Prompts by Deniz Akkabak

FORMAT: 30 seconds / horizontal 4:3 / 1080p high bitrate / 24 fps, true real-time speed / premium automotive brand film / dynamic hard-cut montage, 15 shots / audio ON: SFX and ambience only, NO music. STYLE: Shot on ARRI Alexa 35 with ARRI Signature Prime lenses: creamy round bokeh, soft highlight roll-off, natural skin, true-to-life color, fine organic film grain, high dynamic range, shallow depth of field on close-ups. Natural late-afternoon sun raking across stucco walls, soft bounce in shadows, crisp glints on burgundy paint. Palette: burgundy, cream, warm beige, green foliage, magenta bougainvillea. Mediterranean old-city streets, real traffic, real physics. Every camera is a physical rig with mass and inertia: dolly, low car-mount, camera car, handheld with subtle natural micro-shake on walking shots, no floating gimbal look. One single film look across all shots. REFERENCES: @image1 defines the car ONLY: classic 1980s rear-engine coupe, deep burgundy metallic, round headlights, fastback roofline, black wheels with polished silver outer lips, black rubber bumper trims. Exact proportions and color. Ignore the shop signs and background. @image2 defines the phone ONLY: burgundy matte smartphone with the raised camera plateau of three lenses, back logo exactly as shown. Ignore the knit glove, cup, comb and tubes. @image3 defines the man's face, identity and FULL wardrobe: curly dark-brown hair, brown eyes, short beard and mustache, burgundy heavy-knit rugby sweatshirt with cream collar and placket, cream pleated wide-leg trousers, brown leather belt with silver buckle, chunky silver chain bracelet on his LEFT wrist, burgundy suede running sneakers with cream midsoles, black square sunglasses. Ignore the grid layout, labels, swatches and studio background. @image4 supports the SAME man's face and hair only: curl volume, beard density, skin texture, sunglasses shape. Ignore the grey T-shirt, table, food and tattoos. @image5 defines the final wordmark ONLY: the exact letters P O R S C H E in the black wide-spaced typeface, centered on off-white. VIDEO PROMPT: [ACT 1 — 0–10s: THE EXIT] Shot 1 (0–2.0s): Wide static frame from across the street. A cream stucco apartment building, dark wooden door, magenta bougainvillea over the entrance. The door swings open and the man steps out into the sunlight, sunglasses on, burgundy phone in his right hand. End state: on the top stone step, door closing behind him. Shot 2 (2.0–3.2s): Extreme close-up at ground level. His burgundy sneakers step down two stone steps toward the lens, suede texture crisp, a few fallen petals lift from the stone. End state: both feet on the pavement. Shot 3 (3.2–4.4s): Close handheld lateral tracking at waist height. Silver belt buckle, trouser pleats moving with each stride, left arm swinging with the bracelet catching sun, phone held loosely in his right hand. End state: he walks out of frame right. Shot 4 (4.4–5.8s): Medium close-up, backward-moving handheld in front of him. Sunglasses reflecting the street, curls bouncing with each step, cream collar sharp against burgundy knit, calm confident micro-smile, background in creamy bokeh. End state: he glances right toward the car. Shot 5 (5.8–7.4s): Low wide, lens at bumper height behind the front corner of the parked burgundy coupe, car sharp in foreground. He walks in, pulls the chrome handle, the door opens with real weight. End state: he lowers himself in. Shot 6 (7.4–8.8s): Interior static wide from the passenger side. He drops into the driver seat and with a short relaxed flick of his right hand tosses the phone onto the passenger seat. It lands flat on the leather, bounces once, settles. End state: phone resting on the passenger seat, his hands free. Shot 7 (8.8–10.0s): Exterior close-up as he pulls the door shut with a solid heavy close, the window reflecting bougainvillea. [ACT 2 — 10–20s: THE LAUNCH] Shot 8 (10.0–11.2s): Interior extreme close-up: his hand turns the key, the analog tachometer needle jumps, then he snaps the gear lever into first. Shot 9 (11.2–14.5s): Static low rear angle, camera on the asphalt two meters behind the car, centered. The engine revs, the rear tires spin in place for about one second, a light veil of white tire smoke curls from both rear tires, the rear steps out a few centimeters left, then right as the tires bite, the body squats with real weight transfer and the coupe launches straight away down the street. Smoke drifts toward the lens and thins. End state: car shrinking into the distance. Shot 10 (14.5–17.0s): Low front three-quarter camera-car tracking, lens just above the asphalt, the car holding position in frame through a sunlit city street. Normal traffic flows: cars ahead and in the opposite lane, a scooter, pedestrians. He changes lanes cleanly and passes a slower car. Speed shown by asphalt streaming under the lens and buildings flowing past. Shot 11 (17.0–20.0s): Interior over-the-shoulder from behind-right. His right hand shifts up a gear, left hand on the thin wheel, the windshield framing the city and traffic ahead, sunlight flickering across the dashboard. The phone still rests on the passenger seat. [ACT 3 — 20–30s: THE SIGNATURE] Shot 12 (20.0–22.5s): Side tracking at wheel height from a camera car in the next lane. Rear wheel rotating with real motion blur, burgundy flank catching glints, storefronts streaming behind. End state: the coupe pulls ahead. Shot 13 (22.5–24.5s): High static vantage from a rooftop. The coupe turns through a city intersection in a smooth controlled arc between normal traffic, its long shadow on warm asphalt. End state: exits frame right. Shot 14 (24.5–28.0s): Locked-off perfect side profile wide, long lens across a clean empty street, camera completely still and level, cream stucco wall with bougainvillea behind. At 25s the coupe enters from frame left at speed, crosses in full side profile and exits frame right at 26.5s. The car's rear edge acts as a vertical sweep line: everything behind it wipes left to right into a clean off-white field, revealing the black PORSCHE wordmark from @image5 letter by letter in the car's wake, exactly centered. End state at 27s: full frame off-white, complete wordmark centered, street gone. Shot 15 (28.0–30.0s): Held final frame: off-white field, black wordmark PORSCHE centered and sharp, nothing else, completely still to the end. AUDIO: No music at any time. Diegetic SFX and ambience only, synced to each shot. 0–5.8s: <wooden door unlatching and creaking open> <birds in the bougainvillea> <distant city hum> <crisp sneaker soles on stone steps> <footsteps on pavement> <fabric swish> <faint bracelet clink>. 5.8–10s: <door handle click> <old hinges> <leather seat creak> <soft thud of the phone landing on leather> <deep solid door slam, then muffled interior quiet>. 10–14.5s: <key turning> <starter crank> <air-cooled flat-six catching with a sharp bark> <two throttle blips> <gear lever clack> <rising rev> <short high tire squeal and rubber scrub> <engine roar fading down the street>. 14.5–24.5s: <engine rising and falling through gear shifts> <wind rush> <tire hum on asphalt> <normal city traffic both directions> <distant short horn> <scooter buzz> <tire hiss through the corner>. 24.5–28s: <quiet empty street, one bird> <engine approaching from the left, a fast loud Doppler pass across the stereo field left to right> <soft air rush trailing the wipe>. 28–30s: <near silence, faint airy tail>. No dialogue, no voices, no narration. CONSISTENCY: Exactly one man, the same man from @image3 and @image4 in every shot: same face, curls and beard. Black square sunglasses stay ON in every shot, never removed. Wardrobe never changes. Exactly one car, the burgundy coupe from @image1 with the same wheels. Exactly one burgundy phone: in his right hand until Shot 6, then on the passenger seat for the rest of the film, never moving. Left-hand drive. Travel direction left to right in Shots 12 to 14. Same late-afternoon sun in every shot. Real-time speed in every shot. Final wordmark matches @image5 exactly. NEGATIVE PROMPT: no music, no voices, no narration, no slow motion, no speed ramping, no time-lapse, no removing the sunglasses, no wardrobe change, no different face, no extra people near the man, no second car, no different car color, no phone duplication, no phone falling, no huge smoke cloud, no crash, no collision, no near-miss, no misspelled letters, no extra text, no subtitles, no watermark, no license plate text, no CGI look, no plastic skin, no warped wheels, no wobbling geometry, no floating gimbal motion, no drone, no camera or crew visible, no split screen, no collage, no grid layout, no studio background.

FORMAT: 30-second cinematic multi-shot sequence, 4:3, 1080p, native dialogue and sound. Hard cuts between shots, real-time action, no slow motion. STYLE: A real police-station scene filmed on an iPhone, with the texture of an ARRI Alexa and ARRI Signature Prime lenses: low contrast, lifted blacks, soft highlight roll-off, creamy falloff, muted desaturated grade, fine grain. Handheld micro-shake, no smooth gimbal, except the lineup tracking shot. Lineup room: cold flat fluorescent light. Observation room: dark, lit only through the glass. REFERENCES: @Image 1: LOCATION, BLOCKING AND GRADE. The observation room, the one-way glass, the lineup wall, the four suspects holding cards 1 to 4, the old woman and the detective in the foreground. Not a first frame: start with gentle movement. @Image 2: SUSPECT 1, the platinum-ponytail woman. Character sheet: face, hair, outfit, silver hoops, nose stud. @Image 3: SUSPECT 2, the young man with black glasses. Character sheet. @Image 4: SUSPECT 3, the moustached man with cap and headphones. Character sheet. @Image 5: SUSPECT 4, the curly-haired man in the burgundy leather jacket. Character sheet: outfit and identity. @Image 6: THE OLD WOMAN. Character sheet. @Image 7: THE DETECTIVE. Character sheet. @Image 8: THE BOOK, with its deep red paper belly band. Use the front cover exactly as shown. @Image 9: SUSPECT 4 FACE SUPPORT. A real photo of the same man: use only his face to sharpen the likeness, bone structure, eyes, nose, moustache and goatee. Ignore clothing, room and selfie light. Character sheets: restore each face precisely in every shot; ignore grids, labels and grey backgrounds. VIDEO PROMPT: 0.0 to 2.0s. Exactly the framing of @Image 1: behind the old woman and the detective, looking through the glass at the four suspects. The camera eases in slowly. 2.0 to 4.0s. Close-up of the detective from the glass side, the lineup reflected in his lenses. He points his notebook at the glass, dry and tired. {So, ma'am. Which ones are AI?} 4.0 to 5.5s. Close-up of the old woman leaning toward the glass, eyes narrowing, studying each face. 5.5 to 16.5s. Inside the lineup room, one continuous smooth lateral tracking shot on a dolly at chest height, gliding left to right without ever stopping, pushing in and drifting back out as it passes each suspect. 5.5 to 8.5s. Suspect 1 in close-up, chewing gum slowly, bored, eyes half-lidded, unbothered. {She will never figure it out.} 8.5 to 11.0s. The camera drifts in to an extreme close-up of Suspect 2's forehead: a single drop of sweat runs from his hairline down past his glasses. It eases back to the wide sliding angle; he lifts his chin, trying to stay cool, eyes flicking nervously. {It is pretty obvious I am real.} 11.0 to 14.0s. Suspect 3, jittery: sniffing, rubbing his nose, bouncing on his heels, scratching his neck, eyes darting, card trembling. He repeats fast under his breath. {Not me. Not me. Not me. Not me.} 14.0 to 16.5s. The camera reaches Suspect 4, relaxed, leaning slightly back. It pushes in very close to his mouth as one corner slowly pulls into a cool half smile. The track ends here. 16.5 to 18.0s. Hard cut: close-up of the old woman, quiet and certain. {One, two and three.} 18.0 to 20.5s. Lineup room, wide. A steel side door opens; the detective and two uniformed officers walk in. The detective stops at Suspect 4, tilting his head to the door. {Number four. You are free to go.} 20.5 to 23.0s. Officers cuff Suspects 1, 2 and 3: the woman rolls her eyes chewing, the young man stares in shock, the moustached man mouths silently. Suspect 4 drops his card and walks out. 23.0 to 26.0s. A police-station corridor at a property counter. A bored officer slides him a canvas tote bag. {Your belongings.} He takes it with a small nod. 26.0 to 30.0s. Over-the-shoulder from behind his right shoulder at head height as he walks down the corridor: he pulls the black hardcover book from @Image 8 out of the tote and holds it in front of his chest with both hands, cover up, looking down at it. The camera pushes in over his shoulder; he slows and stops. The cover reads exactly: ULTIMATE CINEMATIC REALISM BLUEPRINT, the arcads logo, six portraits numbered 01 to 06, and the red band: FREE TRIAL · 1,000 FREE CREDITS, FOR ALL NEW ARCADS CUSTOMERS, as on @Image 8. Final 1.5 seconds hold on the cover, sharp. AUDIO: Diegetic sound effects only, no music. Fluorescent hum. Gum chewing on Suspect 1. Sniffing and shuffling feet on Suspect 3. <steel door buzzer and clunk> at 18.0s. <handcuffs clicking shut> at 21.0s, 21.6s and 22.2s. Footsteps on linoleum. <canvas tote sliding on the counter> at 23.5s. Soft rustle of the book from 26.5s. VOICES: DETECTIVE: male, mid-fifties, low dry American English voice, slightly gravelly, weary and unhurried. OLD WOMAN: female, seventies, soft American English voice, shaky but firm. SUSPECT 1: female, early twenties, flat bored American English voice with vocal fry, gum in her mouth, smug. SUSPECT 2: male, mid-twenties, American English, trying to sound calm, his voice cracking slightly. SUSPECT 3: male, thirties, American English, fast, breathy, high-strung, muttering. OFFICER: male, forties, flat bored American English voice. SUSPECT 4 never speaks. Each line is spoken once, by its own character, in the shot where it appears. CONSISTENCY: Every face matches its character sheet in every shot; Suspect 4 also matches @Image 9. Card numbers never change. Suspect 1 chews gum throughout. Suspect 2 keeps his glasses on. Suspect 3 keeps cap, headphones and glasses on. Suspect 4 never wears sunglasses. The tracking shot moves left to right only and never stops. The book cover is identical to @Image 8. NEGATIVE PROMPT: music, extra spoken words, narration of the prompt, subtitles, captions, changed faces, swapped card numbers, sunglasses on Suspect 4, garbled book title or band text, stuttering camera, character sheet grids or labels, high contrast, crushed blacks, slow motion, watermark

FORMAT 15 seconds, 16:9, two shots from the exact same camera position and angle: Shot 1 (0.0s to 10.0s) one continuous take, a hard jump cut at 10.0s with no change of camera angle, Shot 2 (10.0s to 15.0s) one continuous take. STYLE Ultra realistic handheld phone footage at night, real-world physics, natural practical lighting from tall warm floodlights over a wide concrete lot, light sensor noise, high dynamic range, no CGI look. REFERENCES @video1: motion, camera and choreography reference ONLY. Copy its framing, camera distance, handheld shake, timing and the man's full movement 1:1: walk-in, turn to camera, the card move, the hand wipe across the lens that reveals the car. Also copy the location (night concrete lot, floodlights, yellow lines). Replace the man with @image2 and the car with @image1. Ignore the original man and the blue-striped car completely. @image1: the car, every angle. Exact body, proportions, matte white upper body, black lower body, dark tinted glass roof, thin white front light bar, full-width red rear light bar, black six-spoke wheels, rear wing, four round rear thruster outlets, RDSTR plate. Ignore the grid layout, labels and studio background. @image2: Deniz, face, identity and wardrobe. Curly dark brown hair, full beard and mustache, black sunglasses ON at all times, color-blocked Kith short-sleeve shirt (dark green, beige, sage, cream), dark green bandana knotted at the neck, light linen trousers rolled at the hem, grey New Balance sneakers. Ignore the grid layout, labels and studio background. @image3: lift-off reference ONLY. Copy how the car hovers on four vertical columns of white pressurized vapor blasting down from its underside. Ignore its black background, stage lights, watermark and wheel design. @image4: doors and nozzles reference ONLY. Copy exactly how the two doors hinge at the front of the roof and stand raised up and forward, the warm amber cabin glow, and the four short metal air nozzles under the side sills. Ignore its starry desert setting and the person inside. VIDEO PROMPT Ground set-up: dry autumn leaves (brown, ochre, faded yellow) lie scattered thinly across the concrete everywhere, with a denser loose drift on the empty spot behind Deniz where the car will appear. Visible from the first frame. SHOT 1 (0.0s to 10.0s), handheld phone held close, exactly like @video1: 0.0s to 2.5s: Deniz walks in from frame right into a close medium shot, glances back over his left shoulder at the empty lot, then turns and faces the lens. 2.5s to 3.6s: he pulls a card from his pocket and fans out the same two green +2 playing cards seen in @video1, holding them up close to the lens. 3.6s to 4.6s: he holds the cards steady toward the lens for a beat. 4.6s to 5.0s: he flicks his hand quickly upward across the lens, his hand fills the frame with motion blur, a natural wipe. 5.0s: as the hand clears, the car from @image1 is standing behind him in the exact spot and angle of the car in @video1: front three-quarter view, nose toward frame left, parked on the leaf drift. Both doors are already wide open, raised up and forward exactly like @image4, warm amber cabin glow spilling onto the leaves. 5.0s to 10.0s: Deniz glances back at the car, looks back at the lens with a calm, cool smirk, a small nod, points his thumb over his shoulder at the car, then turns and walks out of frame to the left toward the car. Deniz does not speak. SHOT 2 (10.0s to 15.0s), hard jump cut, the camera stays in exactly the same position, height and angle as the end of Shot 1, same handheld feel. The car is in the same spot with both doors open. 10.0s to 11.0s: Deniz is at the open door, steps in with one smooth stride, lowers into the seat and settles, sunglasses on. 11.0s to 11.9s: both doors swing down along the hinge path of @image4 and seal flush, amber glow cut off, the front light bar brightens. 11.9s to 13.4s: the four sill nozzles from @image4 hiss and push soft white vapor columns down. The car lifts gently and lightly off the ground, not perfectly straight: a tiny natural wobble as it finds its balance, a slight roll to one side and a small pitch correction, then it steadies and hovers about one meter up. Leaves skitter outward and lift in lazy swirls. 13.4s to 14.2s: the four round thruster outlets at the rear fire at once with a hard burst of white pressurized air. The car shoots forward toward frame left at a tremendous speed, nose leading, slightly low and level, and leaves the frame in a fraction of a second. The camera stays put, only a small handheld jolt from the shockwave. 14.2s to 15.0s: the blast wave throws a dense storm of leaves straight at the camera, leaves tumble and whip across the lens and past it, vapor trail hanging in the air where the car was. End state at 15.0s: empty lot, no car in frame, leaves still flying past the lens and drifting down, thin vapor settling. CONSISTENCY Deniz matches @image2 exactly in both shots: same face, curly hair, beard, wardrobe and bandana. Sunglasses stay on his face for the entire video and are never removed. The car matches @image1 exactly in both shots: same body, colors, lights, wheels and plate. The car keeps its orientation throughout, nose always leading, front and rear never swap. The downward vapor columns stay visible from lift-off until the car exits. Camera angle is identical before and after the cut. Leaves are on the ground from the first frame. Camera shake matches @video1 1:1, never smoother. NEGATIVE PROMPT blue-striped car, original man from @video1, sunglasses off, speaking, lip movement, smooth gimbal, stabilized camera, camera angle change at the cut, doors closed at the reveal, car changing shape or color, front and rear swapped, car rotating, flipping or spinning, stiff perfectly straight lift-off, slow drift exit, rocket flames, fire, explosion, flash or glow on car reveal, doors moving differently from @image4, grid layout, labels, text overlays, watermark, CGI look, cartoonish motion.

SEEDANCE 2.5 · 12 S · ONE CONTINUOUS HANDHELD SHOT FORMAT: 16:9, 12 seconds, one continuous handheld shot, no cuts, real-time. REFERENCES: @Image 1 = reference only, NOT the first frame: use it for the packed bullring with the white-and-gold arcades, the red wooden barrier, the raked sand arena, the black bull, the white car standing in the sand with the matador in his gold-embroidered suit at the wheel, leaning out of the open driver window with the red cape, the spectators in straw hats in the foreground, the warm late-afternoon sun. The video does not open on this image and does not copy its framing; it reaches the action on its own. The car's nose points to the right toward the bull, its rear to the left. @Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing. @Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car. TIMELINE: 0-3s: someone in the stands behind the straw hats holds the phone up and zooms jerkily to 3x on the bull: it paws the sand with one front hoof, kicking sand backward, snorts, lowers its head and points its horns at the car. 3-5s: the camera swings left late, still zoomed, onto the car: the matador leans out of the driver window and shakes the red cape at the bull, taunting it. Autofocus hunts between the cape and the car. 5-8s: the zoom pumps back out to the wide arena: the bull charges across the sand straight at the car; just before the horns reach the door, the four air jets fire with a sharp hiss, sand explodes outward and the car shoots straight up; the bull thunders through underneath, into the sand cloud. 8-12s: in the air the car does one full forward flip, nose dipping down and coming all the way around, carrying forward over the bull, and lands on the sand beyond it, bouncing on its suspension and sliding to a stop, nose still pointing right; the bull skids, turns and looks around, confused. The whole arena leaps to its feet, hats waving in the air; the people in front stand up and block the view, the camera lifts higher and shakes wildly. Ends on this chaos. CAMERA: filmed on an iPhone by someone in the stands holding the phone up over the straw hats: the action stays small to medium in the frame, never a close-up; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between the hats and the arena, auto-exposure pumping between sun and shade, rolling-shutter wobble on fast moves, out-of-focus hats and heads partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible. STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic. MOTION: true real-time speed, real physics: the bull is heavy and fast, the car has weight, the jets blast real sand, the flip is one continuous rotation forward over the bull, the landing is hard with real suspension bounce. The car is one rigid object: front always at the front, rear always at the rear. AUDIO: crowd murmuring close to the phone, the bull snorting, hoof scraping sand, scattered whistles, the bull's hooves thundering, a rising electric whine, a loud pressurized air hiss and roar, a heavy thud of the landing, then the whole arena erupting in screams and cheers. No music, no clear words. NEGATIVE PROMPT: slow motion, starting on the reference image, close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, fire, flames, rocket exhaust, wings, propellers, explosion, crash, the bull being hit or hurt, blood, the car hitting the bull, front and rear swapping, the car turning around, drone, CGI look, morphing, car shape changing, the bull changing shape, extra legs, extra limbs, people appearing from nowhere.

