches to inspect it. A dew drop or blade of grass should read as unmistakably giant next to them — the scale contrast is the single most important thing in this shot. Face readable. SHOT 2 (6.0-14.0s): The twist. The first heavy raindrops slam down around them like small explosions, splashing higher than their head. They dive into the bottle cap just as a fast stream of rainwater sweeps it off the ledge. Camera follows in a fast tracking glide as the cap spins and rocks through the rushing current, rain hammering down on every side, their expression shifting from alarm to wide-eyed thrill as they grip the rim to stay upright. Same person as @image1. SHOT 3 (14.0-20.0s): The resolution. The current eases and the cap runs aground in a shallow puddle at the base of a potted plant. They climb out onto dry ground, soaked through, catch their breath — then duck under the shelter of a broad overhanging leaf and look back out at the rain, breaking into a wide, relieved grin as it falls harmlessly around them. A clear satisfying end, not a fade-out, not a still.

30-second 9:16 ultra-premium cinematic fashion film. @image1 is the product. Photocopy that object — same olive leather grain, chunky black platform, grey laces, silver eyelets, proportions. Do not redesign. Do not turn it into a sandal or a different shoe. @image2 is the storyboard — photocopy those camera beats. Dark futuristic runway. Glossy black floor. Charcoal architecture. Haze. Olive light accents. No people, no feet, no extra products. 0–3s: Extreme wide establishing. Product on the runway. Slow mysterious open. 3–6s: Low-angle hero. Slow cinematic dolly-in. 6–10s: Smooth lateral track, then a 90° orbit. Stabilized. 10–16s: Macro of original leather texture, then close-up of dark-chrome / silver hardware. Speed ramps, match cuts. Cutting speeds up. 16–22s: Low-to-high reveal. Fast but elegant push-in. Slow-motion three-quarter rotation. 22–27s: Slow down. Final symmetrical low three-quarter hero, overhead spotlight, floor reflection. Subtle last push-in. 27–30s: Hold the hero. Fade to black. No on-screen text, no captions, no logos. AUDIO: deep cinematic bed, sub-bass, fashion-show pulse, metallic whooshes, material foley. Calm confident VO: "Some designs are made to be worn. Others are made to be remembered. Sculpted with precision. Defined by presence. This is more than footwear. This is the new icon." Music under the voice, never silent.

3 steps55282

CHARACTER LOCK — HIGHEST PRIORITY: The character in every shot is exactly the person shown in @image1 — same face, facial features, hairstyle, skin tone, build and gender presentation throughout all 3 shots. No identity drift between shots. Do not beautify, slim, de-age or restyle the face or hair. @image1 is identity only — face, hair, skin — not the dark studio backdrop, not a frozen smiling headshot, not the white crew-neck t-shirt as locked wardrobe. Photocopy the person from @image1 into a lived-in apartment. No other people in frame. ASSET MAP: @image1 — the character. PROP LOCK: From the first frame, a pair of ordinary thin-framed glasses is already sitting on top of their head, resting in their hair above the forehead. They do not notice them until the mirror. Do not recast their face with glasses on their eyes until they slide them down in shot 3. Do not invent a different person. Tell the following story in exactly 3 shots, same character throughout, with a clear visual beginning, twist and ending — never an ambiguous or faded-out close. STORY: The character is running late for an important meeting and frantically searches their apartment for their glasses — digging through couch cushions, patting down their jacket pockets, shuffling through papers on their desk, glancing anxiously at a wall clock as the panic visibly builds. Rushing past a hallway mirror on their way to grab their coat, they catch their own reflection and freeze mid-stride — their glasses have been resting on top of their head the entire time. They blink at themselves in disbelief, then burst out laughing, shaking their head at their own mistake. They slide the glasses down onto their face, grab their coffee and bag from the counter, throw open the front door, and step out confidently into the morning light, still chuckling to themselves — now completely composed and right on time. STYLE: Warm, relatable live-action realism, natural home lighting, handheld documentary-style camera energy, comedic but grounded — no exaggerated slapstick. Vertical 9:16. Continuous real motion. Never freeze on the reference still. No on-screen text, no subtitles, no logos, no title card. AUDIO (native, synced, no music, no voiceover, no narration): rustling and rummaging sounds, a ticking clock building tension, a sudden silence at the mirror moment, a surprised gasp, genuine self-deprecating laughter, then keys jingling and a door closing. SHOT 1 (0.0-7.0s): Establish the panic clearly. Handheld 35mm, medium then closer. They rummage couch cushions, pat jacket pockets, shuffle papers on a desk, then an anxious glance at a wall clock. Urgency and mild chaos immediately obvious. Face readable. Glasses already on top of their head the whole time — visible in hair if the camera angle allows, but they never look for them there. No other people. SHOT 2 (7.0-13.0s): The twist. They rush past a hallway mirror, catch their reflection, freeze mid-stride. Close enough to read their face: the glasses sitting on top of their head, the realization, a blink of disbelief, then a burst of genuine laughter at themselves, shaking their head. Sudden silence then the gasp and laugh. Handheld, eye-level. Same person as @image1. SHOT 3 (13.0-20.0s): The resolution. They slide the glasses down onto their face, grab coffee and a bag from the counter, throw open the front door, and step out into morning daylight — relaxed, put together, still chuckling, keys jingling, door closing. A clear satisfying end — not a fade-out, not a still.

Cate is the FRONT-ROW FAN filming on their phone. Mateo is a FICTIONAL headliner — not a real celebrity. @image1 = CATE. Photocopy their face, hair, eye colour and features exactly as in @image1. IGNORE the clothes in @image1. Concert wardrobe: fitted black outfit + leather jacket, gold hoops. Same person every selfie. They MOVE, scream, laugh — not a posed still. @image2 = MATEO the singer. Photocopy their face, hair, facial hair and features exactly as in @image2. IGNORE the clothes in @image2. Black layered stage clothes, handheld mic. Do not turn Mateo into a real-world celebrity. 30 seconds, 9:16, photoreal SMARTPHONE concert footage. Seedance 2.5. Handheld shake, autofocus hunt, exposure pumping, high-ISO noise. Selfie camera mixed with flips to rear camera. SETTING: night stadium, barricade, red lights, haze, crowd phones, security. AUDIO: RAW phone — crowd scream, bass clip, their voice close. Lines: “I’M SO CLOSE!” and “NO WAY!” Original live-band energy. NO famous song. NO copyrighted lyrics. 0.0–2.5s SELFIE. Cate already front row, smiling into the lens, arm up: “I’M SO CLOSE!” Stage behind them. 2.5–5.0s FLIP to rear. Mateo walks to the front of the stage, red lights, their hand shakes, other phones in frame. 5.0–7.5s Digital zoom on Mateo at the edge. Focus hunts then locks. Cate screams off-camera. 7.5–10.0s Back to selfie. Cate laughing, screaming, messy hair, crowd jumping behind. 10.0–12.5s Rear. Mateo performs to the front row, mic to the crowd. Jump-shake. An arm blocks the frame. 12.5–15.0s Cate moves around the arm. Mateo looks toward the front row — brief eye contact. They freeze then scream. 15.0–17.5s Selfie. Cate “NO WAY!” red light on one side of their face, violent shake. 17.5–20.0s Rear. Stage goes dark. Phone flashlights. Crowd singing. 20.0–22.5s Lights explode red/white. Mateo at the front. Overexposure. 22.5–25.0s Mateo walks the stage edge. Fans reach. Security. Motion blur. 25.0–27.5s Selfie. Cate overwhelmed, laughing, catching breath. Friends behind. Stage over their shoulder. 27.5–30.0s Rear. Mateo under huge red lights, phones glowing, tilted frame, hands blocking, Cate jumps, recording cuts. NEGATIVE: real celebrity likeness, white studio, cinematic gimbal, Cate as the singer, the clothes from @image1 or @image2, on-screen titles.

