Create a 25–30 second ultra-realistic cinematic sequence inside a photorealistic 1950s American diner. Chrome stools, deep red booths, checkerboard floor, warm window light and buzzing neon. Premium film grain with natural handheld texture. GIRL: Use the uploaded reference image as the exact character reference. Young woman with consistent face, hair, skin tone and body proportions, wearing a cream quarter-zip sweater, black pants and white sneakers. She sits calmly at the counter, completely focused on a thick milkshake. MAN: Young male waiter wearing a classic white diner shirt, dark trousers and apron, carrying a tray with a burger and large glass jug of orange juice. She slowly sips her milkshake as the waiter approaches behind her. A man rising from a nearby booth accidentally bumps into him. The tray, burger and orange juice launch into the air. Orange juice explodes into suspended droplets while the camera smoothly orbits around the frozen moment. Everyone freezes in shock. The girl at the counter remains completely unfazed, still slowly drinking her milkshake. The camera makes a full orbit around the frozen diner. Floating burger, tray and orange juice droplets hang in the air while she takes another deliberate sip. Time suddenly rewinds. The food, waiter and orange juice smoothly return to their original positions. The waiter regains his balance. The girl looks up just before the collision happens and quietly moves her milkshake out of the way. The accident is avoided. Final extreme close-up: she takes one last sip, gives a tiny knowing smile toward the camera and continues drinking. CAMERA: 35mm anamorphic look, handheld realism transitioning into a smooth 360° bullet-time orbit during the freeze, shallow depth of field, realistic motion blur, warm film grain, natural skin texture, photorealistic physics. AUDIO: Diegetic only — straw suction, ice moving inside the glass, tray clatter, glass impact, orange juice splash, diner ambience, brief silence during the freeze, reversed sound during rewind. No music. NEGATIVE: No gore, injuries, distorted faces, extra limbs, floating characters outside the freeze effect, unrealistic liquid physics, product deformation, text, subtitles or watermark.
Vintage / Retro Film
Explore free Vintage / Retro Film video prompts from YouMind's AI prompt library, grouped under styles. Every prompt is curated from real creative workflows and ready to copy, adapt, and reuse.
A 2000s studio-comedy film shot, 16:9, 35mm, moderate film grain, bright American daylight, tracking camera at chest height following a man along a city sidewalk. Smooth dolly/track with him, no handheld phone, no gimbal whip, no drone, no cuts. The camera stays with him the whole 30 seconds, medium-wide, the street readable behind him. IMAGE REFERENCES [image_ref] is the opening frame AND the identity lock: the bald man with the thick dark beard, open grey plaid flannel over a white t-shirt, mid-stride on this exact sunlit sidewalk. Keep his exact face, bald scalp, beard, body. Keep this street: Sherman Brothers shop, cafe table, stone steps and arched doorway, red fire hydrant, American flag, storefronts. Start on this composition, then the camera travels with him down the block. Do not redesign his face. He sings out loud, diegetic, the lyrics "I've got the power" in a loud off-key enthusiastic voice, the whole walk. No extra score under it. Street air, footsteps, then the gags. TIMELINE 0-4s: [Tracking medium-wide, opening on image_1] He is already walking, already singing, mouth wide, chest out, a little strut. The camera slides with him. Daylight, grain. He is having the time of his life. 4-8s: [Tracking, he twists his torso toward the hydrant without stopping] He points two fingers at the red fire hydrant on the sidewalk. The hydrant cap blows and three hard jets of water blast out in different directions, high, violent, real water physics, mist in the sun. He keeps walking and singing, does not look back for long. Camera stays on him, hydrant geysers in the background. 8-13s: [Tracking, still singing] He keeps the strut. Water still arcing behind him. Pedestrians flinch at the spray. He grins, points at the sky on a lyric, never breaks stride. 13-18s: [Tracking as he passes a woman coming the other way] A woman in a knee-length dress walks toward him. As they cross, a sudden gust hits only her: the hem lifts a little, Marilyn sidewalk-vent style but modest, a brief flip then it drops. She grabs the fabric, startled. He keeps walking, still singing, a tiny glance, no contact. Camera never leaves him. 18-23s: [Tracking slows as he reaches a shop window] He stops in front of a big storefront glass, still humming. Leans in. We see him and his reflection clearly: bald head, beard, plaid, white tee. He studies himself, tilts his chin. 23-28s: [Held on him and the reflection] In the glass and on his body at the same time, the clothes change in one continuous morph: the flannel and tee become a sharp white open-collar suit, jacket, tailored trousers, a gold chain. No cut, no flash, the fabric rewrites itself. He checks the new look in the window, pleased, shoulders back. 28-30s: [Medium, still on him] He licks the tip of his index finger, taps it to his hip, and a little puff of white steam hisses off the fabric like a hot iron being quenched. He mouths the last "power," smug. Clip ends on that