FORMAT: 16:9, 15 seconds, one continuous handheld shot, no cuts, real-time. REFERENCES: @Image 1 = reference only, NOT the first frame: use it for the misty rocky valley with the stream, the cave mouth, the small campfire with blue smoke, the long-haired caveman in fur pushing the round stone wheel with a hole in the middle, the tribe in furs around the fire (the old grey-bearded elder, the man with the spear, the women, the small child), the rough rocks framing the view in the foreground, the flat misty light. The video does not open on this image and does not copy its framing; there is NO car anywhere in the valley at the start, and it starts a little earlier, with the caveman still rolling the wheel toward the tribe. @Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing. @Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car. TIMELINE: 0-4s: someone hiding behind the rocks films through the gap between them: the caveman rolls the stone wheel the last few meters, stops it, slaps it proudly with both hands and points at it, grunting to the tribe; they stare at it, the child points too. No car in sight, the valley is empty. 4-8s: the tribe erupts: primal whoops, they rush in, lift the caveman up onto their shoulders and bounce him up and down, spears and fists raised, the child jumping around the wheel, the elder clapping. 8-11s: in the middle of the celebration, the white car comes flying low out of the misty valley on its air jets, dust trailing, sweeps from left to right right in front of the tribe, does one fast sideways roll around its own long axis as it passes, nose always pointing the way it is flying, and shoots off out of frame to the right. A wave of dust and smoke washes over everyone; the tribe freezes mid-cheer, the caveman still up on their shoulders. 11-15s: a sudden jerky digital zoom pushes in very close on the caveman's face: wide eyes, mouth hanging open, staring after the car, then slowly looking down at his stone wheel. The zoom is soft, grainy and slightly pixelated, autofocus hunting on his face, small shakes. Ends on his stunned face. CAMERA: filmed on an iPhone by someone hidden behind the rocks holding the phone in the gap: the action stays small to medium in the frame until the final beat, which is a very close but soft, grainy digital zoom on the caveman's face; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between the foreground rocks and the tribe, auto-exposure pumping against the bright misty sky, rolling-shutter wobble on fast moves, the out-of-focus rocks framing and partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible. STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic. MOTION: true real-time speed, real physics: the stone wheel is heavy, the car has weight, the jets kick up real dust and push the campfire smoke, the roll is one continuous rotation around the car's long axis only. The car is one rigid object: front always at the front, rear always at the rear. AUDIO: wind through the valley, the stream trickling, the campfire crackling, the heavy stone wheel grinding over gravel, grunts, primal whoops and stomping, a rising electric whine, a loud pressurized air hiss and roar sweeping past from left to right, gravel and dust pattering down, then sudden silence and the wind. No music, no clear words. NEGATIVE PROMPT: slow motion, starting on the reference image, car visible at the start, sharp clean close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, rocket exhaust, wings, propellers, explosion, crash, the car hitting anyone, injuries, front and rear swapping, the car turning around, end-over-end flip, drone, CGI look, morphing, car shape changing, the caveman's face changing, the stone wheel changing shape, extra limbs, people appearing from nowhere.

SEEDANCE 2.5 · @IMAGE 1 = STILL (REFERENCE ONLY) · 10S · 1080P · AUDIO ON FORMAT: 16:9, 10 seconds, one continuous handheld shot, no cuts, real-time. REFERENCE: @Image 1 = reference only, NOT the first frame: use it for the Giza plateau, the quarry stones, the Pharaoh at address with the golf driver facing the Sphinx, the Sphinx straight ahead in the line of the shot, the pyramids, the caddy, the parasol bearers, the priests, costumes and light. The video does not open on this image and does not copy its framing; it can start from further away and reach the moment on its own. TIMELINE: 0-3s: from behind the quarry stones, the camera peeks over the edge and finds the little group; the Pharaoh, seen from behind, waggles the club and swings; the ball shoots straight forward, away from the camera, toward the Sphinx. 3-6s: the phone does a frantic jerky zoom toward the Sphinx far ahead, losing and finding focus: the tiny ball hits the Sphinx's face and a moment later the stone nose cracks off and drops onto the sand in a puff of dust. 6-10s: the phone zooms back out shakily: the priests slowly turn their heads toward the Pharaoh; he silently hands the club to the caddy, takes a new ball and puts it on the tee. The person filming ducks back down behind the stones. CAMERA: filmed secretly on an iPhone by a quarry worker hiding behind stone blocks: the group stays small in the frame, never a close-up; shaky handheld drift, sudden jerky 2x–3x digital zooms in and out with zoom softness and morning haze, autofocus hunting at the long distance, auto-exposure pumping, rolling-shutter wobble, the stone edge partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible. STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic. MOTION: true real-time speed; the ball only travels forward, from the tee in the direction of the swing, to the Sphinx. AUDIO: desert wind on the microphone, the distant crack of a golf drive, a very faint far-away crack and thud, a long silence, someone gasping close to the phone. No music. NEGATIVE PROMPT: ball flying backwards, ball changing direction, slow motion, starting on the reference image, close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, no music, fingers or hands of the operator, camera interface, text overlays, CGI look, morphing, extra limbs, people appearing from nowhere, logos.

SEEDANCE 2.5 · REFERENCE TO VIDEO · 30 S FORMAT: 30-second cinematic multi-shot sequence, 4:3, 1080p, native dialogue and sound. Hard cuts between shots, real-time action, no slow motion. STYLE: A real night scene filmed on an iPhone, with the texture of an ARRI Alexa and ARRI Signature Prime lenses: low contrast, lifted blacks, soft highlight roll-off, creamy background falloff, muted desaturated grade, fine sensor grain. Handheld operator with natural micro-shake and small breathing drift, no smooth gimbal. Warm amber light from the canopy lanterns and downlights, cool blue-hour sky ambient, wet stone pavement with soft reflections. The penlight is a small hard cool-white source. REFERENCES: @Image 1: LOCATION, BLOCKING AND GRADE ONLY. The hotel entrance under the coffered canopy with hanging brass lanterns, the brass stanchions with black velvet ropes, the round brushed-steel hatch set flush into the wet pavement, the queue receding along the facade, the guard standing to the right of the hatch. Not a first frame: the woman starts one step behind the hatch, not on it. @Image 2: THE WOMAN. Character sheet: face, black layered hair with wispy bangs, septum ring, freckles, oversized white Racing 90 tee over sheer black lace sleeves, black satin slip skirt, red bead necklace, red patent shoulder bag, black Mary Jane flats. Ignore the grid, labels and studio background. @Image 3: THE YOUNG MAN. Character sheet: face, messy black fringe, thin round silver wire glasses, stud earrings, black leather jacket, white shirt, red tie, black wide trousers with a silver chain, chunky black shoes. Ignore the grid, labels and studio background. @Image 4: THE CURLY-HAIRED MAN. Character sheet: face, short dense curly dark brown hair, moustache and goatee with stubble, brown eyes, glossy crinkled burgundy leather bomber jacket worn open, white button-up shirt, cream straight-leg jeans, burgundy suede running sneakers, black square sunglasses. Ignore the grid, labels and studio background. @Image 5: THE GUARD. Character sheet: face, swept-back dark hair, stubble, stern eyes, black button-up shirt, black trousers, black belt, clear coiled earpiece, small black aluminium penlight. Ignore the grid, labels and studio background. @Image 6: THE BOOK. A black linen hardcover; use the front cover design exactly as shown. Use every character sheet to restore each face precisely: same bone structure, skin texture, hair and proportions in every shot. VIDEO PROMPT: 0.0 to 3.0s. Over-the-shoulder from behind the guard, his right shoulder and the back of his head large in the right of frame, earpiece coil visible, exactly the diagonal of @Image 1. The woman stands at the front of the queue, one step behind the steel hatch. She steps forward and plants both feet on the centre of the hatch. The guard lifts the penlight to her eye level, clicks it on and holds the beam on her face. She squints and tilts her head away. The guard speaks, flat and dry. {Are you a real person?} 3.0 to 5.0s. Reverse medium close-up on the woman, eye level, the guard's black shoulder soft in the left foreground. The cool beam hits her eyes and cheek, the rest of her face in warm canopy light. She answers with an offended little smile. {Of course.} 5.0 to 6.5s. Close-up on the guard, slightly low angle, the penlight glare blooming in the lower foreground. He does not blink. {AI.} 6.5 to 9.0s. Close-up on the woman, she leans in, mouth open in outrage, hand flicking at the light, bag strap sliding on her shoulder. {Oh my God, are you kidding me? I am real.} 9.0 to 10.0s. Close-up on the guard, deadpan, one small shake of the head. {Nope.} 10.0 to 11.5s. Top-down shot straight above the hatch. The two steel half-doors split along the centre seam and swing down with a heavy mechanical clunk. The woman drops straight down out of view into darkness, unhurt, her bag following. 11.5 to 13.5s. Camera inside the dark shaft looking straight up through the open round hatch: a bright circle of canopy light, lantern glow and wet rim. The young man from @Image 3 leans over the edge and peers down, glasses catching the light, faces of the queue behind him. The guard's voice comes from above. {Next.} The half-doors swing up and slam shut, frame to black. 13.5 to 16.0s. Over-the-shoulder behind the guard again, same diagonal as the opening. The young man steps onto the hatch, pushes his glasses up, chin raised, cool. The beam hits his face and reflects as two small dots in his lenses. {I am real, man.} 16.0 to 18.0s. Close-up on the guard, flat. {Nope.} Cut wide: the half-doors drop, the young man vanishes straight down, tie flicking upward, the doors snap shut. Behind the rope the curly-haired man, sunglasses on, tilts his chin slightly, unbothered. 18.0 to 20.0s. Medium shot from the guard's side. The curly-haired man from @Image 4 strolls forward wearing the black sunglasses. As his foot lands on the hatch he takes the sunglasses off with his right hand in one smooth unhurried move and folds them, a small half-smile. The guard raises the penlight to his bare eyes. He answers calmly. {Real as it gets.} 20.0 to 22.0s. Extreme macro close-up of the curly-haired man's right eye filling the frame: brown iris fibres, wet tear film, individual lashes, fine skin texture at the edge. The penlight beam enters and the pupil visibly constricts in a quick smooth reflex, the bright point reflecting on the cornea. The beam slides away and the pupil slowly widens back. Fine skin texture, real moisture. 22.0 to 23.5s. Medium close-up on the guard. He clicks the light off, gives one short nod and unhooks the velvet rope with his free hand. {All right. You are in.} 23.5 to 26.5s. Tracking from behind, low shoulder height: the curly-haired man walks past the guard toward the glass doors, easy rolling stride, burgundy leather catching the lantern light, folded sunglasses in his right hand. Over his right shoulder we look down at his left hand: he carries the black hardcover book from @Image 6, cover facing up, swinging gently with each step. Lantern light slides across the cloth. 26.5 to 30.0s. Close-up on the book in his hand as he walks, camera matching his pace, then he slows and the cover holds steady and sharp to the end. The cover reads exactly, in large white condensed letters: ULTIMATE CINEMATIC REALISM BLUEPRINT, with the arcads logo underneath and the film strip of four portraits below, exactly as on @Image 6. Final 1.5 seconds hold on the cover. AUDIO: Diegetic only, no music. City night ambience under everything: distant traffic, soft crowd murmur from the queue, a faint drip from the canopy edge, footsteps on wet stone. <penlight click> at 1.5s and again at 22.0s. <heavy steel latch clunk and hydraulic hiss> at 10.0s and 16.5s. A short surprised yelp from each falling character fading downward. <hatch slam echoing in the shaft> at 13.0s. <velvet rope hook unclipping> at 22.8s. Soft cloth rustle of the book against his hand from 24.0s. VOICES: GUARD: male, mid forties, low flat American English voice, dry, clipped, quiet authority, never shouting. WOMAN: female, early twenties, American English, slightly husky alt-girl voice, offended and rising into disbelief. YOUNG MAN: male, about twenty, soft light tenor, American English with a subtle Korean accent, cool and a little mumbled. CURLY-HAIRED MAN: male, mid-thirties, natural American English accent, smooth warm baritone with a slight husky grain, relaxed and effortlessly confident, a subtle smile in the voice, clear articulation, never shouting. Each line is spoken once, by its own character, in the shot where it appears. CONSISTENCY: Every face matches its character sheet exactly in every shot. The guard keeps the earpiece and the black penlight in his right hand for the whole video; the penlight never leaves his hand. The young man never removes his round wire glasses. The curly-haired man wears the sunglasses until he stands on the hatch, removes them there and never puts them back on. The woman keeps the red bag on her shoulder until she drops. Queue order never changes: woman, young man, curly-haired man, then strangers. The hatch is the same round steel hatch in every shot. Location, lanterns and low-contrast grade stay identical. The book cover is identical to @Image 6. NEGATIVE PROMPT: cars, high contrast, crushed blacks, oversaturated color, smooth gimbal, slow motion, character sheet grids or labels, subtitles, captions, extra spoken words, narration of the prompt, garbled book title, changed faces, young man's glasses removed, teal cap, tattoos on the curly-haired man, sunglasses back on after removal, extra people on the hatch, injury, blood, watermark

VIDEO BRIEF · SEND IN THE SAME CLAUDE CHAT create a funny influencer video of this character getting into funny, ridiculous situations in real life and then edit the video in the invideo Editor.

SEEDANCE 2.5 · REFERENCE TO VIDEO · 9:16 · 14S · UNIVERSAL FORMAT: Vertical 9:16, 1080p, 14 seconds. Eight shots joined by hard cuts, exactly like @Video 1: same number of shots, same cut points, same shot order, same framing and same camera behavior inside each shot. STYLE: Ultra realistic live-action automotive film, real world physics, natural bright sunlight, deep blue sky, high dynamic range, fine 35mm film grain, shallow depth of field on the low shots, real reflections on the car's paint and glass, premium commercial look. Soft vintage anamorphic texture exactly like @Video 1: oval bokeh, thin horizontal streak flares on sun glints, gentle highlight bloom, slight edge falloff. Full vertical frame, no black bars. Not CGI, not 3D render, not game engine. REFERENCES: @Video 1 = THE MASTER. Copy everything from it 1:1: shot list, cut timing, camera heights, angles, framing, push-ins, drifts and its exact handheld micro-shake. Keep its whole world unchanged: the giant twisted tree, the curved green grass hill, the tiny yellow wildflowers, the blue sky, the sunlight, the wind and the bee. The ONLY thing to replace is the car in it. @Image 1 = THE CAR. The exact car from this image: make, model, body shape, proportions, paint color and finish, wheels, lights, trim and every design detail. Doors exactly as shown in @Image 1, open or closed. Ignore its background. VIDEO PROMPT: The car from @Image 1 replaces the car in @Video 1. It stands in the exact same spot on the grass hill, at the same angle and with a believable real-world size, tires resting naturally in the grass. The giant tree towers behind it, monumental and majestic. A strong warm wind blows the whole time: the grass ripples in waves, the canopy sways, leaves, grass blades and seed fluff fly across the frame, yellow flowers bend and shake. The car is perfectly still. CAMERA SHAKE, EVERY SHOT: handheld, low in the grass, constant subtle organic micro-shake on all axes, a tiny horizon roll wobble, a soft breathing sway on top of slow creeping push-ins, exactly like @Video 1. Never stabilized. 0.0-3.5s: low wide shot from inside the grass, rear three quarter view of the car under the giant tree canopy, slow push in. 3.5-4.6s: extreme low close shot on the front wheel, grass and yellow flowers whipping in the foreground. 4.6-6.0s: low close front shot, the nose and headlights filling the frame, slow push in, leaves streaking past. 6.0-7.7s: low wide front shot, the car centered under the canopy. A honey bee zips past very close to the lens, soft out of focus, then is gone. 7.7-9.0s: low side close shot along the door, window and side panel, slow lateral slide against the blue sky. 9.0-10.7s: high overhead angle looking down at the car on the grass, wind waves rippling around it. 10.7-11.8s: low rear wide shot, the car small under the giant tree. 11.8-14.0s: extreme wide shot, the full tree on the curved hill, the car tiny beneath it. End on this frame. AUDIO: No music at all. Natural sound design only, continuous across the cuts, exactly like @Video 1: strong gusting wind, dense grass rustling, the canopy roaring softly, leaves fluttering, an occasional deep creak from the old trunk, distant birds. At 6.0-7.7s a close bee buzz passes the lens with a sharp doppler sweep. No dialogue. CONSISTENCY: Same car from @Image 1 in every shot: shape, paint, wheels, lights and doors never change. Same tree, hill, light and sun direction as @Video 1 in every shot. The car never moves. Wind never stops. Cut timing, camera movement and handheld shake match @Video 1 exactly. NEGATIVE PROMPT: the original car from @Video 1, mixed car designs, stabilized footage, gimbal smoothness, locked off tripod shot, black bars, letterbox, music, soundtrack, people, different location, extra wheels, warped body, melted paint, floating car, wrong scale, added text, license plate text, watermarks, drone, visible camera, camera operator shadow, CGI look, plastic textures, cartoon, toy car, still frozen grass, flicker, morphing.

SEEDANCE 2.5 · REFERENCE TO VIDEO · 9:16 · 18S FORMAT: Vertical 9:16, 1080p, 18 seconds, ONE CONTINUOUS SHOT, no cuts, no edits, no speed ramps that break continuity. Silent render. STYLE: Ultra realistic live-action cinematic footage, real world physics, natural hard desert sunlight, high dynamic range, fine 35mm film grain, true optical lens behavior, ultra-wide rectilinear lens with slight edge stretch exactly like @Video 1, real motion blur, real reflections in chrome and paint, premium automotive commercial look. Not CGI, not 3D render, not game engine. REFERENCES: @Video 1 = CAMERA ONLY. Copy its camera path, speed, timing, rolls, dutch tilts, orbit direction, distance to subject, height changes and lens language 1:1, second by second. Ignore everything visible in it: its car, its man, its desert and its road. @Image 1 = THE CAR. Exact design, proportions, paint and every detail. Ignore the studio backdrop. @Image 2 = THE MAN. Face, identity, curly hair, beard and full wardrobe. He wears the black sunglasses the whole time. Ignore the grid layout, text labels, swatches and studio background. @Image 3 = THE LOCATION. The exact desert highway, sand dunes, rock ridges, light and colors. VIDEO PROMPT: The custom show car from @Image 1 is parked on the near asphalt section of the desert highway from @Image 3, angled slightly across the lane with its shark-mouth nose toward camera left, the long straight road rising behind it into the dunes. Car: glossy pearl white body with candy-apple red side scallops and fine gold pinstriping, a gaping shark mouth on the front filled with rows of polished chrome cone teeth, a single chrome needle spike on the nose tip, chrome spikes running along the hood, an exposed chrome supercharged V8 with a triple red-lens scoop, chrome bundled headers along the side, a tall white and red shark dorsal fin on the roof with its own chrome teeth, tinted bubble windows, red tufted interior, a thin whip antenna, polished chrome wheels, wide rear tires with plain black sidewalls. The man from @Image 2 takes the place of the man in @Video 1 and copies his blocking: curly dark brown hair, short beard and mustache, black sunglasses on, glossy crinkled oxblood leather bomber jacket open over a white button shirt, straight ecru denim, burgundy suede running sneakers with cream soles. 0.0-1.0s: low wide shot from the road surface, the camera surges forward along the center dashes toward the car, the man sitting relaxed on the rear deck behind the cockpit. 1.0-3.0s: the camera dives low to the front wheel, ultra close on the chrome wheel and tire tread, rolling slightly as it passes. 3.0-5.0s: it rises along the front fender into the shark mouth, chrome teeth and nose spike filling the frame, swinging around the front with a dutch roll. 5.0-6.5s: it sweeps along the side past the chrome headers, scallops and bubble window, close and fast. 6.5-8.5s: it arcs up and over the car, rolling over the supercharger, hood spikes and dorsal fin, looking down, then drops in front of the hood. 8.5-11.5s: it lifts toward the man, close wide-lens portrait as he sits on the car, cool and still, slight head turn toward the lens, sunglasses catching the sun, then pulls back with a roll as he leans against the side of the car. 11.5-15.0s: it whips around to the rear, tracking low along the rear quarter, ultra close on the wide rear tire, red paint and chrome trim, sunlight flaring across the curves. 15.0-16.5s: it pulls back from the rear, the man now standing beside the car, hands relaxed. 16.5-18.0s: the camera rises and pulls back into a high wide shot: the car and the man small on the asphalt, the endless road climbing straight into the dunes, hard sunlight and long shadows. Hold steady on this final frame. AUDIO: None. Silent video, no music, no sound effects, no dialogue. CONSISTENCY: Same car design from @Image 1 in every frame: shark mouth, chrome teeth, nose spike, dorsal fin, blower and paint never change. Same man from @Image 2: face, curly hair, beard and wardrobe never change, sunglasses never removed. Same location from @Image 3: dunes, rock ridges and road markings with yellow center dashes and white edge lines. Single time of day, consistent sun direction and shadows. Car stays parked, never moves. Camera path matches @Video 1 exactly. NEGATIVE PROMPT: cuts, scene changes, extra people, removed sunglasses, changed face, changed jacket color, text, logos, letters on the car, tire lettering, watermarks, drone, visible camera, camera operator shadow, CGI look, plastic textures, cartoon, toy car, warped car body, melting chrome, extra wheels, distorted hands, flicker, morphing, frozen motion.

SEEDANCE 2.5 · @IMAGE 1 = PLATE · @IMAGE 2 = CHARACTER SHEET · 10S · 1080P · AUDIO ON FORMAT: 16:9, 10 seconds, real-time speed, two shots with one hard cut. REFERENCES: @Image 1 = location reference only, not a start frame: the same department store entrance with the glass revolving door, the street and traffic, the shoppers and the security guard, filmed from its own angle. @Image 2 = character sheet of the man: use only his face, long nose, curly hair, mustache, build and outfit; ignore the grid, labels and grey background. SHOT 1 (0-5s), wide from across the street, traffic passing in front: the man steps into one wing of the revolving door while filming himself; as it turns, his long nose touches the glass panel in front of him and the door's safety sensor stops it with a jolt. The shoppers in the other wings stop too. SHOT 2 (5-10s), zoomed in closer through the traffic: he steps back half a pace, turns his head sideways so his nose clears the glass, and the door starts turning again; he shuffles around with his head turned to the side and steps out into the lobby. A shopper in the next wing rolls her eyes. CAMERA: a passer-by's phone, handheld, natural shake, one or two short digital zooms, focus briefly drifting, motion blur on passing traffic. No operator hands or phone visible. LOOK: real influencer phone footage, slightly over-sharpened compressed smartphone video, phone HDR colors, natural daylight, reflections on the glass. AUDIO: city street ambience, traffic, a bus passing, the soft hum of the revolving door, a mechanical stop click and the door restarting. No music. VOICE (the man): male, early thirties, American English, slightly nasal, upbeat influencer tone, calm and unbothered. CONSISTENCY: the man matches @Image 2 and his nose keeps the same size and shape; the place matches @Image 1. NEGATIVE PROMPT: no music, no getting stuck, no exaggerated cartoon acting, no opening on @Image 1 as a frozen still, no studio background, no sheet grid or labels, no camera interface, no text overlays, no brand logos, no gimbal, no slow motion, no CGI look, no morphing, no extra fingers or limbs, no people appearing from nowhere, nobody looking into this camera.