BABY DANCE — 50s Rock 'n' Roll @image1 is a twelve-month-old baby rocking a razor-sharp adult-level 1950s rock-and-roll routine on a retro stage — rubber-leg knee wobbles, hip swivels, a two-handed air-guitar and fast jitterbug kicks, to a rockabilly track. Music only, mixed loud. One continuous 20s take. Plug in ANY baby avatar.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT made as a thin hollow shell of tinted glass, sitting on a small white plate on dark slate, with a silver teaspoon held just above it. It defines the object's shape, its colours and markings, the plate, the spoon, the hand, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE CRACK AND THE POUR — this is the whole point of the film: THE OBJECT is a thin glass shell full of a thick, glossy syrup the same colour as the object itself. The back of the spoon taps the top of it three times. The first tap leaves one tiny star-shaped crack. The second tap spreads fine cracks outward from it like a spider's web across the glass. On the third tap the top of the shell gives way, breaking into a few curved shards that sink into the syrup, and the syrup wells up and slowly pours out over the sides in thick glossy ribbons, flowing down the outside of the shell and spreading into a smooth shining pool on the white plate. The shards stay large and clean-edged, and the rest of the shell stays standing, so THE OBJECT is still recognisable to the end. Summary: a macro ASMR film in one unbroken take in which a teaspoon taps a thin glass version of THE OBJECT three times until it cracks open and a thick syrup in its own colour pours slowly out onto the plate. Timeline: 0–2s — The framing of @image1. The spoon taps the top of THE OBJECT once, a bright clear tick, and a tiny star-shaped crack appears. 2–4s — A second tap. Fine cracks race outward across the glass like a web, catching the light. The camera begins to push in slowly. 4–6s — A third, firmer tap. The top of the shell gives way into a few curved shards, and the glossy syrup wells up through the opening. 6–8s — The syrup brims over and slowly pours down the sides of THE OBJECT in thick shining ribbons. The spoon lifts away out of frame. 8–10s — The camera settles close as the syrup spreads into a smooth glossy pool on the white plate around the base of the cracked shell, still flowing slowly, the light glinting on its surface. Notes: THE OBJECT keeps exactly the shape, colours and markings of @image1 on its shell for the whole film, and the syrup is the same colour as the object. The spoon is a small plain silver teaspoon. The same hand appears throughout. The light stays exactly as @image1 has it. The camera moves as one continuous slow push-in with no cuts, and the film runs as one unbroken take. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — three bright clear ticks of the spoon on thin glass, each a little firmer than the last, a fine crackling spread of cracks after the second, a delicate crunch as the shell gives way on the third, then the slow thick glugging and soft sticky flow of the syrup pouring onto the plate, and the soft room tone of a quiet kitchen under everything to the last frame.

2 steps261.4K

90s HOUSE DANCE — Explosive Club Runway @image1 goes full explosive 90s house dance on a lit club runway — the jack, lightning footwork, spins, a jump and a lofting drop, packed non-stop to a driving house beat. Music only, mixed loud. One continuous high-energy take. Plug in ANY avatar.

80s BREAKDANCE — Electric Boogaloo @image1 throws down old-school 80s breakdance on a neon night street — robotic pop-and-lock, arm waves, top-rock footwork and a floor spin into a freeze, to a chunky electro beat. Music only, mixed loud. One continuous take with real street-dance swagger. Plug in ANY avatar.

90s RAVE — Eurodance Warehouse @image1 goes full euphoric 90s rave in a dark warehouse — fast rhythmic arm waves, jumps and shuffles under sweeping lasers and fog, to a pumping eurodance beat. Music only, mixed loud. One continuous high-energy take. Plug in ANY avatar.

Keep the SECOND HALF of the last Fast take. Change only the opening. BACKGROUND: soft blurred forest bokeh behind everything — green trees out of focus, dappled light. Not a white studio. Not the background from @image1. DO NOT OPEN on an empty cup. DO NOT open with a splash ring around an empty cup. @image1 is THE CUP — photocopy the cup and drink exactly as shown — cup type, layers, syrup, cream and drizzle. IGNORE any caption, text or background in @image1. 15 seconds, 9:16. Seedance 2.0 Fast. No people except the cream-can hand at the end if needed. No branded carton. No leaves garnish. AUDIO: powder, pour, cream hiss. No speech. 0.0–3.0s START DIFFERENT: a pool or stream of WHITE MILK already in frame, forest bokeh behind. Fine MATCHA POWDER falls INTO the milk (powder into milk, never milk dumped onto dry powder). Green particles sinking and blooming in the white liquid. No cup yet, or cup already filled in the background — never empty. 3.0–6.0s Milk + matcha swirl, then a ribbon of RED STRAWBERRY SYRUP joining. Macro, forest still blurred behind. 6.0–9.5s KEEP: the cup filling — the drink, layers and syrup streaks exactly as in @image1. Cup is never empty here. 9.5–13.0s KEEP: SLOW-MO whipped cream from a cream CAN / dispenser coiling onto the cup, then the drizzle from @image1 on the peaks. 13.0–15.0s KEEP: hero of the finished cup exactly as in @image1, tall whip, forest bokeh. HOLD. NEGATIVE: empty cup, splash crown around empty cup, milk poured onto dry powder, leaves, white cyclorama, branded carton, overlay caption, storyboard.

Your avatar runs from a giant monster in the dark, gets caught, and the clip ends on a horrifying close reveal of the creature. Upload your own avatar (@image1) and monster (@image2). Music only, loud. See the video step for the full prompt.