Create a premium cinematic lifestyle advertisement using the provided reference image as the exact visual reference. Preserve the woman’s identity, facial features, hairstyle, outfit, blue lace clothing, white headscarf, daisy flower, pink vintage compact camera, proportions, and the beautiful wildflower meadow environment. Do not redesign or alter the subject. SCENE: A young woman is sitting peacefully in a sunlit field of white daisies during golden hour, holding a pink vintage compact camera. The atmosphere is warm, romantic, nostalgic, elegant and authentic, resembling a high-end lifestyle camera commercial. ACTION: Begin with a gentle cinematic push-in toward the woman as she looks naturally into the camera with a warm, confident smile. She slowly lowers the camera slightly from her face, revealing her expression, then looks down at the camera affectionately as if appreciating its design. She gently rotates the camera in her hands to showcase its pink body, compact form and vintage aesthetic. She then raises the camera back toward her eye, takes a photograph, and gives a subtle satisfied smile. Add a brief, elegant product-focused moment where the camera is clearly visible in her hands. Her movements should be natural, graceful and realistic, with delicate finger movement and subtle breathing. CAMERA DIRECTION: Start with a medium-wide shot and slowly dolly/push toward the subject. Transition into a smooth close-up of her face and the camera. Use a gentle cinematic orbit around her hands and camera. Finish with a beautiful close-up product shot of the pink camera in her hands while the background falls into creamy bokeh. LIGHTING: Warm natural golden-hour sunlight, soft backlighting, subtle lens flare, delicate rim light around her hair, realistic skin illumination, soft highlights and gentle shadows. VISUAL STYLE: Luxury lifestyle advertising, nostalgic analog photography aesthetic, dreamy editorial cinematography, premium commercial production, soft film texture, shallow depth of field, creamy bokeh, natural skin texture, realistic fabric detail, photorealistic, sophisticated color grading, subtle 35mm film character. MOTION: Natural human movement, realistic hand and finger articulation, subtle facial expressions, gentle hair movement from a light breeze, softly moving flowers and grass, physically accurate motion, smooth cinematic camera movement. PRODUCT PRIORITY: The pink vintage camera must remain visually consistent throughout the entire video. Preserve its shape, proportions, lens, buttons, colors and overall appearance from the reference image. Make the camera clearly recognizable and desirable without making it look oversized or artificially exaggerated. ENDING: End on a clean cinematic close-up of the camera held elegantly in her hands, with the woman softly out of focus in the background and warm sunlight creating a beautiful glow. Hold the product
Main Subjects: Three Italian university roommates in their early 20s, natural everyday appearances, realistic skin texture, minimal makeup. Woman 1: long dark-brown hair in a loose ponytail, wearing a faded red T-shirt and loose jeans. Woman 2: short curly brown hair, wearing an oversized cream sweater and dark trousers. Man 1: messy dark hair, wearing a grey T-shirt and navy lounge pants. Maintain consistent identities, clothing, hairstyles, and appearance throughout. Location: Modest shared apartment in Bologna on an ordinary weekday evening. Small kitchen, worn wooden cabinets, tiled floor, drying dishes, grocery bags, old refrigerator, open window overlooking neighboring apartments, simple dining table, and everyday household clutter. No luxury styling. Visual Style: Ultra-realistic documentary realism. Genuine roommate interaction, spontaneous laughter, natural body language, believable domestic details. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping near the kitchen window, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 The roommates unpack groceries onto the kitchen counter. One pulls out tomatoes and pasta while another struggles to open a stubborn grocery bag. 00:03–00:06 Woman 1 chops tomatoes while Woman 2 stirs sauce in an old saucepan. The camera moves closer and autofocus briefly locks onto the steam. 00:06–00:09 The man tastes the sauce directly from the wooden spoon and immediately makes an exaggerated face. Everyone laughs. 00:09–00:12 They sit around the small table eating pasta, talking over one another and casually passing bread between them. 00:12–00:15 Someone notices the camera and raises a fork toward the lens while everyone laughs. The operator backs away, bumps lightly into the kitchen doorway, and the recording abruptly cuts to black. Audio: Natural ambience only–pots clattering, chopping, sizzling sauce, running water, chairs scraping, Italian conversation, laughter, refrigerator hum, dishes and forks. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing an ordinary dinner with Italian university roommates–warm, messy, youthful, intimate, and completely believable.