SEEDANCE 2.5 · @IMAGE 1 = THE STILL ABOVE · 10S · 1080P · AUDIO OFF FORMAT: 16:9, one continuous 10 second take, no cuts, real-time speed. REFERENCE: @Image 1 is the EXACT FIRST FRAME. Start on it with no change: same muddy lane, turf-roofed houses, Viking woman in the doorway, dented parcel in the mud, neighbour with the broom, chickens, light and texture. TIMELINE: 0-2s: the flying mud settles around the parcel; the woman steps down from her doorway, wiping her hands on her apron. 2-4s: she picks the box up out of the mud, shakes it off, and gives a small satisfied nod up toward the sky in the direction it came from. 4-7s: she slits the tape with a small knife from her belt, pulls the flaps open, pushes the paper aside and lifts out a sleek modern hair styling wand: a long slim cylinder in deep fuchsia and polished copper, with a set of matching curling barrel attachments in a fitted case inside the box. The bystander zooms in shakily on it, focus hunting. 7-10s: she admires it, clicks a curling barrel onto the end and immediately wraps the end of her long braid around it, its power cord dangling with nowhere to plug it in; across the lane the neighbour stops sweeping and stares with open envy. Zoom out, image shaking. CAMERA: real-time footage filmed on a smartphone held by an ordinary bystander standing in the lane, like a real viral phone clip. Natural hand shake and breathing sway, small jerky digital zooms with no fingers, hands or phone of the operator ever visible in frame, autofocus briefly drifting and snapping back, auto-exposure shifts, natural motion blur, the person reacting a beat late. Modest, believable real-world physics; no slow motion. STYLE: same texture, grain and color as @Image 1 for the whole take. Deadpan. Nobody looks at the camera. CONSISTENCY: the woman's face, braids and clothes, the houses, the neighbour and the parcel stay identical to @Image 1. NEGATIVE PROMPT: no brand names, no logos, no readable text on the box or the product, no fingers or hands of the camera operator in frame, no camera interface, no cinematic camera move, no gimbal, no stabilization, no static tripod frame, no slow motion, no cuts, no CGI look, no AI sheen, no morphing, no warping hands, no extra fingers, no extra limbs, no people appearing from nowhere, no horned helmets, no one looking into the lens.

FORMAT: 9:16 vertical, 27 seconds, one continuous shot, no cuts, 1080p, completely silent video with no audio track. STYLE: Ultra realistic live-action footage, real world physics, natural indoor daylight exactly as in @Image 2, wide-angle lens at tabletop height, shallow depth of field, high dynamic range, subtle handheld camera shake, no smooth gimbal, fine film grain, believable realism, minimal CGI appearance. REFERENCES: @Video 1 = MOTION AND CAMERA SOURCE ONLY. Copy its full-body choreography, every front-limb and paw action, head movement, timing, rhythm, framing and camera movement beat for beat. Ignore its cat's identity, fur, eyes and bandana, its living room, its table, its bottle label and its audio. @Image 1 = CHARACTER IDENTITY. This exact pet, one-to-one: same species and breed, same body shape and proportions, same fur color, length, pattern and markings, same ears, same face, same nose and whiskers, same eye color and every eye detail on the same side as in the photo. Any collar, bandana or accessory visible in the photo stays around the neck exactly as shown. Ignore the photo's floor and background. @Image 2 = ENVIRONMENT AND TABLE. This exact room and this exact table: same tabletop material, shape, edges and surface details, same furniture, walls, floor and light around it. Keep the table and room exactly as shown. VIDEO PROMPT: The pet from @Image 1 replaces the cat from @Video 1 and performs its exact movements, standing upright on its hind legs on the floor behind the table from @Image 2, using its real front paws like hands. On the tabletop: two small clear shot glasses in the middle and one larger clear tumbler close to the lens in the foreground. The bottle is a small plain white plastic bottle with a green cap and no label, filled with a white milky drink, scaled to the pet's paws. The camera sits low at tabletop level, wide lens, glasses large in the foreground, and moves exactly like the camera in @Video 1. 0.0 to 1.5s: The pet stands upright behind the table, holding the bottle out to the side in one front paw, then lifts it up beside its head. 1.5 to 3.3s: It raises the bottle high, tips its head back, brings the bottle down to chest level and gestures with its free paw. 3.3 to 6.0s: It flicks the bottle up out of the top of the frame, front paw stretched high, waiting with a playful rhythm, swaying its upper body, then catches the bottle overhead. 6.0 to 7.0s: It swings the bottle forward in a big arc and lunges toward the camera, both front paws landing on the tabletop, face now close and large in frame, every facial marking from @Image 1 clearly visible. 7.0 to 19.0s: Leaning on the table close to the lens, the pet tilts the bottle horizontally across the frame and pours a thin steady white stream into the two small shot glasses, one after the other, the glasses filling up with real liquid physics. Its eyes and head follow the pour. 19.0 to 21.0s: It moves the bottle to the large foreground tumbler and fills it. 21.0 to 22.3s: It flips the bottle up into the air above its head and rises back onto its hind legs. 22.3 to 23.0s: It catches the bottle and holds it raised in one paw. 23.0 to 25.5s: Keeping the bottle up, it leans forward and puts its other front paw down on the tabletop, slides toward the filled glasses and grips one. 25.5 to 27.0s: It pushes the full glass straight toward the lens, its paw reaching into the camera until the paw and glass fill the frame. End on this frame. AUDIO: None. Silent video. No music, no sound effects, no voice. CONSISTENCY: The pet is exactly the pet in @Image 1 in every frame: same fur color and pattern, same markings, same ears, same face, same eyes with every detail on the same side, never mirrored, never a generic look-alike. Any collar, bandana or accessory from @Image 1 stays on the whole time. Front paws are real animal paws with natural fur and soft pads. The room and the table stay exactly as in @Image 2. The bottle never leaves the pet's paws except during the two tosses. Motion, timing and camera follow @Video 1 exactly. NEGATIVE PROMPT: identity of the cat from @Video 1, bandana or accessory not in @Image 1, olive wood trunk table, glass tabletop with miniature stadium, room from @Video 1, bottle label, logo, text, wrong fur color, wrong markings, mirrored markings, eye color change, eye details on the wrong side, missing accessory, accessory color change, human hands, fingers, human body, cartoon, 3D animation look, CGI look, plastic fur, extra limbs, extra paws, deformed paws, morphing, flickering, identity drift, table change, room change, spilled liquid floating, cuts, scene change, music, sound, voice, subtitles, watermark.

SEEDANCE 2.5 · @IMAGE 1 = THE STILL ABOVE · 10S · 1080P · AUDIO OFF FORMAT: 16:9, one continuous 10 second take, no cuts, real-time speed. REFERENCE: @Image 1 is the EXACT FIRST FRAME. Start on it with no change: same Pharaoh, craftsmen, sarcophagus, tape measure, workshop, light and texture. TIMELINE: 0-3s: the craftsman pulls the yellow tape measure from the Pharaoh's head down to his feet inside the open sarcophagus, reads it, and lets it snap back into the case with a jerk; the Pharaoh flinches slightly. 3-5s: the craftsman shows the number to the one writing on the wax tablet; they both nod and the writer scratches a note. 5-7s: the craftsman holding the heavy lid starts to tilt it down over the sarcophagus to test the fit. 7-10s: the Pharaoh's hand shoots up from inside to stop the lid; everyone freezes; the lid holder slowly lifts it back up; the Pharaoh sits up halfway, uneasy; the bystander zooms in on his face. CAMERA: real-time footage filmed on a smartphone held by an ordinary bystander in the workshop, like a real viral phone clip. Natural hand shake and breathing sway, small jerky digital zooms with no fingers, hands or phone of the operator ever visible in frame, autofocus briefly drifting and snapping back, auto-exposure shifts, natural motion blur, the person reacting a beat late. Modest, believable real-world physics; no slow motion. STYLE: same texture, grain and color as @Image 1 for the whole take. Nobody looks at the camera. CONSISTENCY: faces, costumes, the sarcophagus and the tape measure stay identical to @Image 1. NEGATIVE PROMPT: no fingers or hands of the camera operator in frame, no camera interface, no text overlays, no cinematic camera move, no gimbal, no stabilization, no static tripod frame, no slow motion, no cuts, no CGI look, no AI sheen, no morphing, no warping hands, no extra fingers, no extra limbs, no people appearing from nowhere, no logos, no one looking into the lens.

INVIDEO EDITOR BRIEF Shape flicker transition At every cut (or marker), add a short burst of 4-5 solid white rectangles on their own layer above the video. Set them to Difference blend, overlapping with staggered edges, each blinking rapidly on and off (1-2 frames) out of phase with the others. At the peak, right on the cut, they should cover about 90% of the frame, leaving only slivers of picture. Coverage builds a few frames before the cut and falls away a few frames after, about a third of a second total. Every cut gets a different arrangement and blink pattern. For vertical video, use tall slabs and wide bands across the narrow width. Don't split or trim clips, and leave audio untouched.

INVIDEO EDITOR BRIEF Edit my uploaded video at every timeline marker. Apply a different GPT Image 2.5 mixed-media treatment to each frame from 10 frames before to 10 frames after each marker, inclusive. Give every marker a distinct style that fits its scene, and add a subtle matching sound effect. Keep the original frame order, cuts, dialogue, music, runtime, and all unmarked footage unchanged. Place everything on the timeline and export the finished video.

X-Ray Hit Effect Brief Create a dynamic, frame-by-frame X-ray effect for every moment a person is struck by the ray gun in the supplied video. Identify each impact section precisely. For every frame in each section, extract that exact source frame and create a separate GPT Image 2.5 Sunburst edit. Preserve the person’s pose, face, camera framing, background and existing motion from that frame. Add evolving cyan electrical sparks and bright bone details, keeping the X-ray aligned with the person as they move. Do not reuse one image across multiple frames. Place each edited image over its matching video frame on an upper video track, at exactly one frame long. Every frame of every impact section must be covered, with no gaps. Keep the original footage and audio underneath, and end the effect as soon as the impact ends. Do not replace this with occasional flash frames or a held image. Export at the source frame rate and aspect ratio. Before delivery, inspect the rendered video frame by frame to confirm that every impact frame contains its matching edit, the faces and backgrounds remain consistent, and the original audio is uninterrupted.

THE SMOKE BREAK · PART 1 OF 2 · FORMAT & REFERENCES FORMAT: same duration and aspect ratio as @Video 1 / two-lead replacement / one continuous handheld shot, keep original timing REFERENCES: @Video 1 is the camera, timing, composition and motion-capture master. It is uploaded muted. Treat it as a motion-capture track. It contains two LEADS: the LEAD IN THE WHITE NIKE TRACK JACKET — the black cat who dances, lights the cigarette, opens the jacket and blows out the smoke — and the OPENER IN THE LIGHT BLUE PUFFER VEST — the orange-and-white cat who dances at the very start. Each new lead's body follows the lead it replaces pose-for-pose, frame by frame: the same head position in frame, the same shoulder line, the same elbow angle, the same hand position, the same knee bend and foot placement, at the exact same moment, speed and direction. Keep everything else exactly as it is: the same continuous handheld camera move, framing and distance, the same rooftop with its metal railing, chimneys and tiled edges, the same city view at dusk, the same people around them and everything they do, the same light, grain and color grading. Do not inherit the two original cats' heads, fur, eyes or paws. @Image 1 defines ONLY the new LEAD IN THE WHITE NIKE TRACK JACKET. It can be a person, a cat, a dog or any animal. Preserve this subject's face, eyes, eye condition, hair or fur color, fur pattern, ear shape, nose, skin or fur texture and any unique features — a different or cloudy eye, a scar, a mole, a missing ear tip, special markings — exactly as shown in @Image 1. Do not inherit the background, floor, furniture, lighting or clothes from @Image 1. [optional: short description of your lead, and any unique feature with its exact side, e.g. "black cat, the cat's LEFT eye is cloudy and blind"] @Image 2 defines ONLY the new OPENER IN THE LIGHT BLUE PUFFER VEST. It can be a person, a cat, a dog or any animal. Preserve this subject's face, eyes, eye condition, hair or fur color, fur pattern, ear shape, nose, skin or fur texture and any unique features exactly as shown in @Image 2. Do not inherit the background, floor, furniture, lighting or clothes from @Image 2. [optional: short description of your opener, and any unique feature with its exact side]

BRIEF · PASTE AS YOUR PROMPT IN THE INVIDEO EDITOR PROJECT: Reference-matched, beat-synced masked-transition edit I have uploaded: 1. REFERENCE VIDEO: the guide for music, shot rhythm, cut points, jump cuts, speed changes, and masked transitions. Use its audio as the soundtrack unless I supply a separate track. 2. SOURCE CLIPS: my footage for the new edit. Use only these clips for the picture. DELIVERY Create one finished video at [ASPECT RATIO], [RESOLUTION], and [FPS]. Match the reference’s duration and musical timing unless I specify otherwise. Adapt the composition to my footage without awkwardly cropping the main person. EDITING DIRECTION First analyze the reference frame by frame. Map every shot, cut, beat, masked hold, full-shot reveal, jump cut, and speed change. Then inspect my source clips and choose the clearest person and strongest action for each shot. Do this analysis internally and proceed directly to the edit. Do not stop for shot-by-shot approval. Match the reference’s cut rhythm and energy. Use hard cuts, not dissolves or generic transition presets. At each masked transition, show ONLY the person from the incoming shot over the outgoing shot for the reference’s hold duration. The outgoing shot must remain visible everywhere outside that person. Then hard-cut to the full incoming shot, with the person in the same position and at the same scale. The cutout must use the actual person photographed in my incoming clip, not a generated replacement. Use a moving alpha matte. If video background removal loses transparency, extract the exact incoming source frames for the short hold, make transparent person-only cutouts frame by frame, and place them back in their correct order. Check source-frame numbers against the edit timeline so the person’s motion continues naturally into the full-shot reveal. Good-enough edges are acceptable for these brief holds. Prioritize a recognizable, moving person and genuinely transparent surroundings. If a club or another thin, fast-moving object breaks up, leave that object out of the cutout. Change to a nearby moment in the SAME source clip only if the person cannot be isolated at the chosen moment; keep the masked hold and full-shot reveal continuous. Recreate the reference’s jump-cut positions and punch-ins, stepping tighter without easing. Match its speed-up windows and return to normal speed on the specified cuts. Keep one consistent grade across the entire piece. QUALITY CHECK BEFORE DELIVERY Render the complete video and inspect the rendered frames, not just the edit timeline. Confirm that every requested transition contains a visible incoming person over a still-visible outgoing scene, with no opaque rectangle or black background. Check that each full-shot reveal matches the cutout’s position and motion, all cuts hit the music, and the soundtrack plays without gaps. Fix failed transitions before delivering. Deliver the finished video, not just an edit plan. In your final reply, briefly list any objects omitted from masks, any same-clip moments swapped, and any effect you could not complete. Never describe an opaque overlay as a completed mask. MY SPECIFIC SETTINGS Aspect ratio: [ ] Resolution: [ ] Frame rate: [ ] Runtime: [match reference / specify] On-screen title or text: [none / exact text] Number of masked transitions: [match reference / specify] Anything that must remain in the cut: [ ]

PART 1 OF 2 · FORMAT & REFERENCES FORMAT: same duration and aspect ratio as @Video 1 / two-pet replacement / keep original cuts REFERENCES: @Video 1 is the camera, edit, timing and motion-capture master. It is uploaded muted. Treat it as a motion-capture track: each new pet's body follows the original pet's body pose-for-pose, frame by frame — same head angle, same eye direction, same ear position, same mouth opening, same paw position, same posture, same body sway, at the exact same moment, speed and direction. Keep the same shots, cut points, shot durations, camera framing and movement, the same wooden pier, blue water, sandy beach, sky, golden-hour sunlight and color grading. It contains two performers: the GAZER — the black cat with the red bandana who sits on the pier looking at the sea — and the SINGER — the long-haired orange-and-white cat. Both must be fully replaced in EVERY shot — close-ups, medium shots, wide shots, tiny distant figures, silhouettes and back views. Neither original cat may remain anywhere in the video, and neither original cat's fur, eyes or bandana carries over. @Image 1 defines ONLY the new GAZER. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 1, including any unique features such as a different or cloudy eye, a scar, a missing ear tip or special markings. Keep any collar, bandana or accessory only if visible in @Image 1. Do not inherit the background, floor, furniture or lighting from @Image 1. [optional: short description of the gazer pet, and any unique feature with its exact side, e.g. "black cat, the cat's LEFT eye is cloudy and blind"] @Image 2 defines ONLY the new SINGER. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 2, including any unique features. Keep any collar, bandana or accessory only if visible in @Image 2. Do not inherit the background, floor, furniture or lighting from @Image 2. [optional: short description of the singer pet, and any unique feature with its exact side]

SEEDANCE · UNIVERSAL PARTY ANIMAL FORMAT: same duration and aspect ratio as @Video 1 / single-pet replacement / keep original edit, speed ramps and timing REFERENCES: @Video 1 is the sole source and timeline master. It is uploaded muted. Preserve its exact duration, the opening black, every cut, every speed ramp — each slow-down, hold and sudden speed-up at the exact same moment — the handheld shaky camera, push-ins, tilts and framing, the whole New Year's party room with its tinsel, decorations, table and confetti floor, all party guests and what they do, the flash-lit lighting, grain and color grading. The dancer's performance is the choreography: every arm swing, elbow pump, punch, shoulder shimmy, hip sway, head bob, turn and lean, with the same limb, at the same moment and speed, frame by frame. Nothing in @Video 1 changes except the dancer's identity. Do not inherit the original cat's identity, fur color, eyes or bandana. @Image 1 defines ONLY the new dancer. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 1, including any unique features such as a different or cloudy eye, a scar, a missing ear tip or special markings. Keep any collar, bandana or accessory only if visible in @Image 1. Do not inherit the background, floor, furniture or lighting from @Image 1. [optional: short description of your pet, and any unique feature with its exact side, e.g. "black cat, the cat's LEFT eye is cloudy and blind"] VIDEO PROMPT: Replace ONLY the dancer in @Video 1 with the pet from @Image 1. The pet stands upright on its hind legs in the exact position, scale and framing of the original dancer in every moment and copies the dance 1:1: every arm and paw swing, elbow pump, punch, shimmy, hip sway, head bob, turn and lean with the same limb, the same timing and the same attitude. Front legs move like arms with full dance rhythm while staying real animal anatomy with fur and paws. The pet keeps its own species, breed, fur length, muzzle shape and body build; if it is larger or smaller than the original cat, keep its body center and floor position identical and scale the body naturally. Any unique facial feature stays on the correct side of the face in every shot, every spin and every close-up, exactly as in @Image 1, never mirrored. The party flash lights the pet's fur the same way it lit the original cat; any accessory flies with every move. Photorealistic, real fur physics, believable upright balance, funny and confident. Camera and speed lock: every moment is a frame-by-frame copy of @Video 1 — same handheld movement, same shake, same push-ins, same framing, and the same speed ramps at the same moments, with the dance slowing down and snapping back up exactly where @Video 1 does. Do not smooth the camera, do not remove or add speed ramps, do not shorten or extend anything. AUDIO: silent. No music, no voices, no sound effects. CONSISTENCY: Exactly one animal, always the dancer at the center of the party. Same pet identity from first frame to last. Unique features and accessories present on the correct side in every shot. Party room, guests, camera, speed ramps, cuts and timing identical to @Video 1. NEGATIVE PROMPT: no original cat from @Video 1, no human dancer in the pet's place, no second animal, no identity change, no breed change, no species change, no mirrored face, no eye change, no missing or moved unique features, no added accessories, no fur color drift, no wrong arm on a move, no changed dance order, no smooth stabilized camera, no missing or extra speed ramps, no constant speed, no shortened or missing moments, no changed room, no missing guests, no daylight, no flicker, no cartoon, no cheap CGI, no on-screen text, no watermark.

SEEDANCE · UNIVERSAL PET FIGHTER FORMAT: same duration and aspect ratio as @Video 1 / single-pet replacement / one continuous shot, keep original timing REFERENCES: @Video 1 is the sole source and timeline master. It is uploaded muted. Preserve its exact duration, camera position, camera movement, lens, framing, focus, motion blur, the wet night street, the neon and street-light reflections, the shop shutters, all lighting and color grading. The fighter's performance is the choreography: every stance, weight shift, hop, punch, paw strike, block, head movement, the charge toward the camera and the final strike into the lens, at the exact same moments, speed and direction, frame by frame. Nothing in @Video 1 changes except the fighter's identity. Do not inherit the original cat's identity, fur color, eyes or bandana. @Image 1 defines ONLY the new fighter. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 1, including any unique features such as a different or cloudy eye, a scar, a missing ear tip or special markings. Keep any collar, bandana or accessory only if visible in @Image 1. Do not inherit the background, floor, furniture or lighting from @Image 1. [optional: short description of your pet, and any unique feature with its exact side, e.g. "black cat, the cat's LEFT eye is cloudy and blind"] VIDEO PROMPT: Replace ONLY the fighter in @Video 1 with the pet from @Image 1. The pet stands upright on its hind legs in the exact same position, scale and framing as the original cat and performs the exact same fight choreography 1:1: same guard stance, same hops and footwork, same punch and paw-strike combinations with the same paw at the same moment, same speed, same power, same head tilts and dodges, same charge toward the camera and the same final strike straight into the lens. The pet keeps its own species, breed, fur length, muzzle shape and body build; if it is larger or smaller than the original cat, keep its body center and floor position identical and scale the body naturally. Any unique facial feature stays on the correct side of the face in every frame, every head turn and especially in the final close-up when the face fills the lens, exactly as in @Image 1, never mirrored. The fur catches the neon and street-light reflections naturally; any accessory moves with the body on every strike. Motion blur on fast strikes matches @Video 1 exactly. Photorealistic, real fur physics, natural animal anatomy, believable upright balance and impact. Camera lock: the camera is a frame-by-frame copy of @Video 1: same position, same height, same movement, same focus changes, same speed and same duration. Do not slow the action down, do not shorten or cut it, do not stop early and do not add camera moves. AUDIO: silent. No music, no sound effects. CONSISTENCY: Exactly one animal. Same pet identity from first frame to last. Unique features and accessories present on the correct side in every frame. Street, lighting, camera and timing identical to @Video 1. NEGATIVE PROMPT: no original cat from @Video 1, no second animal, no human, no identity change, no breed change, no species change, no mirrored face, no eye change, no missing or moved unique features, no added accessories, no fur color drift, no changed punch order, no wrong paw, no slow motion, no slow action, no shortened move, no camera change, no daytime, no dry street, no flicker at the edges of the replaced region, no cartoon, no cheap CGI, no on-screen text, no watermark.