LOOK: photographic beauty-campaign footage. Even frontal lighting on a plain white seamless, clean natural colour, realistic skin texture, shallow falloff behind the shoulders. No stylisation, no illustration, no film grain, no vignette. @image1 (bare-styling reference) is an absolute character lock for the first half and @image2 (glam-styling reference) is an absolute character lock for the second half — face, body, hair, makeup, wardrobe, materials and colours are taken from them exactly, with no drift or reinterpretation. The face is the same person in both halves; only the styling changes. @image3 (storyboard) is to be followed exactly: same framing, same hand positions, same order. CAMERA: one locked frame for the entire piece — a centred front-on bust framing, no pan, no tilt, no push, no zoom, no handheld drift. The framing, the lens, the distance and the background are identical before and after the cut. The subject stays centred and facing the lens throughout, breathing and blinking naturally. Beats, in order, each held for roughly the same time: 1. Both hands rise up into the lower frame, fingers extended, palms turning toward each other in front of the chest. 2. The palms press flat together in a single sharp clap, fingers pointing up, elbows out to the sides. 3. The palms part by a hand's width and clap together again, rhythmic and deliberate, and hold pressed together. 4. Hard cut on the held clap. The hands hold the identical position, now gloved, and the styling has changed completely. 5. The hands lower and open apart, sliding down and outward across the chest, then leave the frame at the sides. 6. Shoulders square, the chin lifts slightly and settles, holding a still pose to the lens. THE CUT: beat 3 to beat 4 is a hard instantaneous cut on the matched hand position — same height, same angle, same distance from the chest on both sides of the cut — one frame to the next, nothing in between. Do not dissolve, crossfade, morph, wipe, whip-pan or blur between the two halves. Do not animate the styling changing on screen. Do not show any intermediate state. AUDIO: sharp, close hand claps landing on beats 2, 3 and 4, with quiet room tone underneath. No spoken dialogue, no voiceover, no music. Do not generate any text, subtitles or captions. Do not generate a logo or a watermark. Do not change the background, the framing or the camera distance at any point. Do not add a second person or a mirror.

4 steps1231K

@image1 is an absolute character lock — face, body, hair, wardrobe, materials and colours are taken from it exactly, with no drift or reinterpretation in any shot. @image2 is the location. @image3 is the storyboard, to be followed exactly: same shot order, same framing, same pose and same staging in every beat. LOOK: shot on a DV tape camcorder. Soft, slightly blurry tape quality, faint tape noise, bloomed highlights under the overhead practicals, flickering auto-exposure, muted contrast, realistic skin tones. CAMERA: the subject is holding the camcorder themselves, sometimes propping it on a rack or bench. Hand shake throughout, misaligned framing, delayed focus pulls, clumsy zooms, the face occasionally cut off by the frame edge. Imperfect, unrehearsed shots. The camcorder never appears on screen. STYLE: playful and self-deprecating workout-vlog energy — exaggerated complaining, genuine laughs, exhausted but amused. Quick handheld cuts, the camera wobbling in sympathy with their unsteady legs. Beats, in order, each held for roughly the same time: 1. Propped at the rack, medium shot. They stand with hands on hips, catch their breath and let out a dramatic exhale. Dialogue: "Okay... leg day is not it today." 2. Handheld, close on the face. They wince, shake out one leg and laugh at themselves. Dialogue: "Why did I do that many reps—" 3. Propped medium shot at the machine. They sit down, push through a rep with their face straining, then flop back with a groan. Dialogue: "Okay that's it, I'm done, I'm so done." 4. Macro insert, shallow depth of field. Their hand closes around the machine handle, knuckles tensing, a faint tremor running through the fingers before the grip releases. No dialogue — ambient room sound only. 5. Handheld, walking, camera wobbling. They stand up and immediately wobble, grabbing the rack for balance, bursting into laughter. Dialogue: "Wait— okay my legs are literally shaking—" 6. Handheld, unsteady walk. They take exaggerated wobbly steps across the room toward the water fountain, the camera bouncing with their uneven gait. Dialogue, laughing: "This is so embarrassing, someone help me—" 7. Close handheld at the fountain. They lean down for a sip, sigh in relief and wipe their mouth with the back of a hand. Dialogue: "Okay... water is life right now." 8. Arm's-length framing against the wall. They lean back, still catching their breath, and grin tiredly into the lens. Dialogue: "Never doing legs again — see you guys, I'm going to go lie down somewhere." AUDIO: all dialogue spoken in English, close and slightly clipped as a camcorder's on-board microphone would capture it, breathless between lines. Ambient room tone underneath — distant plates settling, a machine cycling, faint footfall. No music. Do not generate any text, subtitles or captions. Do not generate a logo or a watermark. Do not show a camera, phone or recording device in frame. Do not add a timecode or recording indicator overlay.

4 steps21933

8-second 9:16 premium cinematic advertisement. @image1 is the product. Photocopy that object — same silhouette, materials, grain, hardware, colours. Do not redesign. Do not turn it into a watch. @image2 is the storyboard — photocopy those four beats. 0.0–2.0s: Slow cinematic push-in toward the hero product. Dark luxury set, rim light. 2.0–4.0s: Macro of the original texture. Realistic reflections moving across the real surface. Gentle light sweep, shallow depth of field. Subtle camera rotation. 4.0–6.0s: Lifestyle still of the same product on a refined surface. No people, no hands. 6.0–8.0s: Cinematic luxury hero. Hold. Same product, no deformation. No on-screen text. AUDIO: soft luxury bed, light whoosh, no vocals.

3 steps9131

15 seconds, 9:16. Rapid HARD CUTS on action. Static front-facing camera with occasional ECU. Modern minimalist apartment LIVING ROOM — pale walls, sofa, daylight. NOT the room or background from @image1. LANA LOCK: @image1 is Lana — photocopy face, hair and eyes exactly as shown; dressed in a cream silk shirt, white trousers, brown belt. IGNORE any watermark or overlay in @image1. Same woman every shot. She MOVES. JEWELRY: @image2 = the gift box — photocopy it exactly as shown, any brand name exactly as printed. Never a different box. @image3 = the necklace — photocopy it exactly as shown (metal, pendant, stones, chain, detail). @image4 = the first ring — photocopy it exactly as shown (metal, shape, stones, detail). @image5 = the second ring — photocopy it exactly as shown (metal, shape, stones, detail). AUDIO: room, box, jewelry. No speech. No lyrics. HARD CUT between every shot. ~1.5s each. SHOT 1 (0.0–1.5) Medium. Lana waves BOTH hands near her face, smiling. Living room. HARD CUT. SHOT 2 (1.5–3.0) Medium. She tosses the gift box (@image2) a little in the air, CATCHES it, holds it near her chin. HARD CUT. SHOT 3 (3.0–4.5) CLOSE-UP of her hands opening the box. Inside: the necklace from @image3. HARD CUT. SHOT 4 (4.5–6.0) Medium. She puts the necklace around her neck. HARD CUT. SHOT 5 (6.0–7.5) Medium pose, necklace on, looking at camera. HARD CUT. SHOT 6 (7.5–9.0) ECU of the necklace on her collarbone. HARD CUT. SHOT 7 (9.0–10.5) She takes the first ring (@image4) from a small pouch / from the box and slides it onto a finger. HARD CUT. SHOT 8 (10.5–12.0) ECU fitting the second ring (@image5) onto a finger. HARD CUT. SHOT 9 (12.0–13.5) Pose, both hands together, both rings visible. HARD CUT. SHOT 10 (13.5–15.0) ECU: hand near lower lip, both rings sharp. HOLD. NEGATIVE: the background of @image1, a hair colour different from @image1, a box different from @image2, blob rings, pebble pendant, watermark, on-screen text, extra people, one continuous uncut take.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT remade from soft ropes of smooth matte dough laid in neat rows that follow its shape, in its own colours, with two hands waiting just above it. It defines the object's shape, its colours, the dough, the hands, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every colour on THE OBJECT is a colour that already exists on @image1. SOFT ALL THE WAY THROUGH — this is the whole point of the film: THE OBJECT is made of nothing but soft dough; there is nothing hard inside it anywhere. Wherever the hands touch it, the whole body gives: it dents deeply, bulges out around the fingers, sags and slowly relaxes. The dough is smooth, elastic and glossy where it is pulled, like thick stretchy taffy or butter slime, and it always stays in one smooth connected mass with a clean silky surface. THE STRETCH AND THE SQUASH: first the fingers hook under the top rope and pull it slowly upward and outward, far above THE OBJECT, and it stretches into one long, smooth, glossy band that thins in the middle and turns slightly translucent, then sags back down in a soft heavy loop. Then both palms press flat down onto the top of THE OBJECT, and the whole upper half squashes down, spreading and bulging outward between the fingers in soft rounded ropes of its own colours. Summary: a macro ASMR film in one unbroken take in which two hands stretch one rope of THE OBJECT's soft dough into a long glossy band and then squash the whole object down under their palms, and it slowly relaxes back. Timeline: 0–2s — The framing of @image1. The fingertips come down onto the top rope and sink deep into it, and the dough gives and bulges up softly around each fingertip. 2–5s — The fingers hook under the top rope and pull it slowly up and outward, far above THE OBJECT; it stretches into a long smooth glossy band, thinning and turning slightly translucent in the middle, then sags back down onto the rows in a soft heavy loop. 5–8s — Both palms press flat down onto the top of THE OBJECT. The whole upper half squashes down slowly under them, the ropes spreading and bulging out between the fingers, the colours staying clean along each rope. 8–10s — The hands lift slowly away and out of frame. THE OBJECT slowly relaxes and rises part of the way back, still soft and slightly squashed, with the shallow prints of the palms on its top and the stretched loop resting across it, in its own colours. Notes: THE OBJECT keeps exactly the colours it has in @image1 in every rope of dough for the whole film, and the dough keeps its smooth silky surface throughout. The same two bare hands appear throughout. The light stays exactly as @image1 has it, with soft highlights sliding along the ropes as they move. The camera stays low and close with only a slow gentle drift closer, with no cuts, and the film runs as one unbroken take. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — soft pillowy squishes as the fingertips sink in, a slow sticky elastic stretching crackle with tiny air pops as the band is pulled out, a soft heavy slap as the loop sags back down, deep slow squelches and muffled puffs of air as the palms squash the dough down, a gentle sticky release as the hands lift, and the quiet room tone of a calm bright room under everything to the last frame.