SEEDANCE · UNIVERSAL SINGER + HYPE MAN FORMAT: same duration and aspect ratio as @Video 1 / two-pet replacement / keep original cuts REFERENCES: @Video 1 is the camera, edit, timing and performance master. It is uploaded muted. Copy it exactly: same number of shots, same cut points, same shot durations, same camera framing and movement, same red studio backdrop, same hanging studio microphone, same lighting and color grading. It contains two performers: the SINGER standing at the microphone on screen-right, and the DANCER on screen-left. Copy both performances frame by frame: every mouth shape, jaw opening, head tilt, head turn, eye closing, paw gesture, arm movement, dance move, body sway and bounce, at the exact same moments. Do not inherit the original cats' identity, breed, fur color, fur length, eyes or accessories. @Image 1 defines ONLY the new SINGER. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 1, including any unique features such as a different or cloudy eye, a scar, a missing ear tip or special markings. Keep any collar, bandana or accessory only if visible in @Image 1. Do not inherit the background, floor, furniture or lighting from @Image 1. [optional: short description of the singer pet, and any unique feature with its exact side, e.g. "white dog, the dog's RIGHT ear is folded"] @Image 2 defines ONLY the new DANCER. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 2, including any unique features. Keep any collar, bandana or accessory only if visible in @Image 2. Do not inherit the background, floor, furniture or lighting from @Image 2. [optional: short description of the dancer pet, and any unique feature with its exact side] VIDEO PROMPT: Recreate @Video 1 with both performers replaced. The pet from @Image 1 stands upright on screen-right at the hanging microphone and sings exactly like the original singer: the mouth opens, closes and shapes every word at the same moments and to the same width, so the original song can be laid back in perfect lip sync. Its front paws copy every gesture of the original singer at the same moment and in the same direction, with the same head tilts, the same eyes closing on long notes and the same body sway. The pet from @Image 2 stands upright on screen-left and copies every move of the original dancer: the same hype-man bounces, paw pumps, pointing, spins, leans and poses, landing on the same beats. Both pets keep the exact screen side, spacing, scale and framing of the original performers in every shot. Each pet keeps its own species, breed, fur length, muzzle shape and body build; if a pet is larger or smaller than the original cat, keep its body center and floor position identical and scale the body naturally. Any unique facial feature stays on the correct side of the face in every shot, every head turn and every spin, exactly as in its reference image, never mirrored. The dancer never blocks the singer's face or touches the microphone. The studio lighting wraps each pet's fur naturally. Photorealistic, real fur physics, natural animal anatomy, believable upright balance. Camera lock: every shot is a frame-by-frame copy of the matching shot in @Video 1: same start frame, same framing, same movement, same speed, same duration, same cut point. Do not slow down, shorten, extend, merge or remove any shot. Do not add camera moves that are not in @Video 1. AUDIO: silent. No music, no singing voice, no sound effects. Mouth and body movements follow @Video 1 frame by frame so the original song can be added back in the edit. CONSISTENCY: Exactly two animals and no human. The @Image 1 pet is always the singer at the microphone on screen-right; the @Image 2 pet is always the dancer on screen-left; they never swap roles or sides. Same identities in every shot. Unique features and accessories present on the correct side in every shot. Backdrop, microphone, camera, cuts and timing identical to @Video 1. NEGATIVE PROMPT: no original cats from @Video 1, no human, no third animal, no swapped roles, no swapped sides, no dancer singing, no singer leaving the microphone, no mouth movement out of sync with @Video 1, no identity change, no breed change, no species change, no mirrored face, no eye change, no missing or moved unique features, no added accessories, no fur pattern drift, no dancer blocking the singer, no slow camera, no slow motion, no shortened or missing shots, no change to camera path, speed or cut points, no backdrop color change, no missing microphone, no music, no flicker, no cartoon, no cheap CGI, no on-screen text, no watermark.

SEEDANCE · UNIVERSAL TWO-PET DUET FORMAT: same duration and aspect ratio as @Video 1 / two-pet replacement / keep original cuts REFERENCES: @Video 1 is the camera, edit, timing and performance master. Copy it exactly: same number of shots, same cut points, same shot durations, same camera framing and movement, same orange studio backdrop, same hanging studio microphone, same lighting and color grading. Both animals keep the exact same positions, upright standing poses, body movements, paw gestures, head movements, mouth movements and timing as the original cats. Do not inherit the original cats' identity, breed, fur color, fur length, eyes or accessories. @Image 1 defines ONLY the LEFT pet, the singer. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 1, including any unique features such as a different or cloudy eye, a scar, a missing ear tip or special markings. Keep any collar, bandana or accessory only if visible in @Image 1. Do not inherit the background, floor, furniture or lighting from @Image 1. [optional: short description of the left pet, and any unique feature with its exact side, e.g. "black cat, the cat's LEFT eye is cloudy and blind"] @Image 2 defines ONLY the RIGHT pet, the dancer. It can be a cat or a dog. Preserve this animal's face, eye color, eye condition, fur color, fur pattern, fur length, ear shape, nose, body size and proportions exactly as shown in @Image 2, including any unique features. Keep any collar, bandana or accessory only if visible in @Image 2. Do not inherit the background, floor, furniture or lighting from @Image 2. [optional: short description of the right pet] VIDEO PROMPT: Recreate @Video 1 with the two animals replaced. The pet from @Image 1 stands upright on the LEFT in front of the hanging microphone and performs every movement of the original left cat: same upright stance, same mouth opening in rhythm as it sings, same head tilts toward the mic, same paw positions, same timing. The pet from @Image 2 stands upright on the RIGHT and performs every movement of the original right cat: same paw gestures, same body sway, same head turns, same expressions, same timing. Both pets keep the exact screen side, spacing, floor position and framing of the original cats in every shot, including the wide shot. Each pet keeps its own species, breed, fur length, muzzle shape and body build; if a pet is larger or smaller than the original cat, keep its body center and floor position identical and scale the body naturally. Any unique facial feature stays on the correct side of the face in every shot and every head turn, exactly as in its reference image, never mirrored. The studio lighting wraps each pet's fur naturally. Photorealistic, real fur physics, natural animal motion, believable upright balance. Camera lock: every shot is a frame-by-frame copy of the matching shot in @Video 1: same start frame, same framing, same movement, same speed, same duration, same cut point. Do not slow down, shorten, extend, merge or remove any shot. Do not add camera moves that are not in @Video 1. AUDIO: @Video 1 is uploaded muted. Generate the video silent: no music, no singing voice, no sound effects. Mouth and body movements follow @Video 1 frame by frame so the original song can be added back in the edit. CONSISTENCY: Exactly two animals, @Image 1 pet on the left, @Image 2 pet on the right, never swapping sides. Same identities in every shot. Unique features and accessories present on the correct side in every shot. Orange backdrop, microphone, camera, cuts and timing identical to @Video 1. NEGATIVE PROMPT: no original cats from @Video 1, no third animal, no pets swapping sides, no identity change, no breed change, no species change, no mirrored face, no eye change, no missing or moved unique features, no added accessories, no fur pattern drift, no slow camera, no slow motion, no shortened or missing shots, no change to camera path, speed or cut points, no backdrop color change, no missing microphone, no music, no flicker, no cartoon, no cheap CGI, no on-screen text, no watermark.

SEEDANCE 2.5 · IMAGE TO VIDEO · @IMAGE 1 FORMAT: 15s / 9:16 vertical / one continuous handheld shot, no cuts / natural sync sound, no music STYLE: raw candid smartphone video shot from across the street, looks like a bystander filmed it and posted it. Photorealistic, low contrast, muted desaturated colors, flat overcast daylight, real concrete and asphalt texture, phone sensor noise, slight rolling-shutter wobble on fast moves, focus hunting, digital zoom softness when zoomed in. Handheld level 2 to 3: the camera is a phone held in someone's hands, it bounces with the operator's breathing and small steps, reframing lags behind the action, no smooth gimbal, no stabilization. Everything is real animals with accurate anatomy, size and feather/fur texture. No CGI feel, no cinematic grading. REFERENCES: @Image 1 is the exact FIRST frame, start with no change. Lock everything in it: the grey feral pigeon standing upright on the cracked sidewalk, the small black Wayfarer sunglasses on its face, the small black pistol held in its right wing, the grey concrete wall, the curb, the litter, the cigarette butt, the white lane line, the passerby's legs in dark shorts and black clogs at the right edge. The pigeon is the only hero. The passerby simply finishes walking out of frame to the right. VIDEO PROMPT: 0.0s to 2.0s: Open on the exact frame of @Image 1. The passerby's legs step out of frame right. The pigeon turns its head, then starts walking, upright on two feet with a slow, unbothered swagger, pistol still in its right wing hanging at its side, barrel down. It steps off the curb onto the asphalt. The phone camera drifts slightly and reframes late, a small bounce from the operator shifting weight. 2.0s to 4.0s: The camera performs a shaky digital zoom in on the pigeon as it walks along the road toward the camera side of the street, slight focus hunt, the image gets a bit softer and noisier as the zoom tightens. Sunglasses stay on. 4.0s to 6.0s: The camera pulls the zoom back a little and pans left, revealing the middle of the street ahead of the pigeon: a scruffy tabby street cat crouched on the asphalt with a real small grey mouse held in its mouth, and two more street cats, one black and one orange, sitting close on either side of it, all three looking down at the mouse. The pigeon keeps walking straight at them. Distant traffic passes in the background. 6.0s to 8.5s: The pigeon stops about two meters from the cats, plants its feet, raises the pistol straight up over its head with its wing, pointed only at the empty sky, and fires two short blank shots upward, then a third. Small sharp muzzle flash, a puff of smoke, the wing kicks slightly with each recoil. The phone camera jolts hard with each crack, the operator flinches, the frame jumps and over-rotates, then corrects back onto the pigeon. Nothing and no one is hit. 8.5s to 11.0s: All three cats startle at the first crack. The tabby drops the mouse. The cats bolt with real cat physics, low bodies, scrambling paws, tails puffed: the tabby sprints far down the road and shrinks into the distance, the black cat darts left under a parked car, the orange cat leaps sideways to the right and vanishes behind the curb. The freed mouse scurries fast across the asphalt and squeezes into a storm drain opening in the curb near the camera. The camera whips toward the fleeing cats, lags, then finds the pigeon again. 11.0s to 15.0s: The pigeon lowers the pistol back to its side, barrel down, and continues its walk straight toward the camera across the road with the same slow gangster swagger, head bobbing, feet clicking on the asphalt. The camera performs a second shaky digital zoom in, slowly tightening on the pigeon's head and black sunglasses as it walks, focus breathing, sensor noise rising. The pigeon fills the lower frame, sunglasses on, pistol hanging at its side, and walks past the lens at the last moment. End on the pigeon close and slightly out of focus, camera still handheld and unsteady. AUDIO: Natural street ambience only: distant traffic hum, a car passing, wind on the phone microphone, the passerby's clogs slapping away, the pigeon's claws ticking on concrete then asphalt, <three short sharp pistol cracks echoing off the concrete wall, a fraction apart>, a muffled phone-mic clip and the operator's small startled breath on the first crack, cats hissing and yowling once, the scramble of paws on asphalt, a tiny mouse squeak and a scrape at the drain, then the ambience settles back to traffic and the pigeon's steady footsteps growing closer to the microphone. No music, no narration, no spoken words. CONSISTENCY: The pigeon is the same bird from @Image 1 for the entire shot, identical feather markings and size. The black Wayfarer sunglasses stay on its face for the whole video and are never removed, never slip. The pistol never leaves its right wing. The pigeon stays upright on two feet, real pigeon anatomy, walks like a small person. The cats are real street cats, the mouse is a real small mouse. The location is the same street, same grey wall and curb, from the same across-the-street viewpoint. One continuous shot from one phone. NEGATIVE PROMPT: no cuts, no scene change, no smooth gimbal movement, no stabilization, no cinematic color grading, no cartoon, no CGI look, no plastic or toy look, no extra pigeons, no extra people in the foreground, no camera or phone visible, no drone, no sunglasses removed, no pistol dropped, no pistol pointed at any animal or person, no injuries, no blood, no cats hit, no mouse hurt, no floating objects, no teleporting cats, no morphing, no warping, no text, no captions, no watermark, no music, no narration.

SEEDANCE 2.5 · VIDEO-TO-VIDEO · 7S · 9:16 FORMAT: 7s / 9:16 vertical / pet and environment replacement / one continuous shot, no cuts REFERENCES: @Video 1 is the camera and timing master. Copy its camera movement exactly: same path, same speed, same acceleration, same duration, same lens, same framing, same motion blur, and the animal's position, pose, scale and behavior in frame. Every camera move in @Video 1 must be reproduced completely and at identical speed, from the first frame to the last frame. Do not inherit its room, furniture, carpet, lighting, color grading or original cat. @Image 1 defines ONLY the replacement pet, a cat or a dog. Preserve this animal's face, eye color, fur color, fur pattern, fur length, ear shape, body size and proportions exactly as shown in @Image 1. Do not inherit the background, floor, furniture or lighting from @Image 1. [optional: add a short description of your pet here, e.g. "small fluffy white dog with brown ears"] @Image 2 defines ONLY the environment. Preserve this room, its layout, furniture, floor, materials, colors and lighting exactly as shown in @Image 2. Do not inherit any camera angle or framing from @Image 2. VIDEO PROMPT: Recreate @Video 1 with the pet from @Image 1 inside the environment from @Image 2. The pet sits on the floor of @Image 2, taking the exact same position, pose, scale, orientation and behavior as the original cat at every moment of the video, head and eyes following the camera the same way. The furniture of @Image 2 appears where the original room's furniture appeared along the camera path. If the pet is larger or smaller than the original cat, keep its body center and floor position identical and scale the body naturally. The lighting of @Image 2 wraps the fur naturally, with matching shadows on the floor and correct occlusion as the camera passes furniture. Photorealistic, real fur physics, natural animal motion. Camera lock: the camera is a frame-by-frame copy of @Video 1. It starts on the same extreme close-up of the face, pulls back at the same fast speed, performs the same full low-angle 360-degree orbit around the seated pet at the same speed and in the same direction, passes low under furniture at the same moment, and returns to the same final close-up of the face at the same moment. The full orbit must be completed within the 7-second duration. Do not slow the camera down, do not shorten or cut the move, do not stop the orbit early, do not hold on the pet longer than @Video 1 does, and do not add any camera move that is not in @Video 1. Whip-pan speed and motion blur intensity match @Video 1 exactly. AUDIO: quiet room tone, soft fur and floor sounds, no music. CONSISTENCY: Exactly one animal. Same pet identity and same room from first frame to last. Camera path, speed, direction and timing identical to @Video 1 for the entire duration. NEGATIVE PROMPT: no second animal, no original tabby cat, no identity change, no breed change, no eye color change, no fur pattern drift, no slow camera, no slow motion, no incomplete orbit, no camera stopping early, no static hold, no shortened camera move, no change to camera path, speed or direction, no new cuts, no blue carpet, no original room from @Video 1, no room layout drift, no flicker, no cartoon, no cheap CGI, no on-screen text, no watermark.

FORMAT: 30s / 9:16 vertical / cinematic automotive fashion film / hard-cut montage of 7 camera setups, no dissolves. STYLE: 35mm film capture, shoulder-operated camera with organic sway and footstep micro-jitter, no smooth gimbal. Low contrast, detailed open shadows, restrained brown/cream palette, soft highlight roll-off, fine grain, real car materials. Overcast late-afternoon daylight from screen right. Shallow depth of field with a deliberate rack focus in every shot. ASMR sound design, no music. REFERENCES: @Image 1 defines the man's face, identity, curly brown hair, short beard and black square-framed sunglasses ONLY. Do not inherit the grey t-shirt, table, food or cafe background. @Image 2 defines the car: chocolate-brown Porsche 911 GT3 RS, metallic brown paint, carbon-fibre hood, intakes and swan-neck rear wing, black wheels, yellow calipers, red rear light bar. All panels are the SAME single car; show exactly one. Ignore the grid and studio background. @Image 3 defines the interior, seats, steering wheel, dashboard and rear-view mirror only. [Hero profile] Face and sunglasses: @Image 1. The black wayfarer-style sunglasses remain ON in every shot. Wardrobe: cream oversized heavyweight cotton t-shirt, open chocolate-brown wool overshirt with sleeves pushed to the forearm, relaxed cream wide-leg trousers, grey-and-cream suede New Balance running sneakers, small dark tattoo on the right forearm. No hat, no bag. Exactly one man. [Location] Broad overpass avenue, cream concrete railings, modern skyline in the far distance, matte grey asphalt, sparse distant traffic. VIDEO PROMPT: [Shot 1 - approx 0-4s] Extreme wide shot from far across the avenue, car and man small against the skyline. Initial state: the man stands at the open driver door. Event: he lowers into the seat and the door closes. Camera: slow walking push-in with footstep jitter, rack focus from a near railing post to the car. End state: door closed, man inside, camera still walking. [Shot 2 - approx 4-8s] Interior, camera from the passenger seat framing the rear-view mirror in close-up, shallow depth of field. Initial state: the mirror shows only the rear glass and the empty avenue behind; the man is not in the mirror, only his shoulder soft in the foreground. Event: his right hand enters and tilts the mirror down in one short motion; his face and black sunglasses slide into the mirror; he holds a slow calm look into the mirror for one beat, then looks back to the road. Camera: rack focus from his hand to the mirror reflection. End state: his face framed in the mirror, hand lowered. [Shot 3 - approx 8-12s] Roadside shoulder camera at the railing, wide. Initial state: empty asphalt, skyline soft. Event: the car enters from screen left at brisk natural road speed and passes close to camera; the near pass fills the frame with brown paint and carbon wing as a foreground wipe. Camera: the operator reacts late with a short whip pan, natural motion blur, then settles. End state: the car exiting screen right, wheels rotating, road parallax credible. [Shot 4 - approx 12-16s] Low angle at the road edge, camera near the ground. Initial state: the car far away, small, soft, headlights toward camera. Event: the car approaches steadily, growing large, then passes close on the right of camera. Camera: rack focus from near asphalt to the approaching car, slight shoulder recoil as it passes. End state: the car past the lens, camera settling on empty road. [Shot 5 - approx 16-20s] Interior driving, camera braced in the passenger seat, medium close-up of the man in profile, road vibration. Initial state: both hands on the wheel, skyline sweeping across the windshield, cream railings streaming past the side window. Event: he glances at the side mirror, then back to the road, a small confident exhale. Camera: slow push-in toward his profile, rack focus from the streaming railing outside to his sunglasses. End state: tight on his profile, sunglasses sharp, window blur behind. [Shot 6 - approx 20-25s] Rear tracking from a follow vehicle, shoulder-mounted, low. Initial state: the rear wing and red light bar fill the frame, matched speed. Event: the car accelerates away naturally, the gap opening, the wing shrinking against the skyline. Camera: held on the wing, then rack focus from the receding car to the road streaming under the lens. End state: the car three car lengths ahead and pulling away. [Shot 7 - approx 25-30s] Wide shot from the sidewalk at chest height. Initial state: the car mid-frame, travelling away toward the skyline. Event: it continues down the avenue, growing smaller. Camera: a short pan follows it, then the operator holds; slow focus roll from the car to the far skyline. Final state: held frame, car a small soft shape against the sharp skyline, no camera movement for the last second. AUDIO: <Native diegetic sound only: distant city hum, soft wind, door thump in Shot 1, mirror pivot click in Shot 2, subdued flat-six engine passing with tire roar and wind in Shots 3, 4 and 6, muffled cabin road noise in Shot 5, exhaust fading into the city in Shot 7.> No music. No voice. CONSISTENCY: Keep the man's face, curly hair, beard and black wayfarer-style sunglasses unchanged in every shot; sunglasses never removed. Keep the cream t-shirt, brown overshirt, cream trousers and suede sneakers unchanged. Exactly one man, exactly one car. The man is the only occupant, always in the driver seat. Screen direction: the car travels left to right or away from camera, never toward screen left. NEGATIVE PROMPT: no sunglasses removed, no face distortion, no identity change, no wardrobe change, no second person, no passenger, no second car, no grid layout, no studio background, no glossy CGI, no crushed blacks, no excessive HDR, no smooth gimbal, no drone shot, no speed ramp, no slow motion, no music, no dialogue, no on-screen text, no captions, no REC graphics, no watermark, no warped wheels, no wheel spin, no smoke, no drifting.