2 steps261.4K

Copy the SOURCE CLIP camera and body motion exactly. 13 seconds, 9:16. Photoreal. One woman only. LANA LOCK: @image1 is Lana — photocopy her face, hair and eyes exactly as shown; dressed exactly as in @image1. IGNORE any watermark or logo patch on @image1. A bright kitchen (white cabinets, black track lights). Do not change her hair colour from @image1. Do not change her outfit. JEWELRY FROM THE STILLS — not the source video's blob rings or pebble pendant: @image2 = the first ring — photocopy it exactly as shown (metal, shape, stones, detail). @image3 = the second ring — photocopy it exactly as shown (metal, shape, stones, detail). @image4 = the necklace — photocopy it exactly as shown (metal, pendant, chain, detail). @image5 = the gift box — photocopy it exactly as shown, any brand name exactly as printed. Never a different box. MOTION (match the clip): 0.0–2.0s MCU, waist-up, LOCKED framing. Lana already facing camera. Both hands raised beside her face, fingers spread, showing empty hands, small smile. She MOVES — not a still. 2.0–4.5s SAME MCU. She looks DOWN, brings the gift box (@image5) up, opens the lid with both hands. 4.5–6.5s SAME MCU. She lifts jewelry from the box, holds it at chest height, looks back at the lens. 6.5–8.5s SAME MCU. The necklace (@image4) is now ON over the open shirt. Arms loosely crossed / settling the chain. Head turns slightly, then back to camera. 8.5–10.0s SAME MCU. Looking down, putting on the two rings from @image2 and @image3. 10.0–13.0s CAMERA PUNCHES IN to EXTREME CLOSE-UP: mouth, chin, hands. Both rings from @image2 and @image3 sharp on her fingers. She raises a finger toward her lips. Hold. This CU is mandatory — do not stay wide. AUDIO: room tone, box, jewelry. No speech. No lyrics. NEGATIVE: a hair colour different from @image1, a box different from @image5, blob rings, pebble pendant, watermark patch, storyboard, on-screen text, extra people, frozen JPEG as frame 0.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT made of clear glass tinted in its own colours, standing on the steel bed of a hydraulic press with the flat steel press plate hanging above it. It defines the object's shape, its glass material, its colours, the press, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. REAL GLASS UNDER A REAL PRESS — this is the whole point of the film, and it must look like genuine high-speed footage of a hydraulic press test: THE OBJECT behaves exactly like a real piece of solid tinted glass. The plate comes down and touches it; the glass holds under the load for a moment and a few long bright cracks shoot through it; then it bursts with a sharp crack. It breaks into real glass pieces: a handful of large jagged chunks, many smaller angular shards and a scatter of tiny glittering fragments, every piece the same tinted glass in the same colours as THE OBJECT, with sharp edges catching the light. Some shards skitter outwards across the steel bed and a few spin off the edge. The total amount of broken glass is exactly the amount of glass THE OBJECT had — a low scatter of pieces spread thinly across the bed, never a heap bigger than the object. Summary: a macro ASMR film in one unbroken take, filmed like real press-test footage, in which a hydraulic press slowly crushes a glass version of THE OBJECT until it bursts into sharp tinted glass shards across the steel bed. Timeline: 0–2s — The framing of @image1. The press plate descends slowly and steadily towards the top of THE OBJECT. 2–4s — The plate touches the top of THE OBJECT and bears down. The glass takes the load and a few long bright cracks shoot through it, and it creaks with a high strained ring. 4–5s — THE OBJECT bursts with a sharp crack. Chunks and shards of tinted glass break away and skitter outwards across the steel bed; tiny fragments glitter in the air for an instant and fall. 5–7s — The plate presses on down through what is left, flattening the last pieces with a dense crunch, and small shards keep sliding and settling on the steel. 7–10s — The plate slowly rises and out of the top of the frame, and the camera holds on the steel bed: a thin scatter of sharp tinted glass pieces in the object's colours lying where THE OBJECT stood, the largest chunks still showing fragments of its shape and markings, glinting in the rim light, one last shard rocking to rest. Notes: THE OBJECT keeps exactly the glass material, the colours and the markings of @image1 until it breaks, and every piece of broken glass keeps those same colours. The press bed and plate are brushed steel. The light stays exactly as @image1 has it. The camera stays locked and level for the whole film, and the film runs as one unbroken take. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — the low steady hydraulic hum of the press, a high strained ringing creak as the glass takes the load, one sharp explosive crack as it bursts, the bright tinkling skitter of shards sliding across steel, a dense crunch as the plate flattens the last pieces, a hydraulic sigh as the plate rises, and the quiet hum of a workshop under everything to the last frame.