SEEDANCE 2.5 · VIDEO PROMPT · 5,997 CHARACTERS FORMAT: 30s / 16:9 / cinematic music-video scene / one continuous shot, no cuts STYLE: Live-action music-video realism, overcast daylight, cool desaturated grade, fine 35mm film grain, one consistent look. Match the color, contrast, grain and lens texture of @Video 1. REFERENCES: @Video 1 is the timing, blocking, camera and environment master. Inherit its shot structure, camera moves, the lead performer's path and gestures, the moment the crowd starts dancing, the choreography, the crowd rows, and the location (red-brick building with arched windows behind a paved courtyard). Do NOT inherit its performers, faces, clothing, subtitles, voices or music. @Image 1 defines THE MAN, the only human: curly brown hair, short beard, black square sunglasses, burgundy wool varsity jacket with brown leather sleeves and a cream K patch, dark grey cardigan over a striped shirt, charcoal pinstripe trousers, grey sneakers. Ignore the five-panel layout, labels and studio background. No bag. He takes the place of the lead performer of @Video 1. @Image 2 defines TYPE A: a slim performer in an off-white structured long coat, trousers, boots and gloves, wearing a smooth matte BLACK multi-lobed sphere helmet with two small glowing white eyes and a small black sphere on a thin stem at the neck. Fully covered costume. @Image 3 defines TYPE B: a slim performer in a black structured long coat, trousers, boots and gloves, wearing a smooth glossy WHITE multi-lobed sphere helmet with two small black eyes and a small white sphere on a thin stem at the neck. Fully covered costume. The crowd is many identical copies of TYPE A and TYPE B only, alternating A, B, A, B along each row and offset row to row as a checkerboard. Every crowd member of @Video 1 becomes one of these types. VIDEO PROMPT: [Stage 1 - approx 0-4s] Initial state: tight close-up, head and shoulders, THE MAN centered, sunglasses on. Behind him, out of focus, rows of TYPE A and TYPE B stand motionless facing the camera. Event: he takes a slow deep breath, his breath shows as cold vapor in the chilly air and drifts up past the sunglasses; his right hand adjusts the bridge of the sunglasses, then lowers. He turns his head slightly left, then right, then back to the lens, expression flat. Camera: locked-off close-up, shallow depth of field. End state: hand lowered, he faces the lens. [Stage 2 - approx 4-9s] Continue from that frame. At 4s he turns his back to the camera over his left shoulder, head slightly lowered, and walks straight away from the lens into the crowd through a narrow gap between the figures, following the path and pace of @Video 1. The figures never move. Camera: holds position and height; focus follows him into the wall of alternating black and white helmets. End state: he stops about six rows deep, back to camera, a TYPE A on his left and a TYPE B on his right. [Stage 3 - approx 9-17s] Continue from the unchanged formation. At 13s he turns in place to face the camera, straightens the jacket collar with both hands, lowers his arms and settles into a relaxed standing pose, looking straight into the lens through the crowd. Every figure stays frozen, all helmets facing the camera. Camera: very slow drift, him centered at mid-depth, medium-wide frame. End state: total stillness; he is the calm center of a rigid checkerboard of helmets. [Stage 4 - approx 17-24s] Continue from the frozen formation. At 19s, on a single beat, every figure except THE MAN starts the dance from @Video 1, matching its choreography: each performer twists the whole torso around the vertical spine axis, shoulders rotating to face diagonally left, then diagonally right, head following the shoulders and tipping back, elbows bent and arms sweeping across the chest with the twist, feet planted. Neighboring performers move in opposite phase: when one twists to face left, the performer beside them twists to face right, so every row reads as an interlocking corkscrew of alternating diagonals, never a line of performers all facing the same way. Stylized, energetic; each performer stays in their own space. The sphere helmets stay firmly on and keep their shape through every movement. THE MAN does not move at all, only his breath vapor drifting. Camera: begins a slow, steady pull back and crane up. End state: the whole visible crowd is mid-dance, he stands motionless in the exact center. [Stage 5 - approx 24-30s] Continue the same crane. The camera keeps rising and pulling back to a high wide shot, revealing hundreds of alternating TYPE A and TYPE B performers filling the courtyard, all twisting in the same counter-phase corkscrew rhythm, alternating diagonals across every row, the red-brick building across the top of the frame. THE MAN stays still, sunglasses on, one unmoving point in the middle of the motion. Camera settles and holds. Final state: held high wide frame, crowd dancing, the man still. AUDIO: <cold overcast courtyard air, faint wind> <at 1s one slow breath in and out> <his steps on pavement> <at 19s hundreds of shoes tap the pavement together, coats swishing, a low rhythmic floor pulse> No dialogue. No music. Do not inherit the music, vocals or lyrics of @Video 1. CONSISTENCY: Keep THE MAN's face, hair, beard, sunglasses and full wardrobe unchanged in every frame; sunglasses never come off. Exactly one human. The crowd contains only TYPE A and TYPE B, alternating; every crowd performer keeps the sphere helmet on at all times. TYPE A always has a black helmet and an off-white outfit; TYPE B always has a white helmet and a black outfit; never swap. Keep location, lighting, screen direction and camera path consistent with @Video 1. NEGATIVE PROMPT: no cuts, no identity change, no face distortion, no sunglasses removal, no wardrobe change, no bag, no helmet removal, no mismatched helmet and outfit colors, no helmet deforming, no third character type, no music, no vocals, no subtitles, no on-screen text, no watermark, no cartoon, no cheap CGI, no style drift.

FORMAT: 30s / 9:16 vertical / luxury beauty influencer commercial / staged scene with motivated cuts STYLE: Photographic realism, ARRI Alexa 35 look, 35mm primes, hard midday Los Angeles sun with deep clean shadows, real skin with visible pores, freckles and micro sheen, no beauty smoothing, shallow depth of field, light 35mm grain, warm neutral grade, one consistent visual identity. REFERENCES: @Image 1 defines the woman ONLY: face, green eyes, freckles, messy high bun with loose strands, gold hoops, layered gold chains with padlock pendant, gold chain belt, bracelet and stacked rings, snake and dagger tattoos on left forearm, small cross on right wrist, cream ribbed knit halter maxi dress with open back, terracotta phone case with matching terracotta lip gloss tube clipped to it. Ignore the grid layout and wall backgrounds. @Image 2 defines the man ONLY: salt-and-pepper swept-back hair, grey stubble, tanned, white linen shirt open at collar, sleeves rolled, steel bracelet watch, seated in the driver seat of the cream vintage sedan with chrome trim and cream leather interior. @Image 3 defines the exterior composition for Stage 3 ONLY: high over-the-shoulder angle from behind the woman, her reflection in the dark tinted glass. @Image 4 defines the interior camera position for Stages 1, 4 and 5 ONLY: camera inside the car, passenger side, shooting out through the closed side window at the woman leaning toward the glass; and defines the handwritten lowercase word in glossy terracotta lip gloss on the glass, reproduced with these exact letter shapes, reading correctly from inside the car. VIDEO PROMPT: [Stage 1 - approx 0-6s]​ Initial state: inside the cream sedan, camera at passenger seat height matching @Image 4, looking out through the closed window at a sunlit street with brick warehouse and palms. Event: the woman walks in from the right, stops at the window, bends down and uses the dark glass as a mirror. Her eyes stay on her reflection, never into the car. She unclips the gloss tube from the phone case, uncaps it and applies gloss to her lower lip in one slow unhurried stroke. Camera: locked with faint handheld breathing, no zoom. End state: wand touching her lower lip, phone in left hand, glass closed between her and camera. [Stage 2 - approx 6-10s]​ Cut to exterior. Extreme close-up of her face in direct sun, eyebrows to chin, as she continues applying. Real skin: pores, freckles, sun-lit fine facial hair, gloss catching the sun as a wet highlight, individual lashes, loose strands in a light breeze. Event: she finishes the stroke, presses her lips together once, lifts her eyes to check the reflection. Camera: macro, very shallow focus, slow rack from lips to eyes. End state: eyes open, wand a few centimeters from her mouth, lips glossy. [Stage 3 - approx 10-16s]​ Cut to exterior, exact composition of @Image 3. The tinted glass reads as a mirror; the interior stays dark and unreadable so the man is not visible. Event: she recaps the gloss, tilts her head left then right admiring her lips, touches the corner of her mouth with a fingertip. Camera: slow push toward the reflection, restrained handheld, no gimbal smoothness. End state: gloss in right hand, phone in left, smiling at her reflection, unaware of anyone inside. [Stage 4 - approx 16-21s]​ Cut back to the interior position of @Image 4. Event: she uncaps the gloss and, with a playful half smile, writes on the outside of the glass with the applicator in slow flowing lowercase: arcads, matching the letter shapes of @Image 4, strokes wet and glossy with small drips at letter tails, reading correctly from inside. She leans back a few centimeters and looks at the word, pleased. Camera: locked, faint breathing. End state: complete word on the glass, applicator lifted, her face behind the letters, gloss and phone in her hands. [Stage 5 - approx 21-26s]​ Continue from the unchanged word. Event: at 21s a man's hand with a steel watch enters the lower frame from the driver side and turns the manual window crank. The glass slides down slowly and steadily; the word travels down with the glass at the same speed and disappears into the door seal, revealing her face with no glass between. Her smile stops as she registers movement; eyes widen, mouth opens slightly, she straightens a few centimeters, then presses both palms together at her chest in an apologetic gesture with a small wince. Restrained, no exaggerated acting. Camera: locked, faint breathing. End state: window fully down, word gone, hands pressed together at chest height, gloss tube clasped between them. [Stage 6 - approx 26-30s]​ Cut to medium close-up of the man in the driver seat, sun from the open window on his face. Event: he looks at her, brows drawn together, jaw set, lips pressed flat, one slow unimpressed blink. He does not speak. Camera: static. Final state: held frame on his stern face, then hard stop. AUDIO: <Quiet LA street tone: distant traffic, palm rustle.> <Cap click; wet squeak of applicator on glass in Stage 4.> <At 21s: metallic rotary crank, glass sliding in its rubber channel, soft thud as it seats.> English, natural American accent, soft and embarrassed, spoken by the woman at approximately 24s: {Oh my god, I am so sorry.} No music. CONSISTENCY: Exactly one woman and one man. Keep her face, bun, jewelry, tattoos, cream halter dress and terracotta phone case with attached gloss unchanged in every shot. The gloss tube never leaves her hands. The man stays seated, same shirt and watch. Same car, street and sun direction throughout. Window fully closed until 21s, lowers only once. NEGATIVE PROMPT: no extra people, no second car, no duplicate woman, no face distortion, no identity change, no wardrobe change, no plastic skin, no beauty filter, no cartoon, no cheap CGI, no floating objects, no open window before 21s, no other on-screen text, no captions, no subtitles, no watermarks, no music, no smooth gimbal glide, no zoom.

SEEDANCE 2.5 · 30S · 9:16 · EIGHT-STAGE MAGIC SHOW FORMAT: 30 seconds / 9:16 vertical / one continuous handheld shot, no cuts / comedic magic-show performance STYLE: Photorealistic smartphone footage, bright cream living room, soft daylight from the window on the left, natural color, shallow depth of field, true handheld iPhone feel with breathing sway and small reframes, no smooth gimbal. A real puppet filmed at home, not CGI. REFERENCES: @Image 1 defines the puppet (plush peach terry-cloth skin, dark curly hair, black square sunglasses, drawn-on mustache and goatee, cream cable-knit sweater, grey trousers, plush mitten hands), the room, and the brown suede and cream chunky sneaker used in Stage 4. Ignore that the sneaker is already in hand. @Image 2 defines the black smartphone: size relative to the puppet hands, rounded frame, one-hand grip. Do not inherit its screen content. @Image 3 defines the exact phone screen content for Stage 7: dark-mode social profile page. Reproduce faithfully. Ignore the status bar time. VIDEO PROMPT: The subject is one hand puppet, the puppet from @Image 1, seated at the front edge of the travertine coffee table facing camera, eye-level medium shot from hair to trousers. The puppeteer is hidden below frame; only the puppet's two plush hands touch the props. The puppet moves like a real hand puppet: head bobs, shoulder wiggles, quick tilts, proud showman attitude. [Stage 1 — approximately 0 to 4s] Initial state: the puppet holds a black felt top hat upside down in its left hand, open crown up, brim at chest height. A real live budgerigar, sky-blue body, white face, fine black wing barring, perches calmly on the puppet's right shoulder. The puppet gives the camera a confident nod and raises its right hand. End state: hat in left hand, bird on right shoulder, right hand raised. [Stage 2 — approximately 4 to 8s] Continue. The right hand gently cups the budgerigar, lifts it off the shoulder and lowers it into the open hat until it disappears below the brim. The puppet pats the hat once. End state: hat upright in left hand, right hand on the brim, shoulder empty. [Stage 3 — approximately 8 to 11s] Continue. The puppet tips the hat so the open crown faces the camera and fills the lower third of frame. The interior is completely empty: smooth black satin lining, no bird, no feathers. The puppet shrugs and tilts its head. Camera pushes slightly toward the opening. End state: empty hat opening facing camera, in the left hand. [Stage 4 — approximately 11 to 15s] Continue. The puppet turns the hat crown-up, plunges its right hand deep inside past where the bottom should be, then pulls straight up. The sneaker from @Image 1 rises out toe first, full size, laces swinging, clearly larger than the hat opening. The puppet lifts it beside its face, side profile to camera. Camera tilts up to follow. End state: sneaker high in the right hand, hat in the left hand. [Stage 5 — approximately 15 to 19s] Continue. The puppet lowers the sneaker to chest height in its right hand. With the left hand it pinches the edge of the hat brim with two fingers and lifts; as it lifts, the stiff hat instantly softens and collapses into one square black silk handkerchief hanging from its fingers, edges rippling, no hat remains. The puppet drapes the handkerchief fully over the sneaker so the shape is covered. End state: right hand holds a cloth-covered object, left hand holds the top corner of the handkerchief. [Stage 6 — approximately 19 to 23s] Continue. The puppet whips the handkerchief away upward with the left hand. Under it the sneaker is gone; the right hand now holds the black smartphone from @Image 2, screen facing camera, still dark. The handkerchief falls out of frame below and is never seen again. The puppet does a proud shoulder wiggle. Camera gives a small jolt, then steadies. End state: dark phone in right hand at chest height, left hand free. [Stage 7 — approximately 23 to 27s] Continue. The puppet extends the phone toward the lens until it fills most of the frame width; the screen lights up showing the exact profile page from @Image 3, sharp and readable. Camera racks focus to the screen. End state: phone screen dominating frame with the profile displayed. [Stage 8 — approximately 27 to 30s] Continue. The left plush hand enters from above and taps the top edge of the screen once. On that tap the profile vanishes and the screen turns solid black with exactly two lines of clean white centered sans-serif text: the upper line reads Comment and the lower line reads "Prompt" with straight double quotation marks around the word Prompt. No other text, icons or logos. The puppet peeks over the phone and nods. Camera holds steady on this final frame to the end. AUDIO: <Quiet room tone.> <Budgerigar chirp at the start, a tiny flutter as it enters the hat.> <Felt rustle when the hat tips.> <Soft thud as the sneaker emerges.> <Silk swish on the transformation and the whip-away.> <Phone wake tone at 23s, one soft tap at 27s.> (Playful lo-fi jazz, brushed drums and upright bass, quiet throughout, a cymbal hit on each reveal, clean bass note on the final frame.) No dialogue. CONSISTENCY: Exactly one puppet, one bird, one hat, one sneaker, one handkerchief, one smartphone. Keep the puppet's face, sunglasses, hair, sweater and trousers identical to @Image 1; the sunglasses never come off. Room, lighting and camera position unchanged. Hat in left hand until it becomes the handkerchief; sneaker and smartphone only in the right hand. Once an object vanishes it does not reappear. The puppeteer stays hidden below frame. NEGATIVE PROMPT: no human hands or arms, no second puppet, no duplicate sneaker or phone, no bird reappearing, no feathers in the hat, no hat after the transformation, no extra text or watermark, no misspelled words, no morphing on the puppet face, no sunglasses removal, no CGI glow or particles, no smooth gimbal, no cuts, no lighting or room change.

FORMAT: 30s / 9:16 vertical / luxury fashion film into automotive ASMR drive / fast-cut opening, then long takes / no music STYLE: Hollywood live-action realism, ARRI Alexa LF, anamorphic, fine 35mm grain, warm low late-afternoon sun, long soft shadows, natural light only, shallow depth of field on the man, editorial fashion grading in cream, sand, caramel and white. One visual identity, no style mixing. REFERENCES: @Image 1 is a six-panel sheet of ONE white wide-body sports coupe and ONE location. It defines only: the car (white body, wide arches, large white swan-neck rear wing, white multi-spoke wheels, full-width red rear light bar, cream and caramel leather interior, caramel steering wheel) and the environment (white curved architecture, facade lettering exactly as shown, horizontal red light strip, two white arched hangar entrances, sand-colored concrete plaza, warm sky). Ignore the grid layout. The panels are NOT keyframes, shot order or angles to copy. Exactly one car, no collage. @Image 2 defines the hero's face and identity ONLY: dark brown tight curly medium-length hair, black square-framed sunglasses, short mustache and light beard, warm skin tone, relaxed half-smile. Do not inherit his grey t-shirt, food or restaurant background. WARDROBE (fixed): cream heavyweight boxy tee; open chocolate-brown suede overshirt, cuffs pushed up; cream wide-leg pleated wool trousers; cream-and-brown suede New Balance 9060 sneakers with a chunky layered sole; matte black square sunglasses never removed. VIDEO PROMPT: [Stage 1 — approx 0–5s] FASHION CUT. Six hard cuts of about 0.8s, no transitions, each a different lens, all on the plaza, white car in the far background. Cut 1: ground-level macro, a sneaker lands on concrete, trouser hem swings. Cut 2: 100mm close-up of the suede sleeve, hand pushing the cuff up. Cut 3: tight profile of the sunglasses, the white car reflected in the lens. Cut 4: 35mm handheld from behind, curls catching sun, car soft ahead. Cut 5: waist-level tracking of the trousers. Cut 6: high oblique drone at about 45 degrees, the man a small figure crossing toward the car, long shadow leading him. End state: man mid-plaza, walking left to right toward the driver door, car about 15 meters away. [Stage 2 — approx 5–11s] Continue from mid-plaza. Camera: one continuous drone shot, diagonal top-down at about 45 degrees, descending and drifting to hold man and car in one frame. He walks at a steady unhurried pace, hands relaxed. At 9s the drone is about 3 meters off the ground behind him as he reaches the driver door. End state: he stands at the driver door, right hand on the handle, sunglasses on. [Stage 3 — approx 11–18s] ASMR INTERIOR. Continue from hand on handle. Camera: restrained handheld, breath-level micro movement only, no gimbal smoothness. Shot A: close-up of the handle, the door unlatches and swings open. Shot B: from the passenger seat, he lowers into the cream seat, door pulls shut with one solid close. Shot C: macro of his hands settling on the caramel wheel, thumbs on the stitching. Shot D: macro of the seatbelt buckle clicking home. Shot E: macro of fingers on the ignition, one press at 17s; the dashboard wakes. End state: engine at idle, both hands on the wheel, sunglasses on, door closed. [Stage 4 — approx 18–26s] DRIVE. Continue from idle. Shot A: low static ground-level shot beside the rear wheel, the car pulls out of the plaza left to right, rear wing and red light bar crossing frame. Shot B: drone chase from a high oblique 45-degree angle behind, the car leaving the plaza onto a long empty two-lane asphalt road through pale sand terrain, the drone descending as the car accelerates; speed shown by road markings streaming past. Shot C: interior over-the-shoulder from the passenger headrest, his hand shifting, road unrolling through the windshield, sunlight sliding across the sunglasses. End state: car at speed on the empty road, no other vehicles. [Stage 5 — approx 26–30s] CLOSING. One continuous drone shot: from a rear-following position the drone rises and slows while the car continues away, becoming small on the straight road with its long shadow, the architecture faint on the horizon. Hold the final frame for the last second, car still moving. Final state: one white car receding on an empty road, no text. AUDIO: No music at any point. Diegetic sound only, close-miked, ASMR clarity. Stage 1: <crisp sneaker steps on concrete, suede rustle, light dry wind, each cut lands on a footstep>. Stage 2: <footsteps growing closer, soft wind>. Stage 3: <door latch, leather creak as he sits, one deep solid door close, hands on stitched leather, seatbelt click, at 17s a single ignition press then a raw naturally aspirated flat-six cold start bark settling into a textured idle with low-frequency pressure>. Stage 4: <tires on asphalt, engine climbing the rev range, one clean upshift, exhaust echoing off the architecture then opening into wide space, wind rising>. Stage 5: <engine fading into distance, wind takes over, final second near silent>. No voiceover. CONSISTENCY: Exactly one man, the hero from @Image 2. Exactly one car, the white coupe from @Image 1. Keep face, curly hair, black square sunglasses, wardrobe, car color, white wheels, rear wing, red light bar and interior unchanged in every shot. Sunglasses stay on for all 30 seconds, including inside the car. Man walks left to right; car exits left to right, then away from camera. Sun low from the left throughout. No other people, vehicles or graphics. NEGATIVE PROMPT: no music, no voiceover, no subtitles, no on-screen text, no watermarks, no split-screen, no grid, no panel borders, no collage, no second car, no duplicate man, no face distortion, no identity change, no sunglasses removed, no wardrobe change, no grey t-shirt, no hat, no warped wheels, no morphing car body, no extra rear wings, no cartoon, no cheap CGI, no plastic skin, no flat lighting, no smooth gimbal in Stage 3, no night, no crowd.

SEEDANCE 2.5 · START FRAME → 12 S SINGLE TAKE · STEP 02 OF 02 Continuous single-take handheld vertical smartphone video, 12 seconds, no cuts. Scene lock from the start frame: harsh midday sun, orange sandstone cliff edge, young woman in a black swimsuit on the lip, black climbing net stretched across the canyon far below, blonde friend sitting behind her. Keep the start frame's lighting, colors, framing and her face unchanged. 0-3s: She rocks on her toes, exhales, glances back at the friend who says "you're actually doing it". Wind moves her ponytail. The camera creeps closer to the edge, tilting down to show the drop. 3-5s: She drops off the edge feet-first, arms up, falling straight down past the rock face, the camera tilting down to follow. She hits the net dead center, the net sinking deep in a V, the anchor ropes creaking taut. 5-9s: The net snaps back and launches her upward, higher than she fell, her body straightening, arms reaching, rising up the rock face toward the camera in one clean arc. The friend screams. The camera jerks back as she rises into frame. 9-12s: At the top of the arc she grabs the exact lip of rock she jumped from with both hands, hangs for half a second with her feet against the wall, then pulls up and swings a knee over the edge, sitting down on the rock next to the friend, breathing hard, wiping chalk on her thigh. The friend grabs her arm, laughing and shouting. The net still swaying below. Camera behavior: tilt down to follow the fall, tilt back up fast, framing lost and recovered, rolling shutter wobble, sun flare at the top of the arc, autofocus hunting on the net far below. Ambient audio: desert wind, a gasp, the net creaking and thudding, the friend screaming then laughing, her breathing hard at the end. No music. No text, no overlay, no logo, no slow motion, no drone angle, no cinematic camera moves, no cuts.

Continuous single-take handheld vertical smartphone video, 12 seconds, no cuts. Scene lock from the start frame: dim humid reptile enclosure under a corrugated shade roof, algae-streaked concrete wall above a shallow murky green pool, a keeper in a dark green polo kneeling on the wet ledge leaning down with his bare forearm holding a dead rat over the water, a very large green anaconda coiled half-submerged below with one coil tensed, railing bars and a child's hand at the bottom of the frame, visitors' sneakers at the top edge. Keep the start frame's lighting, colors, framing and the keeper's face unchanged. 0-3s: The keeper dangles the rat, tapping it on the surface, the anaconda's head drifts closer, tongue flicking, coils shifting slowly under the water. The keeper glances up and says something to the visitors, then looks back down. 3-5s: The snake strikes upward in a blur, bites the keeper's forearm, and in the same motion a thick coil whips up over the wall edge and wraps his arm, yanking him forward so his chest slams onto the concrete lip, head and shoulders hanging over the pool. The rat drops into the water. 5-9s: The keeper braces his free hand against the wall and shouts, his legs kicking on the ledge. A second keeper in the same green polo sprints into frame from the right, grabs him by the belt and waist, and both pull backwards while the snake's body tightens and drags the trapped arm toward the water, the wet coil sliding on the concrete. A third pair of hands grabs the first keeper's shoulder. 9-12s: With a sudden lurch they all fall backwards onto the ledge in a pile, the anaconda releases and drops back into the pool with a heavy splash, its body sliding away under the green water. The camera stumbles back as the visitor retreats, framing tilting to the railing and back, finding the first keeper sitting up clutching his forearm, the second keeper on his knees, a child crying somewhere behind the phone. Camera shakes hard at the strike, framing slips and recovers, autofocus hunting between the railing bars and the keepers, rolling shutter wobble, slight exposure flicker under the shade roof. Ambient audio: echoing enclosure acoustics, a splash, men shouting "pull, pull", the metal railing rattling, a child screaming, a woman saying "oh my god" repeatedly. No music. No text, no overlay, no logo, no slow motion, no cinematic camera moves, no cuts.