2 steps291.5K

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT remade in glossy tinted glass, lying on a dark wooden board, steadied by a hand in a black glove, with the edge of a large chef's knife touching its top. It defines the object's shape, its glass material, its colours, the hand, the knife, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE CUT FACE — this is the whole point of the film: when THE OBJECT is opened, the face the knife leaves shows the inside of THE OBJECT as it really is inside, made in the same glass. Whatever that object really holds inside — its segments, its seeds, its core, its layers, its chambers, its filling — is there on the cut face, laid out in its true pattern and its true colours, as smooth polished glass. Where the object is solid all the way through, the cut face shows fine concentric rings of colour running out from the centre, like growth rings in glass, with tiny suspended bubbles. The cut face is flat, polished and bright, and the light shines through it. HOW IT CUTS: the knife goes straight down through the middle of THE OBJECT the way a sharp knife goes through firm chilled jelly — steadily, with an even resistance and a faint crisp crackle. Wherever the knife has already passed, the glass is divided along one clean flat plane. Every piece stays whole and solid and keeps its own shape. The gloved hand holds THE OBJECT steady the whole time. Summary: a macro ASMR film in one unbroken take in which a gloved hand holds a glass version of THE OBJECT while a chef's knife cuts it cleanly in half, and one half falls open to show its glass inside. Timeline: 0–2s — The framing of @image1. The knife presses and begins to sink into the top of THE OBJECT with a crisp crackle, and a bright line of light opens along the cut behind the steel. 2–5s — The knife travels steadily down through the middle of THE OBJECT. The camera pushes in slowly and close to the blade. The gloved hand holds it still. 5–7s — The knife reaches the board. The gloved hand lets the near half lean away, and it tips over and settles on the board with its cut face turned up towards the camera. 7–10s — The camera holds close on the cut face as it rocks gently to a stop: THE CUT FACE fills the frame, polished and glowing, light shining through its pattern and colours, the other half still standing behind it softly out of focus. Notes: THE OBJECT keeps exactly the glass material, the colours and the surface detail it has in @image1 for the whole film, and both halves are that same glass. The knife is a large polished chef's knife with a straight bright edge. The hand wears the same black glove throughout. The light stays exactly as @image1 has it, with highlights travelling along the cut edges as things move. The camera moves as one continuous push-in with no cuts, and the film runs as one unbroken take. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — the crisp crackling crunch of the knife moving down through the glass, one clean bright crack as the halves part, a hard glassy clack as the half lands on the wood, a short rocking rattle as it settles, and the soft room tone of a quiet kitchen under everything to the last frame.

2 steps281.5K

FULL-BODY GROOVE — Loft Funk & Soul @image1 drops advanced funk-style street dance in a warm loft — popping hits, clean body waves, tutting, a floating glide illusion and a spin into a knee-drop, to a fat funk-and-soul groove. Music only, mixed loud. One continuous technical, powerful take. Plug in ANY avatar.

80s DISCO FUNK @image1 grooves through a glittering 80s disco — the classic point-to-the-sky, hip sways, spins and roller-disco glides under a mirror ball on a glowing floor, to a funky disco beat. Music only, mixed loud. One continuous stylish, groovy take. Plug in ANY avatar.

90s HIP-HOP BLOCK PARTY @image1 throws down a classic 90s hip-hop set at a sunny block party — the running man, the roger rabbit and the cabbage patch, bouncing on a fat boom-bap beat with old-school swagger. Music only, mixed loud. One continuous high-energy take on an outdoor court with graffiti and a boombox. Plug in ANY avatar and let them own the block.

SLOGANS — edit these words and nothing else: BEAT 1 WORD = MAKE IT LOUD BEAT 2 WORD = GOLD REVOLUTION BEAT 3 WORD = MOVE FAST HERO WORD = BOLD BEAT 5 WORD = NO LIMITS BEAT 6 WORD = CREATE NOISE HERO WORD is used twice: once in beat 4 and again on the closing frame. A polished stylized 3D animated film of the kind used in high-end animated features and AAA game cinematics, with hand-painted surfaces over believable 3D forms, physically lit, real depth of field. Premium fashion campaign pacing, energetic but controlled. @image1 is an absolute character lock. Face, body, hair, clothing, materials and colours are taken from it exactly, with no drift or reinterpretation in any frame. @image2 is the storyboard and is followed exactly: its six panels are the six beats in order, and each beat matches that panel's shot size, camera position, figure placement, colour system, type voice and type layout. This is not a film in which the background slides. The typography is the moving force: the letters themselves animate, and the walk is what triggers them. One continuous walk, no cuts. The figure walks toward the camera with their face to the lens, travelling toward the lens for the whole clip, the camera retreating ahead of them at their own pace with a slow drift to one side. Beats, each given equal weight, one word event per beat: BEAT 1 WORD writes itself on stroke by stroke, then expands outward, some letters stretching tall and others snapping into place, arriving in layers — one letter passing behind them while another crosses in front. BEAT 2 WORD bursts in as separate pieces from several directions, overscaling and rotating slightly before locking together, with a block of colour landing behind it and torn paper edges lifting. BEAT 3 WORD rushes through the frame, the letters stretching forward in perspective and snapping back, the nearest streaking past the lens while others slam into place beside them. HERO WORD assembles in segments, splitting briefly into a near layer and a far layer so part of it stands in front of them and part behind, then settling into one controlled sculptural composition. BEAT 5 WORD hits large and stacks, fragmenting like torn paper at one corner, then recomposing into a clean arrangement as photographic fragments, ink strokes and halftone texture gather around it. BEAT 6 WORD surges toward the camera, stretches across the frame, breaks apart, collides and reassembles, every earlier motif layering back in, and everything locks into one final poster composition with HERO WORD standing large and complete behind them as they keep walking. Throughout, the letters behave as physical objects with depth: expanding, compressing, rotating in space, slicing across the frame, wrapping around their path, pushing toward the lens and receding, and passing both in front of and behind them. Type events land on the footfalls. The clothing moves with the walk — the open front of the outer layer swinging, hems and cuffs settling, everything coming to rest naturally between steps. Every movement runs forward in normal time: the subject always travels in the direction their body faces, their feet lead their motion, and nothing moves in reverse. Sound is the ambience of the space in @image2. No cuts, no camera shake, no glitch effects, no identity drift, no face change, no garment substitution, no lettering in any script other than Latin, no words beyond the slogans listed above, no sliding-background-only motion, no static type sitting flat on a surface, no sliding feet, no walking backwards, no warped hands, no extra limbs, no subtitles, no logos, no watermark.

3 steps6316.5K

@image1 is an absolute lock for the starting look and @image2 is an absolute lock for the revealed look: face, hair, styling, wardrobe, jewellery, materials and colours are taken from them exactly, with no drift and no reinterpretation at any point. Photographic live-action beauty-campaign rendering: soft even studio key, shallow depth of field, fine skin texture retained, neutral colour, natural motion blur on fast movement. No stylisation, no illustration, no beauty smoothing. A single locked-off centred portrait, framed head and shoulders. The camera does not move, push, pan or cut at any point, and the backdrop and framing stay identical from first frame to last. Facing the lens in the starting look, they raise both hands to the temples and run them up and back through the hair, fingers combing through to the ends, lips moving as if mouthing along to music. They lower both hands away out of the bottom of frame, the head settling square to the lens, shoulders shifting slightly, gaze steady into the camera. One hand lifts fast toward the lens, palm open and fingers spread, sweeping up across the frame until the palm fills it and the image blurs through the motion. The hand pulls away downward out of frame and clears the lens, revealing the revealed look in the same position, same framing and same backdrop. The chin lifts slightly, the head turns a few degrees, and the gaze returns to the lens, holding with small natural movement — breath, a settle of the shoulders, the curls swaying to rest — through to the end.

3 steps2720

15-second 9:16 ultra-realistic beauty vlog. Fast 1–2s cuts, gimbal, macro application, golden morning light, LED vanity mirror. @image1 is FACE ONLY — photocopy their face. Realistic skin: visible pores, texture, peach fuzz. Do not beautify, do not de-age. Do not describe hair or clothes. @image2 is the sheet — photocopy outfit. One person only. 0–2s: Makeup-free, smile to camera, holding a brush. They SAY out loud: "Come get ready with me in under a minute!" 2–5s: Primer, foundation, concealer jump cuts. They SAY: "Keeping it light, fresh, and glowy for today's look." 5–9s: Blush, bronzer, highlighter, brows. Macro of real skin. They SAY: "A little blush and glow... because we're going for that effortless look." 9–12s: Shadow, mascara, glossy nude lip. Hair flip. They SAY: "Mascara, lip gloss... and we're basically done!" 12–15s: Walk toward camera. They SAY: "Simple, fresh, and ready for the day. What's your favorite makeup step?" No on-screen text. AUDIO (required): generate a full soundtrack. All five spoken lines must be clearly audible English lip-sync. Light upbeat music bed under the voice from 0s to 15s. Never silent. Never SFX-only.

2 steps8924.3K

CHARACTER LOCK — HIGHEST PRIORITY: The character in every shot is exactly the person shown in @image1 — same face, facial features, hairstyle, skin tone, build and gender presentation throughout all 3 shots. No identity drift between shots. Do not beautify, slim, de-age or restyle the face or hair. @image1 is identity only — face, hair, skin — not any studio backdrop, not a frozen headshot, not any specific outfit as locked wardrobe. Photocopy the person from @image1 into the scene below. No other people in frame. WARDROBE (from the scene, not the still): a regular at-home bathrobe over sleep clothes. Not an evening gown, not a black cutout dress, not restaurant jewelry. Ignore the still's background completely — it is not the set. ASSET MAP: @image1 — the character. Tell the following story in exactly 3 shots, same character throughout, with a clear visual beginning, twist and ending — never an ambiguous or faded-out close. STORY: The character steps outside their front door in a bathrobe to grab the newspaper, and the door swings shut and locks behind them. They pat down the robe’s pockets, realize they have no key, and panic — pulling at the locked handle, peering through the window, pacing the porch. Then they freeze, remembering something, and hurry to a fake plastic rock sitting among the garden plants. They lift it, twist it open, and pull out a spare key hidden inside. They unlock the door, step back in relieved, then do a small triumphant fist-pump before the door clicks shut behind them. STYLE: Warm, relatable live-action realism, natural morning daylight, handheld documentary-style camera energy, comedic but grounded — no exaggerated slapstick. Vertical 9:16. Continuous real motion. Never freeze on the reference still. No on-screen text, no subtitles, no logos, no title card. AUDIO (native, synced, no music, no voiceover, no narration): a door clicking shut, birds and quiet street ambience, frantic patting on fabric, a rising sigh of panic, footsteps on a porch, the rock’s plastic lid twisting open, a key jingle, a relieved exhale and a short triumphant laugh. SHOT 1 (0.0-6.0s): Establish the lockout clearly. Handheld 35mm, medium then closer. The character steps out in a bathrobe, the door swings shut behind them with a click, and they turn the handle to find it locked. They pat down empty robe pockets, panic rising, peering through the window and pacing the porch. The problem is immediately obvious. Face readable. SHOT 2 (6.0-12.0s): The twist. The character freezes mid-pace, a realization crossing their face, then hurries to a cluster of garden plants beside the porch. They crouch and pick up an ordinary-looking fake rock, twist its hidden lid open, and pull out a small brass key, holding it up with a relieved grin. Handheld, eye-level. Same person as @image1. SHOT 3 (12.0-18.0s): The resolution. The character unlocks the front door, pushes it open, and steps back inside — then turns back for one beat to pump a fist in quiet triumph before pulling the door shut behind them. A clear satisfying end — not a fade-out, not a still.

Keep the 10s 9:16 breakfast-ad grammar. Make the TABLE look like @image2 — real plated breakfast, not a lone jar on empty linen. @image1 = the spread jar. Photocopy it exactly as in @image1 — lid, label, printed brand name and the colour of the spread. @image2 = the plated stack. Photocopy this look: the pancakes, plate, toppings, cutlery and table exactly as in @image2, the @image1 spread between the layers, glass of milk nearby, bright window light. Add a matching gold knife. Real breakfast mess — crumbs, a smear of the @image1 spread on the plate. 0.0–2.0s Slow push-in across the SET TABLE: jar (@image1), glass of milk, gold knife and fork, pancake stack like @image2. Warm morning. No empty white void. 2.0–4.0s MACRO: knife spreading the @image1 spread onto a pancake from the stack (round fluffy pancakes, not square toast). 4.0–6.0s Spoon lifting a swirl of the spread from the open @image1 jar. Slow. Milk glass soft in bokeh. 6.0–8.0s The finished stack like @image2: pancakes, the @image1 spread, the toppings from @image2, gold fork + knife, milk glass beside the plate. 8.0–10.0s HERO: jar + plated pancakes + milk + cutlery, window light, subtle camera drift. HOLD. No overlay type. AUDIO: knife, spoon, soft morning. No speech. NEGATIVE: a jar that differs from @image1, toast as the hero food, empty table, missing milk, missing cutlery, overlay type, people.

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT remade as a squishy stress toy packed with tiny glossy beads under a thin clear skin, resting on a white tray, with two hands waiting just beside it. It defines the object's shape, its colours and markings, the beads, the skin, the hands, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE PRESS AND THE RETURN — this is the whole point of the film: THE OBJECT is soft all the way through. Under the thumbs it flattens and spreads open into a wide, bumpy, pearly disc, and the tiny beads roll and shift under the thin skin, crowding towards the edges and parting in the middle, so the pressed centre turns thin and see-through and the colours deepen where the beads pile up. When the thumbs let go, THE OBJECT slowly puffs back up and fills out again, the beads rolling back into place, until it stands once more in its own exact shape. HOW IT MOVES: the skin is soft and stretchy and never tears; the beads are small, round and loose inside it, and they move like a crowd of tiny marbles — shifting, rolling, bulging the skin into little bumps. The return is slow and even, like memory foam, and the last beads settle into place one by one. Summary: an ASMR squishy film in one unbroken take in which two thumbs press THE OBJECT flat into a wide beaded disc on a white tray, and when they let go it slowly rises back into its own shape. Timeline: 0–2s — The framing of @image1. The two thumbs come onto the top of THE OBJECT within the first half-second and press down firmly into it, and the beads under them begin to shift and bulge the skin around the thumbs. 2–5s — The thumbs press deep and spread outward. THE OBJECT flattens into a wide bumpy disc, beads rolling to the edges, the centre thin and pale, while the fingers underneath cup and turn it slightly so the light rolls across the beads. The camera drifts slowly closer. 5–6s — The thumbs lift away and the hands open and move out of frame. 6–10s — Alone on the tray, THE OBJECT slowly rises back: it puffs up, fills out and rounds itself, the beads rolling back into place under the skin, until it stands in its exact shape from @image1 and the last few beads settle with a tiny tremble. Notes: THE OBJECT keeps exactly the shape, colours and markings of @image1 whenever it is at rest, and the beads keep their colours throughout. The same two bare hands appear throughout. The light stays exactly as @image1 has it, with tiny highlights sliding across the beads as they move. The camera moves as one slow continuous drift closer with no cuts, and the film runs as one unbroken take. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — a soft rubbery squeak as the thumbs sink in, then the dense crackling, rustling, bubbly crunch of hundreds of tiny beads rolling and popping against each other under the skin, growing fuller as it flattens, a soft rubbery release as the thumbs lift, a gentle fading bead rustle and a few last tiny clicks as it rises back into shape, and the quiet room tone of a calm bright room under everything to the last frame.