SEEDANCE 2.5 · VIDEO PROMPT · 15S · 9:16 FORMAT: 15s / 9:16 vertical / viral handheld comedy / one continuous shot, no cuts, no zoom STYLE: Ultra realistic smartphone handheld footage, natural overcast daylight, real world physics, slight handheld shake from a friend filming, no cinematic grading, no slow motion, documentary authenticity. REFERENCES: @Image 1 defines the environment, camera vantage and wardrobe ONLY: a tall old brick and stone wall on a cliff edge above a hazy canyon, a thick natural fiber rope hanging over the top edge, and two outfits. Outfit A (man on top of the wall): blue satin varsity jacket with orange-and-white striped cuffs and embroidered patches, dark navy baseball cap. Outfit B (climbing man): burgundy wool varsity jacket with cream striped trim and chenille letter patches, dark denim jeans, grey suede sneakers, black baseball cap. Use its framing, wall texture, rope, cliff and haze exactly. Do NOT use its faces. VIDEO PROMPT: [Stage 1 — approx 0–4s] Initial state: the handheld phone camera holds the same vantage as @Image 1, slightly below the top of the wall, looking at the brick face and the canyon haze behind it. Only ONE man is visible: the blue-jacket man leans over the top edge of the wall gripping the rope with both hands. The rope runs taut straight down the wall and exits the bottom of frame. Nobody else is in frame. Event: he pulls hand over hand with visible effort; his shoulders strain, his cap tilts, small dry dust falls from the bricks where the rope rubs. Camera: restrained handheld, small breathing shake, no pan. End state: the blue-jacket man is still on top gripping the rope, the rope is taut, the lower half of the wall is empty. [Stage 2 — approx 4–9s] Continue from that state. Event: the burgundy-jacket man rises slowly into frame from the bottom edge, climbing the rope, his grey sneakers planted flat against the bricks, body leaning back away from the wall, cap visible, sunglasses on, face tilted up toward the top. He gains roughly one brick row per pull, slow and effortful, nothing sudden. Camera: same handheld hold, follows nothing, keeps both men in frame. End state: the burgundy-jacket man is about one arm length below the top edge, both hands on the rope, feet on the wall; the blue-jacket man still holds the rope from above. [Stage 3 — approx 9–12s] Continue from that state, everything at normal real-time speed. At 9s the blue-jacket man releases the rope with his right hand and reaches down toward the climbing man with an open palm, keeping his left hand on the rope. The burgundy-jacket man glances up, lets go of the rope with his right hand and snaps his hand up to the offered palm in one quick natural motion; the grip lands immediately, no pause, no stretched moment, the frame rate and motion speed stay exactly as in the previous stages. Right after the grip the burgundy-jacket man's feet scrape and slip off the bricks. End state: right hands locked together, the blue-jacket man bent far over the edge, the burgundy-jacket man hanging from that grip with feet off the wall. [Stage 4 — approx 12–14s] Continue from that state. Event: the added weight pulls the blue-jacket man forward; his chest slides over the top edge of the wall and he tips over it, still holding the other man's hand. Both men drop together straight down along the wall face and exit the bottom edge of frame within one second, the rope whipping after them. The camera does NOT tilt down to follow them. End state: no people in frame. [Stage 5 — approx 14–15s] Hold the empty composition: only the brick wall, the loose rope end swinging against the bricks, dust drifting down, canyon haze behind. Hard stop on the empty frame. AUDIO: <light wind across the cliff, distant canyon ambience, rope fibers creaking under load, grit and small stones scraping on brick, strained breathing and effort grunts from the blue-jacket man, sneaker rubber scuffing brick as the second man climbs, a short surprised shout from both men as they tip, then only wind and the rope tapping the wall> No music, no voiceover, no dialogue. CONSISTENCY: Exactly two men, both with the identical face from @Image 2. Outfit A stays on the man on top, Outfit B stays on the climbing man; no wardrobe swap. Sunglasses and caps stay on both men in every stage. One single rope. Camera vantage, wall, cliff and haze unchanged from @Image 1. Camera never pans, tilts or zooms. Constant real-time playback speed from first frame to last; the hand grab plays at the same speed as the climbing. The burgundy-jacket man is absent until Stage 2. Both men exit the bottom of frame together in Stage 4 and never reappear. NEGATIVE PROMPT: no third person, no duplicate hands, no merged hands, no face change between the two men, no different faces, no wardrobe change, no camera pan or tilt, no slow motion, no time ramp, no speed change at the hand grab, no cuts, no cinematic color grade, no floating, no impact shown, no landing shown, no on-screen text, no captions, no watermark, no music.

Five stages inside one continuous shot, each closing with an explicit End state. Paste it as written.

SEEDANCE 2.0 · 9:16 · 15S · ONE CONTINUOUS HANDHELD TAKE FORMAT: 15s / 9:16 vertical / extreme 4DX cinema illusion / single continuous handheld take STYLE: Raw documentary phone-in-the-theatre aesthetic, amateur smartphone capture, natural handheld sway with hard startled jolts at the blast, rolling shutter wobble, phone auto-exposure locked on the bright screen so the room reads dark, exposure blooming as the wave passes, autofocus hunting, no cinematic grading, sharp phone sensor detail. REFERENCES: Match Reference 1 exactly - the dark auditorium, the crowd holding glowing phones, the grey 4DX wall signs, and the film on screen: a live-action fantasy movie, a man with spiky white hair in a blue outfit crouched in a rocky storm-lit canyon, charging a glowing blue sphere of swirling wind and energy between his hands. Preserve his face, hair and screen image style. VIDEO PROMPT: 0-4s: Normal screening filmed from a middle-row seat. On screen the man strains against the growing sphere, arms trembling, blue lightning crackling, the screen light pulsing over the rows. 4-6s: He drags the sphere back beside his hip, body coiling for momentum, the rumble deepens, seats tremble. 6-9s: He thrusts both hands forward - a visible glowing blue energy wavefront bursts off the screen, crosses the screen plane and physically travels through the auditorium air from the screen toward the back rows, a churning wall of light, wind and dust moving above the seats, occluding the front rows as it passes over them, casting racing shadows across the walls and 4DX signs. Small rocks, branches and leaves from the canyon tumble inside the wave over the audience. 9-12s: The wavefront sweeps row by row toward the camera and past it - people duck low in sequence as it reaches them, caps and popcorn ripped backward, hair and jackets whipped flat, debris and leaves raining between the seats, screams, the camera jolts hard as the wave passes overhead and continues to the back wall, dust swirling in the screen light. 12-15s: The wave dies against the back wall. The camera whips around 180 degrees to the row behind: a middle-aged man sits frozen in stunned silence, eyes wide, mouth open, his glasses knocked crooked across his face, leaves in his hair - he holds the deadpan shocked stare for a beat, then snaps out of it and yells "Dude, that was AWESOME!". Hard stop, no fade. SOUND: Diegetic film audio - crackling energy and a deep charging hum escalating; at the thrust a massive WHOOMP, then a roaring wind wave audibly traveling front-to-back through the room with low-frequency pressure, debris clattering off seats, screams in sequence as it passes; sudden near-silence with dust settling, ringing ears ambience, then the stunned man's clear voice: "Dude, that was AWESOME!", no music, no voiceover. NEGATIVE PROMPT: no cuts, no zoom, no gimbal smoothness, no cinematic grading, no cartoon, no anime style, no distorted faces or hands, no injuries, no screen tearing, no fire, no caption overlays, no subtitles, no watermarks.

Handheld shaky camera moves forward. As the woman sews the T-shirt, the man whose head is sticking out of the T-shirt turns to her and jokingly says in English, "I'm the best T-shirt you've ever sewn, aren't I?" Add cinematic vibe. Add real-time motion.

Style: photoreal live-action, filmed on a spectator's handheld smartphone from a huge daytime crowd at an open-air theater (matching @Image1) — raised phones in the foreground, distant city; bright sun-drenched daytime; realistic, weighty, effective fantasy combat with GRAND black-energy VFX; stylized magic, no blood, no gore. CAMERA: a FIXED camera position, NO zoom, NO push-in, NO dolly — only small pans and tilts to keep the fight in frame; stay wide, no face close-ups. @Image2 = the hero archer with his giant obsidian bow; he teleports in bursts of black dust-energy to deliberate flanking positions, aiming his arrows purposefully. @Image3 = the giant rival, about twice the hero's height, who actively FIGHTS BACK throughout — charging and hurling ripped-up stones. ONE continuous shot, no cuts, FIXED camera, minimal pan/tilt only: 0-4s: the giant rips a slab of stone from the ground and HURLS it at the archer; the archer teleports in black dust to dodge, lands at a flanking spot to the giant's LEFT and looses an arrow that opens a swirling BLACK HOLE right there beside the giant — a deliberate mark. 4-8s: the giant tears up another stone and throws again, then swings a heavy arm; the archer teleports to dodge and repositions to the giant's RIGHT, loosing another arrow that opens a second black hole deliberately beside him — a real back-and-forth exchange. 8-11s: the giant charges and swings hard; the archer teleports behind him and looses a big obsidian arrow that strikes the GIANT square in the chest and stays embedded there, glowing. 11-15s: the two flanking black holes ignite and PULL the giant from both sides at once; he is dragged apart into great streams of black dust shot through with swirling dark-blue energy and sucked into the vortexes; the holes collapse and vanish; the crowd erupts. Audio: roaring crowd; stone tearing and heavy thrown-rock impacts, teleport dust whooshes, taut bow draws and sharp arrow releases, vortex hums as black holes open, a heavy thunk as the arrow embeds, a building gravitational roar then a suck-and-collapse boom, scattering dust, crowd erupts on the final frame. Preserve: ONE continuous shot, no cuts; FIXED camera, pan/tilt only, NO zoom, stay wide, no face close-ups; the hero (@Image2) with obsidian bow, the giant (@Image3) ~2x height actively fighting back with stone throws; purposeful black-hole placement beside the giant; photoreal live-action; black dust-energy, obsidian arrows, swirling black holes, dark-blue energy within the black dust; distant huge stage, crowd and city from @Image1; foreground spectators with raised phones; stylized fantasy, no blood or gore; no on-screen text.

ONE CONTINUOUS SHOT — NO CUTS, TRANSITIONS, TELEPORTATION OR HIDDEN EDITS. Use the reference images exactly: take the character's glasses-free face, eyes and facial structure from Image 2; take his curly hair, beard and the exact black square-framed sunglasses from Image 1 — the sunglasses stay ON in every frame. Ignore the clothing, backgrounds, food and table in both reference photos. Wardrobe: gray double-breasted suit, tie, briefcase and Sony Ericsson W810i. No identity, wardrobe or prop changes. Bright, colorful, sunny Midtown Manhattan, early-2000s MiniDV Handycam aesthetic: 4:3 SD, CCD softness, natural handheld shake, tape artifacts. No modern cinematic sharpness or desaturation. Character runs through the crowd while cameraman follows. Dialogue finishes within 2 seconds: "Got the prompt?" — "Not yet, I'm getting it now." — "Hurry." — "I've got it." Immediately he trips. Coffee, papers, phone and briefcase fly naturally. Sunglasses remain one intact, unbroken pair on his face. Before impact, within 2–3 seconds, TIME FREEZES COMPLETELY. Everything freezes except the camera. Absolute silence: no dialogue, voices, traffic or phone audio. Camera smoothly evolves from handheld into FPV flight, rises above the frozen Manhattan scene, flies past the character, intact sunglasses, coffee, phone and documents. End on a physical document reading exactly: "COMMENT 'PROMPT' TO GET THE FULL PROMPT" No digital text or overlays. Orbit back to the original position. Time instantly resumes with no transition. Objects continue naturally, character hits the ground, gets up, adjusts his intact sunglasses, looks at his phone, then at camera in disbelief. Crowd and traffic continue normally. Maintain realistic physics, bright colors, exact identity and continuous spatial continuity throughout.

FORMAT: 20s / 9:16 vertical / viral comedy, candid iPhone beach footage / one continuous handheld take, no cuts STYLE: Realistic smartphone video look, natural overcast daylight, handheld shake from the filmer, real world physics, no cinematic grading. REFERENCES: @Image 1 defines the hero: curly dark wet hair, short beard, black square framed sunglasses that stay ON in every frame, shirtless, grey laptop, paper coffee cup. Identity and props only. @Image 2 defines the same single man's face and hair only; ignore its clothing, food and background. VIDEO PROMPT: [Stage 1 — approx 0–2s] Initial state: handheld phone view from a sandy beach, choppy sea, a few ordinary swimmers near the shore, one man visible very far out. Event: the unseen woman filming notices him. Camera: quick punch zoom toward him at 2s. End state: the man fills the frame in a long lens look. [Stage 2 — approx 2–8s] Continue from the zoomed view. The man stands chest deep in rolling waves, typing on the open laptop on one hand, lifting it above each incoming wave at the last second, sipping coffee between waves. A dark dorsal fin slowly circles him. Camera: handheld zoomed follow, micro shake. End state: the fin passes close in front of him; he freezes mid sip. [Stage 3 — approx 8–15s] Continue. He downs the last coffee, the empty cup drifts away, he snaps the laptop shut and holds it like a paddle. Each time the shark lunges near the surface he swats its snout once with the flat closed laptop while wading toward shore. The shark keeps following. Camera: the filmer tracks him along the waterline, frame bouncing with her steps. End state: he is waist deep, shark beside him. [Stage 4 — approx 15–20s] Continue. One final firm swat; the shark goes limp and dazed at the surface, unharmed. He tucks the limp shark under his right arm, closed laptop in his left hand, and walks out of the surf toward camera, deadpan, sunglasses on, water streaming off him. Camera: slow zoom out. Final state: held frame as he passes the camera, shark under his arm. AUDIO: <realistic beach ambience: rolling waves, light wind over the phone mic, distant kids, seagulls> No music. English, natural American accent, woman filming, amused, off camera: at 1s {Oh my god you guys look at this.} at 5s {Is he literally working out there?} at 9s, alarmed then laughing {There is a shark. There is an actual shark!} Male bystander, American accent, off camera at 13s {He is fighting it with the laptop bro!} Woman at 18s, laughing {No way. He is taking it home.} CONSISTENCY: Exactly one man in focus, one shark, one laptop, one cup. Sunglasses remain on in every frame. Keep face, hair and props unchanged. Camera never enters the water. No other swimmer interacts with him. NEGATIVE PROMPT: no face distortion, no identity change, no sunglasses removal, no injuries, no bite contact, no cartoon shark, no cheap CGI, no cinematic grading, no captions, no on screen text, no music, no extra sharks, no duplicate man.

SEEDANCE 2.5 · IMAGE TO VIDEO · 30S · 9:16 · 2 REFERENCES FORMAT: 30s / 9:16 vertical / influencer travel vlog ad / fast-cut montage opening, then one continuous handheld selfie take STYLE: Authentic phone-shot influencer vlog realism, natural golden-hour Mediterranean light, warm color, slight handheld micro-shake from her arm, shallow phone-camera depth, no cinematic grading, one consistent visual identity. REFERENCES: @Image 1 defines the influencer: her face, freckles, wavy sun-bleached blonde hair, black bikini, sheer orange-and-white striped kimono, layered gold chain necklaces with a small coin pendant, gold rings, AND the balcony location with white railing, string lights, terracotta floor and the open sea view with cliffside village. Preserve identity and wardrobe exactly in every cut. @Image 2 defines ONLY the white wordmark logo that appears on the black parachute canopy in Stage 5. Treat the black background of @Image 2 as the canopy surface itself. The logo appears nowhere else in the video. VIDEO PROMPT: [Stage 1 — approx 0-2s] Quick vlog cut: the same woman in the same kimono outfit walks toward camera down a narrow sunlit Italian cliffside village lane with lemon trees and pastel walls, smiling, hair moving in the breeze. Camera: handheld phone tracking backward at chest height. End state: she is mid-stride, relaxed. [Stage 2 — approx 2-4s] Quick vlog cut: outdoor cafe table, she bites into a slice of pizza, eyes closing briefly with pleasure, silent delighted reaction. Camera: handheld close-up across the table. End state: slice lowered, she chews happily. [Stage 3 — approx 4-7s] Quick vlog cut: she stands at the edge of the lane as a young dark-haired Italian man rides past on a vintage scooter and turns his head to look at her. She glances at the camera with raised eyebrows. English, natural American accent, playful teasing influencer tone: {Italian men...} End state: scooter exits frame right, she smirks at the lens. [Stage 4 — approx 7-12s] Hard cut to the balcony from @Image 1, matching its framing: selfie-style front camera held in her extended arm, sea and cliffs behind her, boats crossing the water. She talks straight into the lens with real influencer energy. English, natural American accent, confident casual delivery: {I was made with AI. My hair is not real.} She lifts a strand of hair toward the lens; the camera pushes in close so individual hair strands catch the light. End state: camera close on hair, her face partly visible behind it. [Stage 5 — approx 12-16s] Continue from the close hair shot. She lets the hair fall and lifts the coin pendant with two fingers. English, natural American accent, same delivery: {Neither is this necklace.} Camera pushes to a near-macro on the gold chain and pendant, tiny natural handheld drift. End state: pendant resting back on her chest. [Stage 6 — approx 16-23s] English, natural American accent, same delivery: {Nor is this Amalfi vacation.} She swings the phone camera away from herself toward the open sea: boats leaving white wakes, two seagulls flying past close to the lens. At approx 19s a single paraglider crosses the frame from the cliff side gliding toward the sea: pitch-black canopy and harness, the white wordmark from @Image 2 large and clean on the canopy, one distant joyful male scream: {Woohoo!} End state: paraglider small over the water, camera still on the view. [Stage 7 — approx 23-30s] She swings the camera back to her face, wind in her hair, golden light on her skin. English, natural American accent, slower, teasing, dropping to a knowing tone: {So... how was I created?} She gives a silent knowing smile directly into the lens. Final state: held selfie frame on her smile, sea behind her, no camera movement. AUDIO: <Coastal wind, soft waves below, seagull calls, fabric flutter of the kimono. Stage 1: distant village ambience and footsteps. Stage 2: cafe chatter, plate clink, one soft bite. Stage 3: scooter engine approaching and passing. Stage 5-6: wind rises slightly on the open view, faint canopy flutter as the paraglider passes.> All dialogue lines as written per stage, recorded like a real phone vlog: close, present, slightly windy. No music. CONSISTENCY: Exactly one woman, the SAME woman from @Image 1 in every cut: same face, freckles, blonde wavy hair, black bikini, striped kimono, gold necklaces and rings, unchanged across all locations. Exactly one scooter rider, visible only in Stage 3. Exactly one paraglider, visible only in Stage 6, logo only on its canopy. Balcony layout, railing, lighting direction and sea view match @Image 1. NEGATIVE PROMPT: no identity change, no face distortion, no wardrobe change, no extra people on the balcony, no second woman, no duplicate paraglider, no logo anywhere except the canopy, no logo distortion, no on-screen text, no captions, no subtitles, no watermark, no music, no cartoon look, no cinematic color grading, no plastic skin, no warped hands, no unnatural camera stabilization.

FORMAT: 30s / 16:9 / romantic cinematic couple film / soft rhythmic cuts driven by rack-focus transitions and motion-blur passes, dreamy flowing pace STYLE: 35mm analog film aesthetic matching @Image 3: fine grain, soft pastel grade, creamy halation, muted greens and warm skin tones, golden late-afternoon Aegean light, gentle handheld sway, shallow depth of field as the storytelling tool, romantic realism, one visual identity, no style mixing. REFERENCES: @Image 1 defines the couple's identities: preserve both faces exactly. HIM: curly dark brown hair, light beard, black square-framed wayfarer sunglasses, thin silver chain, the same cream resort shirt with botanical embroidery, now with relaxed beige linen trousers and tan espadrilles. HER: dark chin-length bob under a white patterned headscarf tied at the nape, white angular cat-eye sunglasses, small red hoop earrings. Both keep sunglasses on in every shot. @Image 2 defines HER outfit exactly as she appears: sleeveless blue denim mini dress with raw hem, beige suede espadrilles, delicate bracelets. No handbag. This styling is identical in every shot. @Image 3 defines the car, field and film texture: a white classic air-cooled sports coupe with a low rear spoiler, front trunk lid open and overflowing with a lush arrangement of orange, yellow, cream and red wildflowers, parked in a tall green meadow dotted with wildflowers. Match this exact car, arrangement and analog texture. @Image 4 defines the backdrop ONLY: the hilltop acropolis of Lindos, ancient stone walls and columns above a cascade of white cube houses and dry Aegean slopes, deep-blue sea beyond. It sits softly hazed in the far background of every wide shot; use it as scenery only. VIDEO PROMPT: [Shot 1 — 0–2.5s, hook] Extreme close-up through blurred foreground wildflowers in the breeze; rack focus pulls slowly from the petals to the white coupe, its open trunk glowing with flowers, the acropolis a warm silhouette in the haze. End state: car sharp, petals blurred. [Shot 2 — 2.5–5s] Cut. Close-up on the trunk flowers; rack focus drifts past the blooms to the couple far behind in the bokeh, running toward camera through tall grass, laughing. End state: couple sharpening, growing in frame. [Shot 3 — 5–8s] Cut. Low fast tracking through the grass, heavy natural motion blur: she runs ahead, headscarf tails streaming, glancing back with a laugh; he chases two steps behind, linen trousers rippling, grass whipping past the lens. End state: her hand almost caught. [Shot 4 — 8–10.5s] Cut. He catches her hand mid-stride; momentum swings them into one playful spin, grass seeds and petals lifting in the golden backlight, motion blur streaking the meadow. End state: spin settling, foreheads close. [Shot 5 — 10.5–13s] Cut. Still macro: her white cat-eye lenses fill the frame, his smiling reflection mirrored in both lenses, background melting to golden bokeh. Focus racks from the reflection to her soft smile. End state: her smile sharp. [Shot 6 — 13–15.5s] Cut. He jogs to the open trunk and picks one perfect orange-gold bloom with a soft stem snap; a few loose petals drift off. End state: bloom raised, trunk still full. [Shot 7 — 15.5–19s] Cut. Slow dolly push-in, waist to close: he gently tucks the bloom under the edge of her headscarf above her ear; her hand rises to hold it; both laugh quietly, the acropolis glowing in the haze between their shoulders. End state: flower seated, her fingers on it. [Shot 8 — 19–21.5s] Cut. He lowers the trunk lid with care to a soft vintage click; they split around the car, both doors open, they drop into the seats, twin door thunks. Sunglasses on. End state: both seated, smiling at each other. [Shot 9 — 21.5–24s] Cut. Through-windshield two-shot, warm reflections sliding over the glass: he drives relaxed, one hand on the thin wheel; she leans toward him laughing, then stretches her arm out the window, fingers surfing the wind. End state: her hand riding the wind. [Shot 10 — 24–27s] Cut. Side tracking with soft motion blur at wheel height: the coupe rolls along a narrow dirt track through the meadow, tall grass brushing the sills, wildflowers streaking past the lens. End state: car easing right toward the valley. [Final shot — 27–30s] Cut. Static wide: the coupe recedes down the winding track toward the white houses and the acropolis hill, a faint golden dust ribbon behind it, sea glinting beyond. One last rack focus from a sharp foreground wildflower to the tiny distant car. Hold the final frame 0.8s. AUDIO: (Intimate minimalist neoclassical score, warm felt piano with soft organic-electronic swells, entering on the first rack focus, breathing with the cuts, lifting gently when the flower is given, settling into a tender sustained chord over the final wide.) <ASMR-grade close-mic foreground: grass swishing against legs, soft footfalls on meadow soil, linen and denim fabric movement, her light laugh and his low chuckle, one delicate stem snap, petals brushing, the trunk lid's soft click, twin door thunks, a gentle air-cooled engine settling to a warm burble, tires rolling on dry earth.> <Background ambience: meadow breeze, cicadas, distant gulls, faint sea wash.> No dialogue, no voiceover, no subtitles. CONSISTENCY: The same two people as @Image 1 in every shot, identical faces, hair and skin tones; his black wayfarers and her white cat-eyes never removed; the orange-gold bloom stays at her headscarf from Shot 7 to the end. Identical outfits throughout. Exactly one white classic coupe, same flower arrangement. Same meadow and light direction, the acropolis always in the same far background position; screen direction left to right in the chase and drive. NEGATIVE PROMPT: no removed sunglasses, no altered identities, no outfit changes, no handbag, no second car, no other people, no traffic, no plate text, no on-screen text or logos, no drone shots, no style mixing, no CGI look, no warped hands, no distorted car, no crushed flowers, no dialogue.