2 steps291.5K

Asset referencing: @image1 is the first frame of this video. It shows THE OBJECT remade as a squishy toy — a thin painted skin over a soft clear jelly body — held from above in two bare hands on a pale grey-white background. It defines the object's shape, its colours and markings, the skin, the jelly, the hands, the lighting and the framing of the opening shot. ATTACHED IMAGES ARE MANDATORY AND FINAL: the attached first frame outranks every word written below it. Wherever the image and this text disagree, follow the image. Every marking on THE OBJECT is a marking that already exists on @image1. THE SKIN AND THE JELLY — this is the whole point of the film: the outside of THE OBJECT is only a thin brittle skin, and the inside is soft, thick, glossy jelly. When the hands squeeze, the skin splits and curls away in large thin flakes that keep the colours and pattern of @image1, and the clear tinted jelly swells out between the flakes and bulges up between the fingers. From then on the jelly is soft, heavy and stretchy, carrying the flakes of skin inside it and on its surface like petals set in glass. HOW IT MOVES: the jelly moves slowly and heavily, like thick cold gel — it stretches, folds over itself and slumps under its own weight, always holding together in one mass. The flakes stay thin and crisp, and they bend and ride along with the jelly. The hands move slowly and deliberately, the way they would in a real squishy video. Summary: a top-down ASMR squishy film in one unbroken take in which two hands squeeze THE OBJECT until its thin painted skin splits into flakes and its soft jelly inside swells out, is kneaded and stretched, and is set down to settle. Timeline: 0–2s — The framing of @image1. The fingers press in slowly, the skin creases deeper around each fingertip, and a first thin crack runs across it with a soft papery crackle. 2–4s — The hands squeeze firmly. The skin splits open all around and curls away in large flakes, and the glossy tinted jelly swells out through the gaps and bulges up between the fingers. 4–7s — The hands knead the jelly slowly: they fold it over, press it with the thumbs and pull it gently apart between them, the flakes of skin turning and glinting inside it and the jelly stretching thick and glossy between the palms. 7–10s — The hands lower the jelly onto the background and let go, and move out of frame. The jelly slumps into a round glossy mound studded with the flakes of skin, wobbles softly a few times and comes to rest, catching the window light. Notes: THE OBJECT keeps exactly the colours and markings of @image1 on every flake of its skin for the whole film, and the jelly keeps the one colour it has in @image1. The same two bare hands appear throughout. The light stays exactly as @image1 has it. The camera stays above, looking straight down, with only a slow gentle drift closer as the jelly comes out, with no cuts, and the film runs as one unbroken take. No subtitles. No BGM; generate only environmental sounds and action sounds: a close intimate ASMR mix, dry and present — the soft papery crackle of the skin creasing, a crisp crunchy crackle as it splits into flakes, then the wet squelching, sticky squishing and soft pops of the jelly being kneaded and stretched between the hands, a soft heavy plop as it is set down, a gentle wobbling squish as it settles, and the quiet room tone of a calm bright room under everything to the last frame.

2 steps271.4K

Generate a small icon for social media.

Photoreal live-action capture throughout, handheld phone footage, natural available light, true-to-life colour. The first nine beats are older compressed phone video — softer resolution, warm blown highlights, light grain, small handheld wobble. The last three beats are clean modern phone video — sharp, steady, cool-neutral. No stylisation, no illustration, no animation, no cinematic colour grade. @image1 (earlier-state reference) is an absolute lock for the first nine beats: face, hair, body state, wardrobe, fabric and colour are taken from it exactly, with no drift or reinterpretation. @image2 (present-state reference) is the same absolute lock for the last three beats. It is the same person throughout — the face must read as identical across every beat. @image3 (storyboard) is to be followed exactly: same beat order, same locations, same framing, same pose, same caption placement. Each beat holds for a comparable length of time and carries a comparable amount of movement. No beat is rushed and none is held long. Beat 1. Two people stand side by side outside a house at dusk. The subject shifts weight, the shoulders ease, a small self-conscious smile arrives and settles. Beat 2. Alone on an open beach in low sun. The subject stands square to the lens, the loose shirt lifting slightly in the wind, the head tilting a fraction and coming back. Beat 3. Seated in profile on a covered veranda, a phone loose in one hand. The thumb moves once across it, the chin drops slightly, the shoulders fall on an out-breath. Beat 4. Standing indoors in a bright tiled room. The subject turns a small water bottle in one hand, the weight settles onto one leg, the jaw tightens briefly. Beat 5. Tight selfie framing at arm's length, the face filling the frame, speaking to the lens. The brows draw together, a slow blink, the head gives one small shake. Beat 6. Seated in profile against a moving vehicle window, landscape rushing past behind. The eyes narrow slightly and the jaw sets. Beat 7. Same seat, same window. A single slow blink, the chin lifting a fraction. Beat 8. Same seat, same window. The jaw clenches once and holds. Beat 9. Same seat, same window. The chin comes up the rest of the way and the shoulders square. Beat 10. Gym interior at night, a warm strip light glowing behind. Tight close profile, the chin lifted, the faintest smile arriving and staying. Beat 11. Bright gym training floor. Side view, full body, one controlled set at a loaded barbell — the bar draws in toward the waist, holds an instant, lowers under tension. Beat 12. Gym walkway in front of a wood-slat wall. Clean side view, the subject walking past the lens at an even pace, arms swinging naturally, the camera tracking alongside and holding the same distance until the end. Joins: every change of beat is a hard cut on the frame. No dissolve, no wipe, no morph, no speed ramp, no transition of any kind. Beats 6 through 9 share one continuous unbroken setup — identical seat, window, framing and light — and the cuts between them land without the camera moving. On-screen text, one caption per beat on beats 1 through 7 and beat 9, each appearing on that beat's first frame and clearing on its last: plain white sans-serif, no box, no outline, no bar or band behind it. Beat 1 — would you date me? Beat 2 — no, you're fat... Beat 3 — and that, umm… Beat 4 — that hurt, you know? Beat 5 — and I think that just flipped a switch in me Beat 6 — and I was like Beat 7 — Okey Beat 9 — watch this! Beats 8, 10, 11 and 12 carry no on-screen text at all. Audio: one unhurried spoken voice over beats 1 through 9, saying exactly the words written on screen and nothing else, recorded close and plain as if into a phone. It is a single voice throughout, quoting both halves of the remembered exchange rather than being answered by a second speaker. Beat 8 is silent. The last three beats carry only quiet room tone from the gym. Exclusions: no music, no lyrics, no score, no added sound effects. No words spoken that are not written on screen. No captions or subtitles beyond the eight listed. No camera orbit, no zoom, no push, no pull, no crane, no drone. No slow motion, no freeze frame, no still or duplicated frames. No second person in frame in any beat after the first. No mirrors, no phone or device screens visible, no on-screen interface. No logos, no watermarks, no brand marks, no gym signage, no end card, no title card.