FORMAT: 30s / 9:16 vertical / luxury menswear-automotive ASMR film / clean precise cuts, each shot built around one tactile sound event, calm confident pacing STYLE: Cinematic editorial realism matching @Image 2: soft overcast London light with warm boutique glow, muted stone and charcoal palette against silver paint, ARRI look with fine grain, shallow depth of field on detail shots, polished high-end commercial grade, one visual identity, no style mixing. All signage softly out of focus in every shot. REFERENCES: @Image 1 defines the hero's identity ONLY: preserve this exact man's face, features, skin tone, curly dark brown hair and light beard in every shot, black square-framed wayfarer sunglasses on at all times. Do NOT inherit any clothing, objects or background from @Image 1. Wardrobe redesigned in refined American heritage luxury style: navy unstructured double-breasted blazer over a crisp white oxford shirt, top button open, a cream cable-knit sweater draped over the shoulders and loosely tied, tailored beige pleated trousers, dark brown suede loafers, a slim silver dress watch. This exact outfit is identical in every shot. @Image 2 defines the environment and the car: a corner luxury heritage menswear boutique with a deep navy awning, tall dark-framed windows glowing warm with mannequins, pale limestone facade, granite sett pavement, and a silver modern flagship sports coupe parked at the curb: wide rear haunches, retractable rear wing, black multi-spoke wheels over yellow brake calipers, twin exhausts, dark glass roof. Match this exact storefront, street, light and car. Exactly ONE car, street otherwise empty. VIDEO PROMPT: [Shot 1 — 0–2.5s, hook] Interior-facing close-up on the boutique's brass door handle: a hand grips it, the latch releases with a crisp metallic click, and the tall glass door swings open into the grey street light. End state: door open, hero stepping through. [Shot 2 — 2.5–5s] Cut. Low cinematic angle from the pavement: the hero steps out of the doorway under the navy awning, adjusts the blazer lapel with one small tug, sunglasses catching the soft sky. Slow push-in as he pauses, seeing the car. End state: chin lifting toward the coupe. [Shot 3 — 5–7.5s] Cut. Tracking at knee height behind him: unhurried confident steps across the granite setts toward the car, loafers striking stone with clean sharp footfalls, trouser fabric swaying. End state: arriving at the front fender. [Shot 4 — 7.5–10s] Cut. Macro: his fingertips land on the silver fender and glide slowly along the beltline toward the door, reflections of the limestone facade sliding across the paint. End state: fingers stopping above the door handle. [Shot 5 — 10–12s] Cut. Extreme macro on the flush door handle: it deploys outward with a precise electric whirr and a soft click; his fingers curl under it. End state: handle gripped. [Shot 6 — 12–14.5s] Cut. The door swings open with a smooth hinge glide; he lowers into the black leather sport seat, leather flexing with a rich slow creak, and pulls the door shut with one deep thunk. Sunglasses on. End state: seated, settled. [Shot 7 — 14.5–16.5s] Cut. Interior macro: the seatbelt draws across the chest and the buckle seats with a bright metallic click; his hand comes to rest on the leather-wrapped wheel. End state: hands set. [Shot 8 — 16.5–19s] Cut. Macro on the start control: his finger presses it, the flat-six ignites with a deep muscular bark, then settles into a smooth turbocharged idle pulsing gently through the cabin. End state: idle steady. [Shot 9 — 19–21.5s] Cut. Rear exterior macro on the engine cover: the retractable wing rises slowly on its supports with a fine servo whirr until it locks. End state: wing fully deployed. [Shot 10 — 21.5–24s] Cut. Ground-level macro by the twin exhausts: the idle breathes, one restrained rev sends a low rounded pressure pulse toward the lens, faint heat shimmer. End state: burble settling. [Shot 11 — 24–27s] Cut. Wide from across the street: the boutique glowing behind, the silver coupe eases off the curb and rolls past camera left to right, tires pattering softly over the granite setts. End state: car crossing frame. [Final shot — 27–30s] Cut. Low rear three-quarter static: the coupe recedes down the narrow stone street, wing silhouetted, exhaust echoing softly off the facades and fading. Hold the final frame 0.8s as the street falls quiet. AUDIO: No music, no score anywhere. Pure diegetic ASMR sound design only, close-mic, crystal clean, intimate. <Foreground events in order: crisp brass latch click and door swing, awning fabric shifting in the breeze, clean loafer footfalls on granite setts, slow fingertip glide on paint, electric handle whirr and click, smooth hinge glide, rich leather creak, one deep door thunk, seatbelt draw and bright buckle click, start-control press, deep flat-six ignition bark settling to a pulsing turbo idle, fine servo whirr of the rising wing, one restrained exhaust rev, soft tire patter on setts, fading exhaust echo between the buildings.> <Continuous ambience: quiet London street, distant city hum, faint pigeons, light breeze.> No dialogue, no voices, no laughter, no vocal sounds, no voiceover, no subtitles. CONSISTENCY: One single hero throughout, exactly the same man as @Image 1: identical face, curly hair, beard and black wayfarer sunglasses in every shot; sunglasses never removed. Identical outfit in every shot, sweater staying draped over the shoulders. Exactly one silver coupe, same details, same parking spot. Same street, same overcast light; screen direction left to right for the walk and the drive. NEGATIVE PROMPT: no music, no soundtrack, no vocal sounds, no dialogue, no removed sunglasses, no altered identity, no outfit changes, no second car, no other people, no pedestrians, no traffic, no legible signage or plate text, no on-screen text or logos, no drone shots, no slow motion, no style mixing, no CGI look, no warped hands, no distorted car.

Six numbered shots, each with its own camera grammar, plus a sound design that does half the comedy. Paste it as written.

SEEDANCE 2.0 · 9:16 · 15S · ONE CONTINUOUS HANDHELD TAKE MASTER PROMPT — "Istanbul Bosphorus Tsunami Wave Tank BTS" (15s, vertical 9:16, handheld) ACTIVE REFERENCE Reference 1 is the exact design authority for the miniature set. Recreate its two hero structures at 1:24 scale, preserving proportions, materials and colour exactly: (a) the mid-channel island tower — low white stone curtain wall with crenellations on a rocky islet, an attached red-tiled roof block, a whitewashed half-timbered upper storey with dark timber framing and small dormer windows, a grey lead-covered dome with a small lantern and a green finial, and a tall white flag mast with a red flag; a small red-and-white striped light beacon on the rocks at its left, a low wooden pier with two moored white passenger ferries alongside. (b) the background suspension bridge — twin tall grey steel portal towers, sweeping main cables with vertical hangers, a slim road deck crossing the strait high above the shoreline. Also from Reference 1: the far shore — a domed waterside mosque with two slender minarets sitting under the bridge foot, dense cream, ochre and pale-yellow apartment blocks with red-tiled roofs climbing a green wooded hillside, a long low coastal viaduct running along the waterline, tiny ferries on the water. Use Reference 1 for architecture, colour and layout only — the footage itself is behind-the-scenes studio footage, not a location shot. GLOBAL LOOK Hyper-realistic behind-the-scenes smartphone footage, vertical 9:16, handheld with natural micro-shake, slight rolling-shutter wobble, phone autoexposure — must look like real leaked set footage, no cinematic grade. A colossal film soundstage: an Olympic-sized indoor wave tank filled with deep blue-green water standing in for the strait. The island tower sits on its rock islet in the centre of the tank, close to the near edge; the suspension bridge spans the far half; the mosque, viaduct and hillside townscape line the far bank. Background: enormous bluescreen wall with a grid of red tracking markers; overhead truss with panel lights; a large techno-crane with a stabilized camera head reaching over the tank. In the foreground, effects crew in black "EFFECTS CREW" t-shirts kneel along the concrete tank edge with cinema cameras on dolly track; monitors, tripods and cable runs on the studio floor. SHOT 1 (00:00–00:03) — Calm strait, tower reveal EFFECT: handheld observational hold + slow drift Elevated operator's POV over the crew's shoulders: flat calm water, the island tower and its red flag mirrored in it, the moored ferries idle at the pier, the bridge and minarets small behind, dolly rails in foreground, crew silhouettes against the bluescreen Phone exposure balancing bright water vs dark rigging Continuous take — the entire video is ONE unbroken handheld shot SHOT 2 (00:03–00:05) — Wave generation EFFECT: practical swell formation + slow camera tilt A massive smooth swell rises across the full width of the tank at the far end and rolls down the strait toward the bridge, glassy face catching the studio lights, already taller than the bridge deck The far-shore mosque disappears behind the rising face; crew lean into their eyepieces; handheld drift follows the swell SHOT 3 (00:05–00:08) — The bridge goes EFFECT: miniature-scale breaking wave + span collapse The wave breaks against the bridge: whitewater climbs both grey towers, the deck is buried, main cables snap on the near tower with a whipping recoil, and a whole deck section tears free and folds into the churn in slow heavy miniature physics, tiny cars spilling off it The surge shears the coastal viaduct off its piers and rips the mosque's near minaret away at its base Camera pans down-frame tracking the front as it closes on the tower SHOT 4 (00:08–00:12) — The tower falls, crew scramble EFFECT: hero miniature collapse + water breaching the tank wall The wall of foam slams the islet: the moored ferries are lifted and thrown over the pier, the light beacon snaps off its rock, water bursts through the crenellated stone wall and the red-tiled block is stripped away The half-timbered storey shudders, the lead dome tips, and the whole upper structure leans and topples sideways into the churn, the flag mast whipping down last — heavy, slow miniature physics Water crests the concrete tank edge and cascades onto the studio floor; crew grab gear and stumble backward off the dolly track. Handheld shake intensifies, quick reframes between the drowning tower and the fleeing crew. This is the SIGNATURE VISUAL EFFECT: the icon coming down practically, in-camera, in a studio tank SHOT 5 (00:12–00:15) — Overflow aftermath EFFECT: waterfall over tank edge + wide destruction tableau Sheets of water pour over the tank wall; in the foam float the lead dome with its green finial, the red flag still on its snapped mast, capsized white ferries, roof tiles and the twisted bridge deck; the bare stone islet wall stands broken above the churn, the crane arm silhouetted above Crew stand ankle-deep on the flooded floor, still filming; spray droplets visible on the phone lens Ends on this wide hold — no fade, hard stop MASTER EFFECTS INVENTORY Continuous handheld one-take (whole video) — micro-shake, imperfect reframes Practical wave-tank swell and break (shots 2–3) Suspension bridge collapse (shot 3) — cable snap, deck tear and fold Viaduct shear + minaret snap (shot 3) — background destruction layer Island tower collapse (shot 4) — wall breach, dome tip, sideways topple, flag mast last Ferry toss + beacon snap (shot 4) — small-scale impact beats Water breaching containment (shots 4–5) — cascades onto real studio floor Floating debris tableau (shot 5) — dome, flag, ferries, twisted deck Lens droplets + exposure shifts (shots 1, 5) — realism cues EFFECTS DENSITY MAP 00:00–00:05 = LOW (calm hold, swell rise — 2 effects) 00:05–00:12 = HIGH (wave break, bridge collapse, viaduct and minaret, tower fall, wall breach, crew scramble — 6 stacked) 00:12–00:15 = MEDIUM (overflow waterfall, debris tableau — 2 effects) ENERGY ARC Act 1 (0–5s): mirrored calm — tower, flag, ferries on still water; sells the "real shoot" premise Act 2 (5–12s): the wave takes the bridge, then the tower, then breaks the fourth wall by breaching the tank Act 3 (12–15s): flooded-floor aftermath, the red flag drifting past — hard stop AUDIO: raw on-set production audio only, no music — a loud "Action!", the hydraulic thump of the dump tank, a building roar of moving water, snapping scale cables, groaning steel, cracking timber miniatures, water slapping the stage floor, crew shouting off camera "Hold on! Keep rolling! Camera two, stay on the tower!" Negative prompt: no CGI-looking water, no color grading, no lens flares, no smooth gimbal motion, no cuts, no text overlays, no watermarks, no logos, no distorted hands or faces, no ocean horizon, no drone or aerial angle — the bluescreen and studio must stay visible; do not change the tower's proportions, dome shape or flag.

SEEDANCE 2.0 · 4K · 9:16 VERTICAL · 15S · 5-SHOT SLOW-MOTION MONTAGE FORMAT: 15s / 9:16 vertical / cinematic romantic montage / dynamic cuts, rack-focus transitions, all in slow motion STYLE: Hollywood live-action cinema, ARRI Alexa LF, anamorphic lens, 35mm film grain, halation on highlights, professional color grading, golden-hour Mediterranean light, extremely shallow depth of field, dreamy defocus-to-focus pulls, realistic motion blur, photorealistic textures, real-world physics, no CGI feel. REFERENCES: Reference 1 = the bride. Preserve her exact face, skin tone, dark hair, black wayfarer sunglasses, veil, white plunging V-neck wedding dress, necklace and solitaire ring. No identity change. Reference 2 = the groom. Preserve his exact face, curly dark hair, black wayfarer sunglasses, black tuxedo, bow tie, white shirt and wedding band. No identity change. Reference 3 = previous video. This scene continues directly from its final frame: same ancient Greek colonnade, same golden light, same spinning embrace, same swirling white petals. Match environment, wardrobe and atmosphere exactly. VIDEO PROMPT: The scene opens mid-spin, exactly where Reference 3 ends — the groom holding the bride by the waist, her feet off the marble, both turning in slow motion among drifting white petals. Shot 1 (0-3s): Extreme close-up of the bride's face as she spins — frame starts defocused, then racks into crisp focus on her smile and sunglasses, petals blurring past in the foreground, veil floating. Shot 2 (3-5s): Macro close-ups of white petals tumbling through golden air, soft bokeh, one petal drifts across the lens and pulls the focus with it. Shot 3 (5-8s): Extreme close-up of the groom's face — defocus blooms into sharp focus on his smile and sunglasses, warm rim light on his curls, petals spiraling behind him. Shot 4 (8-11s): Perfect top-down bird's-eye view — the couple spinning at the center of the marble floor, her white dress fanning into a full circle, columns radiating around the frame edges, petals orbiting them like a slow galaxy. Shot 5 (11-15s): Final extreme wide from the side — a mountain-top colonnade against a vast golden sky, the couple tiny between the distant columns, still turning, mist drifting below, sun flaring softly through the pillars. Total: 15s / 5 shots / 9:16 SFX: no music; soft slowed wind, petals whispering past the lens, muffled dress swoosh, faint heartbeat, distant mountain breeze in the final wide, gentle fabric flutter. NEGATIVE PROMPT: no identity change, no face distortion, no sunglasses removal, no outfit change, no environment change, no text, no cartoon look, no cheap CGI, no plastic skin, no floating objects, no unrealistic physics, no warping, no morphing, no flat lighting, no harsh cuts mid-motion.

One continuous handheld take with a five-beat script, a dedicated SETTING block, a PHYSICS clause and a bystander-camera plan. Paste it as written.

SEEDANCE 2.0 · 15S · 16:9 · ONE CONTINUOUS SHOT · WITH AUDIO FORMAT: 15s / 16:9 / surreal slapstick comedy / one continuous shot, no cuts STYLE: Ultra-realistic natural iPhone footage texture, handheld authenticity, vivid saturated summer colors, crisp daylight, real-world physics with one cartoon-logic gag executed photorealistically, subtle motion blur, no CGI feel. REFERENCES: Reference 1 = the man, main character: preserve his exact face, curly brown hair, mustache and goatee, body proportions, black wayfarer sunglasses at the start. He wears loose knee-length board shorts under a grey t-shirt. Identity locked. Reference 2 = the same man's face without sunglasses: after removing sunglasses his face must match Reference 2 exactly. Same person throughout. VIDEO PROMPT: One continuous shot, no cuts. Summer midday on an old Italian stone bridge. The man from Reference 1 stands near the bridge ledge. Around him, a lively mixed crowd of attractive young women and men in colorful beach outfits cheer him on in English — "Jump! Jump! Do it! You got this!" — clapping and filming with phones. Off to the side, two elderly Italian ladies back from the market with woven vegetable bags watch with skeptical amusement, one shaking her head. He smirks with total confidence, climbs onto the stone ledge with cool swagger, pulls off his grey t-shirt and tosses it, calmly removes his sunglasses and sets them on the ledge — his bare face matching Reference 2. He flexes once, salutes the crowd, and leaps off in a perfect stylish cliff-diving arc. The camera swings over the ledge following him down — REVEAL: there is NO water. Below is a vast dry cracked-earth basin, dusty and sun-baked. He plummets and his head plants straight into the soft dry soil with a comedic THUNK and a big dust puff — his body stays stuck perfectly vertical and upside down, head buried in the ground, torso and legs pointing straight up at the sky, loose board shorts visible, legs kicking and wiggling helplessly in the air. Above, the crowd leans over the ledge gasping then bursting into laughter; the elderly ladies peer down unimpressed, one muttering with a dismissive hand wave before they shuffle off. His muffled voice grumbles from the dirt as his legs keep pedaling. CAMERA: Natural handheld iPhone at eye level on the bridge, tracks his swagger walk, tips over the ledge following the dive, drops WITH him in one unbroken move, lands to a low wide angle on the planted body, legs kicking against the sky. No cuts, no zoom snaps. SFX: Mixed male and female cheering in English, whistles, seagulls, paper bags rustling, fabric toss, sunglasses click on stone, wind rush during fall, deep comedic dirt THUNK, dust hiss, muffled grumbling, elderly lady muttering in Italian, laughter echoing. No music. NEGATIVE PROMPT: no identity change, no face distortion, no cartoon look, no cheap CGI, no water anywhere, no morphing, no plastic skin, no flat lighting, no limb distortion, no flagpole, no flag, no speedo, no tight briefs.

SEEDANCE 2.0 · 15S · ONE CONTINUOUS SHOT · WITH AUDIO Style: photoreal live-action, filmed on a spectator's handheld smartphone from a lively daytime crowd at a grand ruined-temple open-air theatre (matching @Image1) — towering ancient columns, blue sky, raised phones and animated spectators in the foreground; bright daytime; a FAST, DYNAMIC, two-sided fantasy duel where BOTH fighters are highly active, with spectacular colliding VFX; stylized magic, no blood, no gore. Energetic handheld that whip-follows the exchange and cranes up for the clash, but ONE single unbroken take with no cuts. @Image2 = the steampunk hero (stage-left) — Deniz's likeness, brass-and-leather steampunk armor, glasses, brass DRAGON-HEADED steam-lance venting steam and ember-orange dragon-fire; agile, dashes, vaults, spins. @Image3 = the magnificent warlord (stage-right) — ornate dark-steel-and-gold armor, crowned-horned helm, long cape; wields dark ember-gold energy, a spectral greatsword and a dark energy beast. ONE continuous handheld shot, no cuts, kinetic shake — one unbroken take: 0-3s: both strike at once — the hero lashes a whip of ember-orange dragon-fire, the warlord hurls a wave of dark ember-gold energy; the two blasts COLLIDE mid-stage in a shoving burst of sparks, driving both back a step. 3-6s: the warlord conjures a dark spectral greatsword and swings a shockwave; the hero steam-bursts into a dash, vaults, and spins his lance to parry it in a shower of embers and sparks; in the crowd a spectator hurls a bottle that bounces across the stage as people shout. 6-9s: the warlord raises both hands and summons a dark energy WRAITH-BEAST; the hero thrusts his lance skyward and a COLOSSAL ember-orange fire-DRAGON erupts from its jaws — the two giant constructs CLASH mid-air in a massive collision of fire against dark energy, shaking the arena. 9-12s: the constructs grapple, pushing back and forth; the warlord slams a dark shockwave, the hero answers with a surging steam-and-dragon-fire blast — the fire-dragon overpowers and shatters the wraith in a burst of dark shards. 12-15s: the fire-dragon dives and engulfs the warlord in a vast firestorm; his armor blazes and he is driven down, dispersing into embers and dark smoke; the hero lands in a stylish crouch, plants his steam-venting lance and rises into a cool victory pose as the crowd erupts, roaring and tossing things in celebration. Audio: a LIVELY, LOUD crowd throughout — gasps, oohs and aahs, cheers and scattered shouts ('WHOA!', 'GET HIM!', 'YESSS!'), whistles; clashing energy booms, dragon-fire crackle and a deep dragon ROAR, dark-energy hums and a wraith shriek, steam hisses, lance parries and spark clangs, a thrown-bottle clatter, a huge collision boom, a final firestorm rumble; the crowd erupts loudest on the final frame. Preserve: ONE continuous handheld shot, no cuts; the hero (@Image2) with dragon-headed steam-lance, the warlord (@Image3) in ornate armor and cape; BOTH fighters active with multiple distinct skills; colliding fire-vs-dark-energy VFX; photoreal live-action; grand ruined-temple theatre and lively crowd from @Image1; foreground spectators with raised phones; stylized fantasy, no blood or gore; no on-screen text.