4 steps1660

DUO DANCE — Sunny Park Swing @image1 and @image2 dance a playful swing routine together in a sunny park — side-by-side charleston kicks, hand-to-hand rock-steps, a swing-out and spin, to a bouncy swing beat. Music only, mixed loud. One continuous joyful take. Plug in ANY two avatars.

FULL-BODY GROOVE — Rooftop Afrobeats @image1 throws down real Afrobeats footwork on a golden-hour rooftop — Azonto, Shaku Shaku, Zanku legwork and Gwara Gwara, to a bouncy log-drum beat. Music only, mixed loud. One continuous grounded, high-energy take. Plug in ANY avatar.

80s AEROBICS POP @image1 leads a high-energy 80s aerobics-pop routine in a mirrored studio — grapevines, jumping jacks, side kicks and hip bumps snapping to a bright synth-pop beat. Music only, mixed loud. One continuous retro take, full of upbeat energy. Plug in ANY avatar.

Photoreal live-action capture, clean modern camera clarity, natural warm interior daylight, gentle shallow depth of field, neutral true-to-life colour grade. No stylisation, no illustration, no animation. @image1 (before-state reference) is an absolute lock for the first half: face, hair, body state, wardrobe, fabric and colour are taken from it exactly, with no drift or reinterpretation. @image2 (after-state reference) is the same absolute lock for the second half. It is the same person in both halves - the face must read as identical across the two. @image3 (room plate) sets the location, camera position, framing, lens and lighting, and these stay identical throughout, unchanged across the cut. The camera is locked off and never moves. One static medium shot, framed from mid-thigh to just above the head, the figure standing centred in the empty floor space with the bed and headboard behind. First half. The figure stands centred with its back to the lens. It begins one slow continuous turn in place, unhurried and even in speed: the spine rotates away, a three-quarter back view passes, then a clean side profile, then it arrives square to the lens looking straight down the barrel. Without pausing it carries the same rotation onward - the opposite profile passes, then a three-quarter back view, then the full back again - and rolls on to settle into a held side profile. Arms hang loose the whole way, hands relaxed, shoulders level, hair swinging slightly with the rotation. Then a hard cut. No dissolve, no wipe, no morph, no transition of any kind. Framing, camera position, lens, lighting and room are identical either side of it. Second half. The figure now stands open to the lens in a relaxed three-quarter stance, weight settled on one leg, and does not turn away again. It presents rather than inspects: small unhurried shifts of weight from one hip to the other, the head turning slightly toward the lens and easing back again, a slow settle of the shoulders, quiet natural breathing, hair moving a little with each turn of the head. The body stays open to camera from the cut to the end. On-screen text, both halves: plain white sans-serif, centred over the chest, no box, no outline, no bar behind it. In the first half the word is 69kg - it is there from the opening frame and fades cleanly once the figure has come round to face the lens. In the second half the word is 56kg - it appears on the first frame after the cut and fades cleanly once the stance has settled. Nothing else is written on screen at any point. Audio: a soft, low, even instrumental music bed only. Exclusions: no speech, no dialogue, no voice-over, no narration, no lyrics, no sound effects. No captions or subtitles beyond the two weight labels. No camera movement of any kind - no push, no pull, no pan, no tilt, no orbit, no handheld drift, no zoom. No cut other than the single hard cut between the halves. No second person in frame. No logos, no watermarks, no product, no end card.

4 steps736.4K

@image1 is a 3x3 storyboard reference. Its nine numbered frames define the order of the assembly, the studio viewpoint and the miniature model. The video plays these steps as one continuous full-frame vertical image, without the grid, gutters or numbers. @image2 is the closing-frame reference. It shows the finished full-size space exactly as the last frame must look, with the same framing, layout and lighting, and the video ends on a frame identical to it. Every element of the space, its design, material, colour and placement, comes from @image2, first at miniature scale and then at full size. In one continuous 15-second take with no cuts, one pair of realistic adult hands builds a miniature version of the space in @image2 step by step, in the order of @image1, on a seamless pure white studio sweep. Then a seamless scale match turns the miniature into the full-size space, and the video ends on @image2. Realistic live-action footage, crisp neutral whites, fine sensor grain. During the build the white sweep fills the frame edge to edge around the model, equally bright in every corner, flooded with strong, fully diffused light from every direction at once, as inside a large white light tent. Every surface of the model and the hands reads bright and evenly lit with true colours; only a faint soft darkening sits in the seams where two parts meet. Rules for the whole take: - The only body parts ever in frame are the two hands and their forearms, bare skin from the fingertips to the frame edge, with no sleeves, cuffs, gloves, rings, watches or bracelets. Each arm enters from the top, left or right edge and is cut off at mid-forearm by that edge. - Exactly one left hand and one right hand do all the work. Every part is gripped, carried and set by a single hand, and the two hands never hold the same part together. While one hand sets a part, the other carries the next part or rests at the frame edge. The hands move with quick, precise movements, and each finishes its placement before reaching for the next. - Every element enters only at the moment a hand places it. Until then its spot stays empty, and once placed it stays exactly where it was set. - The image stays clean from first frame to last: no text, titles, captions, numbers, logos, watermarks or overlays. - Every movement runs forward in normal time, and nothing moves in reverse. A wide shot opens on the plinth carrying only the bare floor, standing on the white sweep. The camera looks down at about 30 degrees, frontally and slightly from one side, matching @image1, and makes one slow, steady dolly push-in through the whole take. 1. A hand lowers the first bare wall onto the plinth edge and presses it down, and the remaining bare walls follow, one per hand. 2. The large built-in and fixed elements stand into place against the walls, one at a time. 3. The surfaces and fixed finishes that lie on top of them are lowered and pressed flush. 4. Appliances, fittings and fixtures are pushed and clicked into place, still unlit. 5. Free-standing furniture and any partitions or dividers are set down. 6. Lighting, textiles, rugs and plants are hung and placed. 7. The hands take turns placing the last loose objects and decor, each carrying one piece at a time. Then both hands withdraw past the frame edges and the model's lights glow on. 8. The frame holds only the model, with no body parts in view. The camera eases down to standing eye level and moves forward, and the miniature grows seamlessly into the full-size space. Only during this scale change does the white studio sweep give way to the real surroundings of @image2, its ceiling, its outer walls and its openings, as the light settles into the light of @image2. The shot lands on @image2 exactly and holds, with only small natural ambient motion. Steps 1 to 7 share the first twelve seconds evenly; step 8 takes the final three.

3 steps244