Four timed scenes, a dialogue exchange, a camera plan and a sound pass — written like a real commercial board. Paste it as written.

FORMAT: 30s / 9:16 vertical / luxury fashion-automotive montage / fast rhythmic hard cuts synced to sound design, one shot per beat, high-energy pacing STYLE: Mediterranean cinematic editorial realism, ARRI Alexa 35 aesthetic, 35mm film grain, warm golden sun, deep-blue sea against sun-bleached stone, strong coastal wind moving fabric and hair in every exterior shot, shallow depth of field on details, high-end commercial grade, one visual identity, no style mixing. REFERENCES: @Image 1 defines the hero's identity ONLY: preserve this exact person's face, features, skin tone, hair texture and length, and body proportions in every shot, whoever they are. If @Image 1 shows eyewear, preserve that exact eyewear; otherwise the hero wears black square-framed wayfarer sunglasses. Sunglasses stay on in every shot. Do NOT inherit any clothing, objects or background from @Image 1. Wardrobe is redesigned as premium unisex summer streetwear: oversized ecru boxy tee, unbuttoned camel linen overshirt, relaxed wide-leg off-white pleated trousers, chunky off-white and grey sneakers, thin silver chain, minimal steel watch. This exact outfit is identical in every shot. @Image 2 defines the environment and the car: a sun-drenched Mediterranean clifftop terrace of pale gravel with a low stone parapet, a sand-colored tower with a terracotta-red dome, one tall palm, deep-blue sea below, and a classic air-cooled orange sports coupe with a whale-tail rear spoiler, black five-spoke wheels and chrome trim. The same coastline continues as a winding two-lane coastal road along the cliffs, rising toward hazy inland mountain ridges. Match this light, palette and architecture exactly. Exactly ONE car in the video. VIDEO PROMPT: [Shot 1 — 0–1.5s, hook] Extreme macro low angle: a chunky off-white sneaker strikes the gravel hard mid-stride, dust kicked sharply backward, blurred sea in the bokeh. End state: foot pushing off. [Shot 2 — 1.5–3s] Hard cut. Low-angle tilt up to the hero's face: fast, confident, powerful strides straight at camera, the linen overshirt whipping behind in the strong wind, hair lifted, sunglasses catching a sharp sun flare. End state: face centered, mid-stride. [Shot 3 — 3–4.5s] Hard cut. Medium close-up, fast parallel tracking left to right matching the pace: fabric snapping in the gusts, the hero's hand slides into the pocket without breaking stride. End state: still moving fast right. [Shot 4 — 4.5–6s] Hard cut. Static wide: tower, palm and parked coupe; the hero strides quickly through frame left to right, overshirt streaming. End state: one step from the driver's door. [Shot 5 — 6–7.5s] Hard cut. Tight macro on the sunglass lenses while walking: the orange coupe mirrored in the reflection, growing larger. End state: reflection filling the lens. [Shot 6 — 7.5–9s] Hard cut. Close-up: the hand grabs the chrome handle in motion, click, door swings open in one fluid pull. End state: door open. [Shot 7 — 9–11s] Hard cut. Interior from the passenger side: the hero drops into the black leather seat in one athletic motion, pulls the door shut with a deep vintage thunk, hands landing on the thin classic wheel. Sunglasses on. End state: seated, ready. [Shot 8 — 11–13s] Hard cut. Low rear three-quarter by the twin exhaust tips: the flat-six barks awake, two sharp revs, heat shimmer behind the whale tail. End state: revving. [Shot 9 — 13–15s] Hard cut. Wide from the terrace: the coupe launches off the gravel, rear tires flicking stones, and swings onto the coastal road left to right. End state: on asphalt, accelerating. [Shot 10 — 15–18s] Hard cut. Fast parallel tracking at wheel height: the coupe sweeps along the cliffside road, low stone wall and deep-blue sea rushing past on one side, guard stones strobing by. End state: car leaning into a long curve. [Shot 11 — 18–21s] Hard cut. Behind-the-shoulder interior: window open, wind roaring through, overshirt collar fluttering, hands steady on the wheel, the road curving upward toward hazy mountain ridges. End state: mountains centered in the windshield. [Shot 12 — 21–24s] Hard cut. Static roadside wide on a hairpin: the coupe sweeps through the bend, sea far below, mountain slopes rising above, thin dust trailing. End state: car exiting the bend, climbing. [Shot 13 — 24–27s] Hard cut. Frontal tracking through the windshield: golden light strobing across the sunglasses, a faint knowing smile, one hand relaxed on the wheel. End state: road reflections sliding over the lenses. [Final shot — 27–30s] Hard cut. Static roadside wide: the orange coupe pulls away along the winding coastal road toward the hazy mountains, growing smaller, wind moving the roadside grass. Hold the final frame 0.8s as the exhaust fades. AUDIO: (Driving organic deep-house pulse with a warm piano motif enters at 1.5s, fast tempo, one hard accent on every cut, energy lifting when the engine starts, fading on the final wide.) <ASMR-grade close-mic foreground: rapid crisp gravel strikes, dust hiss, linen snapping in gusts, sharp chrome handle click, one deep door thunk, raspy flat-six bark and two revs, tires biting gravel then smooth asphalt, rising gear pulls, wind buffeting through the open window, exhaust echo off the cliffs.> <Background ambience: sea wash far below, strong coastal wind, distant gulls.> No dialogue, no voiceover, no subtitles. CONSISTENCY: One single hero throughout, exactly the same person as @Image 1: identical face, hair, skin tone and proportions in every shot; sunglasses never removed. Identical outfit in every shot. Exactly one orange classic coupe. Same coastline and light direction; screen direction left to right in all walking and driving shots. NEGATIVE PROMPT: no removed sunglasses, no altered identity, no outfit changes, no second car, no other people, no other vehicles or traffic, no plate text, no on-screen text or logos, no drone shots, no slow motion, no style mixing, no CGI look, no warped hands, no distorted car, no music before 1.5s, no dialogue.

FORMAT: 30s / 9:16 vertical / viral CGI illusion filmed as real bystander footage / one continuous handheld take, no cuts STYLE: Ultra realistic smartphone footage, bright Mediterranean midday sun, handheld sway and micro shake, rolling shutter feel, real world physics, no cinematic grading. REFERENCES: @Image 1 defines the environment and the giant phone: sunlit stone-coast cove, wooden pier deck, steel railings, turquoise water, striped umbrellas, pastel buildings, swimmers, and the exact Instagram profile page on the giant phone screen: dark UI, circular profile photo, account name, stats, bio lines, link row, story highlights, buttons and reels grid exactly as designed. In the video the phone starts pocket-size; do not inherit its giant scale until Stage 3. @Image 2 defines the water-dragon post shown on the phone screen during the scroll, and the dragon's exact design: long serpentine body, blue-green scales, thin whiskers, spiked mane crest, amber eyes, wet texture, rising from stormy water. @Image 3 defines the hero's identity and face ONLY: dark brown curly hair, trimmed mustache and short beard, black square-framed sunglasses that remain ON at all times, even underwater. Do not inherit its background. VIDEO PROMPT: [Stage 1 - approx 0-4s] Initial state: handheld frame on the empty pier deck from @Image 1, swimmers behind, umbrellas above. Event: a young woman in a bikini sprints along the pier and cannonballs into the sea, a white splash rises. Camera: handheld, slight pan following her jump. End state: the splash settles, the deck is empty. [Stage 2 - approx 4-8s] Continue from the empty deck. Event: the man from @Image 3, in a grey tank top, patterned swim shorts and colorful clogs, walks in from the right edge holding a normal pocket-size iPhone. He crouches and stands it upright on the planks, screen facing the camera, then steps back. Camera: handheld pan right, then settle. End state: the small phone stands upright, the man beside it on the right. [Stage 3 - approx 8-12s] Continue from the standing phone. Event: the phone grows smoothly to a monolith over twice the man's height, planks creaking; the screen lights up showing the full Instagram profile page from @Image 1, crisp and readable. Camera: handheld tilt up as it grows. End state: the giant phone stands fixed on the deck displaying the profile page, the man at its right side. [Stage 4 - approx 12-15s] Continue from the giant phone. Event: the man reaches up and swipes the huge screen; the page scrolls fast with real UI motion blur, decelerates and stops exactly on the water-dragon post from @Image 2, the dragon photo filling the screen. Camera: handheld hold. End state: the dragon post displayed full and still, his hand lowers. [Stage 5 - approx 15-20s] Continue from the still dragon photo. Event: inside the screen the dragon blinks, then physically slithers OUT of the display, crossing the screen plane into the real pier space, head, whiskers and claws passing IN FRONT of the phone bezel, closer to the lens than the screen, seawater dripping from its scales onto the planks, casting a moving shadow. Behind it, the photo keeps a dragon-shaped empty gap where it stood; the rest of the post stays unchanged. Camera: startled handheld jolt, step backward, autofocus briefly hunts. End state: the full dragon coils on the deck, the empty-gap photo glowing behind it. [Stage 6 - approx 20-25s] Continue from the dragon on the deck. Event: the man grabs the spiked mane crest, swings onto the dragon's back and holds on; the dragon leaps over the railing, diving into the sea with a massive splash. Camera: handheld rush to the pier edge and PLUNGE into the water after them, foam sweeping over the lens, the image turning into clear sunlit underwater blue with light rays from the surface. End state: the camera is fully underwater, the dragon and rider ahead swimming into the blue. [Stage 7 - approx 25-30s] Continue underwater. Event: in the distance the dragon banks into a wide turning maneuver and comes back straight at the camera, accelerating hard with serpentine strokes, the man pressed low gripping the mane crest, sunglasses on, a thin bubble trail from his nose; it streaks past EXTREMELY close along the camera's right side with heavy motion blur, the pressure wake violently shaking the camera as a dense corridor of bubbles erupts behind it and washes over the lens, and they exit the frame completely. Final state: held frame on empty blue water, the bubble corridor collapsing and fading, hard stop, the video ends underwater. AUDIO: <Seaside ambience, swimmers' chatter, gulls, lapping water.> <Sharp real splash at the cannonball.> <Deep low rumble and wood creak while the phone grows.> <Soft UI swipe whoosh during the scroll.> <Wet slithering and a low reptilian breath as the dragon emerges.> <Huge splash at the dive, then instantly muffled underwater ambience, deep pressure hum.> <A sharp accelerating whoosh and a violent bubble rush at the close pass, then settling water.> No music. No voiceover. CONSISTENCY: Keep the man's face, curly hair, beard and black square sunglasses unchanged, even underwater. Exactly one man, one dragon, one phone. The phone stays fixed to its deck spot from Stage 3 onward. Screen UI matches @Image 1, then @Image 2. The dragon outside matches the @Image 2 dragon exactly: serpentine body, whiskers, spiked mane crest, blue-green scales. The stormy sky exists only inside the on-screen photo; the real world stays sunny. The dragon never touches the camera or any swimmer. NEGATIVE PROMPT: no cuts, no zoom, no gimbal smoothness, no face distortion, no identity change, no wardrobe change, no removed sunglasses, no duplicate phone, no duplicate dragon, no dragon rendered as a sticker on the screen, no western winged dragon, no wings, no teleport, no glitch jump, no cartoon, no cheap CGI, no plastic skin, no murky dark water, no text outside the Instagram UI, no watermarks, no injuries, no panic.

FORMAT: 30s / 9:16 vertical / handcrafted stop-motion romance short / staged continuous scenes with one clean cut STYLE: Authentic fabric stop-motion on a miniature kraft-paper set, 12 frames per second stepped motion with subtle frame-to-frame jitter, visible fibers, stitching and fabric weave, warm tungsten key light, soft shadows, tilt-shift miniature depth of field. REFERENCES: @Image 1 defines Ivy, a girl character formed entirely of clothes with no visible body: green fleece zip jacket, cream ribbed top, cream pleated skirt, cream socks with green stripes, cream-green-orange sneakers, green cap; her props: cream tote bag, tennis ball, green scrunchie. Preserve garments and colors exactly; ignore layout and text. @Image 2 defines Ace, a boy character formed entirely of clothes with no visible body: navy varsity jacket with cream leather sleeves and red trim, cream tee, relaxed blue denim, white socks with red stripes, cream-navy-red sneakers, red corduroy cap; his props: vintage camera on a woven strap, folded newspaper. Preserve garments and colors exactly; ignore layout and text. @Image 3 defines ONLY the closing composition: a dense vertical block of folded garments on kraft paper, the four-letter logo carved as negative space across its middle band, exactly as shown. Use it solely for the final frame; do not show this arrangement earlier. VIDEO PROMPT: [Stage 1 - approx 0-6s] Initial state: Ivy's miniature kraft-paper bedroom, morning light. Her outfit stands upright in human shape, hollow at collar and cuffs. Event: her sleeves lift the green cap above the empty collar, the scrunchie snaps around one cuff, and she hops as the tote lands on her shoulder with the tennis ball inside. At 3s, one clean cut to Ace's bedroom: his varsity jacket shrugs itself square, the camera strap swings across his chest, the newspaper tucks under his arm. Camera: locked-off medium shots. End state: both fully dressed, Ivy holding the tote, Ace holding the newspaper. [Stage 2 - approx 6-12s] Continue. Two miniature front doors creak open onto one street: Ivy walks left-to-right on the near sidewalk, Ace walks right-to-left on the far sidewalk, in stepped strides. Behind them, paper-cutout street objects glide past on parallax layers: lampposts, a cardboard bus, a fire hydrant, potted plants. At 9s Ivy kneels and strokes a small cat built from folded cream knit socks with a green scrunchie tail; the cat arches. Ace pats a puppy stitched from grey denim scraps; its sock tail wags frame by frame. Camera: parallel tracking with each character. End state: pets scamper off, both resume walking toward the same intersection. [Stage 3 - approx 12-17s] Continue. Both reach one miniature cardboard traffic light glowing with a red felt disc and wait on opposite corners, idly bobbing frame to frame, her skirt pleats swaying. At 15s the light flips to a green felt disc. Event: they step into the crossing distracted, Ivy digging inside the tote, Ace reading the newspaper, and gently bump into each other mid-crosswalk with a soft comedic fabric thump; nobody is hurt. Her tote tips and the tennis ball rolls out; his newspaper flutters to the ground. Camera: static wide on the crossing. End state: both frozen one beat, props lying on the crosswalk between them. [Stage 4 - approx 17-23s] Continue. Both kneel at the same moment reaching for the fallen items; his cream leather sleeve and her fleece cuff touch on the tennis ball. They tilt their caps up toward each other and hold still for two beats. A small red felt heart pops up above them with a springy bounce and hovers. He returns her tote; she returns his newspaper. Camera: slow dolly in to a two-shot. End state: both standing, facing each other, sleeve linked in sleeve. [Stage 5 - approx 23-30s] Continue. Sleeve in sleeve, they walk away from camera up the kraft-paper street. Event: from every edge of frame, hoodies, tees, joggers, jeans, beanies, socks and sneakers slide in and fold themselves flat onto the ground in stepped motion, assembling into the exact garment arrangement of @Image 3 with its negative space forming the four-letter logo, the tiny couple standing at its center. Camera: slow crane up into a top-down view filling the vertical frame. Final state: completed @Image 3 logo layout held as a still frame for the last beat. AUDIO: (Playful pizzicato and glockenspiel score, swelling when the heart appears and resolving on the final held frame.) <Handmade stop-motion foley synced to the stepped motion: soft felt footsteps, fabric rustle, a zipper zip, door creaks, paper flutter, the tennis ball rolling on paper, a gentle fabric thump at the bump, a springy boing as the heart pops, a whoosh of sliding garments in the finale.> Reactive puppet-like vocalizations timed to events. Light female voice, playful: {Oh!} as the tote lands in Stage 1. Warm male voice, a soft amused hum at the puppy. Both voices together, surprised: {Oh!} at the bump. Female voice, a small gasp then a shy giggle at the sleeve touch. Male voice, gentle and low: {Oh.} as the heart appears. No other dialogue, no narration. CONSISTENCY: Both characters remain clothes-only with no visible skin, face, hair or body in every stage. Keep garments, colors, caps and prop ownership unchanged; tote and tennis ball belong to Ivy, camera and newspaper to Ace, exchanged only during the pickup. Exactly two characters, one cat, one dog, one traffic light. Same kraft-paper set, lighting and stepped 12fps cadence in all stages. Screen direction preserved: they approach from opposite sides and exit away from camera together. NEGATIVE PROMPT: no visible humans, no skin, no faces, no hair, no mannequins, no smooth 24fps motion, no motion blur, no glossy CGI look, no 2D cartoon rendering, no style mixing, no extra characters, no duplicate props, no loose garments in the street before the final stage, no invented lettering, no captions, no subtitles, no watermarks, no split screen, no panel grid.

Eleven timed shots in five movements: the red-light staredown, the launch, the wheel-to-wheel sprint, the gear-slam duel, and the ribbon finish over the painted logo. Paste it as written.

SEEDANCE 2.0 · 15S · 3-ACT MINI FILM · DYNAMIC CUTS FORMAT: 15s / 9:16 vertical / comedic stop-motion claymation epic / dynamic cuts, 3-act mini film STYLE: Handmade claymation stop-motion, visible fingerprints and tool marks in the clay, subtle frame-to-frame jitter at a 12fps stop-motion cadence, miniature set with shallow depth of field, warm tungsten kitchen light, sculpted cotton-wool flame clouds backlit orange behind the set, rich practical texture, charming imperfect animation, cinematic epic-trailer framing played completely straight for comedy. REFERENCES: Reference 1 = the full scene: the tiny clay warrior with bronze helmet, blue mohawk crest, knitted oven-mitt fists, quilted potholder armor and two spatulas, plus the food-monster army - the giant red oven-faced boss with glowing mouth, the pizza monsters, sausage and green veggie monsters. Preserve every character design, color and material exactly. VIDEO PROMPT: 0-3s (SETUP): Slow heroic push-in on the tiny warrior standing alone before the towering food-monster army, the oven boss glowing behind them. He raises both spatulas and screams a squeaky battle cry: DINNERTIME! The monsters roar back, clay jaws wobbling. 3-8s (BATTLE): He charges. He vaults off a rolling meatball, and in speed-ramped slow motion flips the big pepperoni pizza monster high into the air with one spatula - it spins, flattens, and lands as an ordinary harmless pizza, its angry face gone. He parries a lunging sausage monster, then bops the green veggie monster on the head; it wobbles and topples backward into a bowl of dip with a thick splat. 8-12s (CLIMAX): The oven boss opens its glowing door-mouth wide and inhales, pulling crumbs and small monsters sliding toward it. The warrior sprints along the counter, leaps, and slams the door shut with both spatulas. A beat of silence - then the oven timer on its forehead rings a bright DING. 12-15s (PAYOFF): At the ding, every remaining monster instantly freezes and shrinks down into cute, steaming, ordinary dishes. The warrior calmly plants one spatula upright in a mound of mashed potatoes, tears a tiny slice from the defeated pizza, takes a bite, and gives a slow approving nod straight to camera. Hard stop, no fade. PHYSICS: Clay has soft weight - bodies squash and stretch on impact, the flipped pizza follows a real gravity arc, the dip splashes in thick clay droplets, crumbs scatter and settle, stop-motion motion blur absent, movement slightly stepped. SOUND: Overblown epic trailer drums and choir that cut out comically at the ding, squeaky tiny battle cry DINNERTIME, clay squishes and boings, a whoosh and slap on the pizza flip, thick splat, oven inhale rumble, bright oven DING, gentle sizzle, one small crunch on the final bite, no on-screen text. NEGATIVE PROMPT: no realistic humans, no smooth CGI interpolation, no glossy 3D render look, no identity change, no design change on any character, no melting faces, no on-screen text, no captions, no watermarks.

FORMAT: 30s / 9:16 / photoreal POV flight / single continuous shot, no cuts STYLE: Hyper-realistic live-action, sharp detail, overcast daylight, real physics, real time speed only. REFERENCES: @Image 1 defines everything: rider's chest POV, gloved hands on cables, harness clamps, the dragon's grey-green scales and head, the cliff. Preserve exactly. VIDEO PROMPT: [Stage 1 - 0-4s] Exact composition of @Image 1, dragon at the cliff edge, wind in the grass. The rider speaks; the dragon looks back, one beat of eye contact, exhales, faces forward. [Stage 2 - 4-9s] The dragon takes 3 fast running strides, each jolting the camera, then leaps off with wings folded tight, dropping into a steep head down free fall along the rock face, wind roaring, grit streaking past. Camera: shake on strides only, then wind trembling. End state: rocks and sea rushing up. [Stage 3 - 9-14s] The dragon plunges between sharp rocks at the cliff base; an instant before hitting the water the wings snap open with a heavy thump, wingtips slamming through wave tops, ripping spray curtains up, droplets on the lens, the wave strike converting the fall into fast low flight. Camera: hard g-force compression. End state: skimming the swell, wet lens. [Stage 4 - 14-19s] Jagged sea stacks rise ahead. The dragon weaves between them at speed, banking left around one, hard right around the next, wingtip nearly brushing wet stone, gusts shoving it so it drifts and corrects, the rider's arms pulled side to side. Camera: rolling lean into banks. End state: past the last stack, open water. [Stage 5 - 19-27s] From screen right a colossal whale, dark barnacled skin, launches from the sea in a long horizontal arc, right to left over their path, water cascading off its flanks. The dragon holds low, shooting through the gap under the arcing whale while airborne, wet belly passing huge overhead, shadow sweeping the water. It crashes down left behind them, spray drenching the lens. End state: clear. [Stage 6 - 27-30s] Calm glide with small wind corrections. The rider exhales, speaks the final line. Held frame: hands relaxed, horizon level. AUDIO: <wind, 3 footfalls before the leap only, then none, roaring dive air, heavy wing snap, wave slaps, spray hiss, gulls, breach eruption, deep whale call, thunderous splashdown> English, American accent, cinematic warm male voice, the rider: at 1s {Ready, my friend? Remember, this is my first time.} in the fall {Whoa whoa whoa!} at the wave strike {Okay okay, easy!} at 27s {Alright, no more tricks. Straight and safe now.} No music. CONSISTENCY: Locked first person POV, camera never leaves the rider's chest, hands and cables always in frame. Exactly 1 dragon, 1 whale. NEGATIVE PROMPT: no slow motion, no speed ramps, no cuts, no zoom, no third person angle, no glow effects, no cartoon, no cheap CGI, no plastic scales, no warping, no weightless motion, no rigid flight path, no footsteps after the leap, no on-screen text, no captions, no watermarks, no music.