Create a 15-second ultra-photorealistic vertical travel vlog with six fast candid shots, recorded on a small consumer compact camera from around 2010. It must feel like a real friend desperately trying to catch the last ferry, not a commercial.\n\nCHARACTER LOCK: One adult man in his late 20s, lean build, tan skin, short windblown black hair, faded coral overshirt over a white T-shirt, khaki shorts, worn navy sneakers, canvas backpack and one paper bag of takeaway food. Preserve his face, outfit, backpack, food bag and proportions throughout.\n\n0–2s — IMMEDIATE HOOK: The ferry ramp is already lifting as he bursts into frame sprinting down the harbor pier, waving one arm and clutching the food bag. The departing ferry and widening gap must be visible in the first frame.\n\n2–4.5s: Shaky camera runs beside him. His backpack bounces, wind hits the microphone and the food bag almost slips. A deckhand sees him and urgently lowers the ramp a final few centimeters.\n\n4.5–7s: Low angle at the ramp. He makes one believable forward leap across the small remaining gap, lands on both feet and stumbles safely against the rail without dropping anything.\n\n7–9.5s: The ramp closes behind him. He bends over catching his breath, checks the crushed food bag and begins laughing with relief while the camera struggles to refocus.\n\n9.5–12s: He walks onto the windy open deck. The harbor recedes behind him as gulls cross the sky and ropes vibrate against the rail.\n\n12–15s: Natural arm’s-length selfie. Still breathless, he opens the bag and reveals that the takeaway meal survived. He grins, turns the camera toward the island on the horizon and the clip ends abruptly.\n\nVISUAL STYLE: 9:16, early-2010s compact-camera video, imperfect stabilization, occasional optical micro-zoom, mild compression, clipped highlights on water, natural focus delay and cool coastal colors. No drone, gimbal, cinematic crane or polished advertising look.\n\nAUDIO: Harbor wind, footsteps, gulls, ferry engine, ramp hydraulics, bag rustle, breathing and natural laughter. No music, narration or scripted dialogue.\n\nCONSTRAINTS: One traveler, one backpack and one food bag only. Realistic running, jump distance, ferry motion and landing weight. No fall into water, injury, duplicated people, changing clothes, disappearing props, logos, readable signs, subtitles or watermark.
Create a photorealistic 30-second 1990s multi-camera sitcom scene, 9:16 vertical, shot like genuine 35mm television footage. Bright cosy apartment, warm tungsten lighting, soft even fill, subtle film grain, evening blue dusk outside, authentic sitcom staging and natural audience laughter. A young man enters his apartment carrying groceries and freezes when he discovers 12 real cats having a “book club.” Cats are naturally scattered across the red sofa, armchair, rug and coffee-table area with open books nearby. His chubby white cat, wearing a backwards burgundy cap, rectangular glasses and red-black plaid flannel, sits proudly in the middle of the sofa. All cats must remain completely realistic four-legged domestic cats; only the white cat speaks, with a posh British accent. 0:00–0:05 Man stares around in disbelief. MAN: “No. Nope. What is THIS?” CAT: “Book club.” MAN: “Book club?!” CAT: “Every Thursday.” 0:05–0:11 MAN: “There are ELEVEN cats in my living room!” CAT: “Twelve.” MAN: “Where’s twelve—?” Another cat suddenly pokes its head naturally from his grocery bag. MAN: “OH, COME ON!” 0:11–0:17 Man points at the books. MAN: “None of you can even READ!” Dead silence. All cats gradually turn and stare at him naturally. MAN, suddenly unsure: “…Right?” 0:17–0:22 White cat looks over its glasses. CAT: “And yet, somehow… you’re still the dumbest one here.” Huge audience laughter. Man gives the camera an exhausted stare. 0:22–0:27 MAN: “That’s it! Everybody OUT! Book club is OVER!” CAT: “We took a vote.” MAN: “And?!” CAT: “You’re leaving.” 0:27–0:30 Doorbell rings. Man opens the door and finds another real cat sitting outside with a paperback gently held in its mouth. CAT, from sofa: “Oh good. That’s Margaret.” Man closes his eyes in defeat. Freeze frame with huge laughter, applause and a short upbeat 90s sitcom ending sting. Ultra-realistic physical set, natural human acting, genuine cat fur and anatomy, believable physics and imperfect feline movements. No CGI/AI look, anthropomorphic cats, human-like cat gestures, extra limbs, cartoon styling, futuristic elements, dark cinematic grading, subtitles, logos or watermark.
Create a 15-second Vlog-style home video of a 'mild yankee' style Japanese high school boy meeting a kitten in a cardboard box on a rainy day, filmed casually by a friend from under the eaves. 480p. The 15 seconds consist of a hard-cut montage of 7 short shots (approx. 2 seconds each). Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since a close friend is filming, he remains his natural self, unconcerned about being recorded. Main Subject: Same Japanese high school boy throughout all shots. Short hair dyed bright brownish-gold, a small silver earring in one ear. Thin, groomed eyebrows and sharp slanted eyes with hidden double lids, but upon closer look, long eyelashes, a straight nose, and a sweet face with well-shaped thin lips that looks much younger when he smiles. Realistic sun-tanned skin texture, slim jawline. Wearing an oversized black T-shirt, baggy black pants, sandals, and a transparent vinyl umbrella. Completely consistent face, physique, hairstyle, clothing, and umbrella from start to finish. Kitten: A tiny white kitten in a cardboard box partially getting wet in the rain. Location: An alleyway on the edge of a rural shopping street on a rainy evening. Closed storefronts, wet asphalt, eaves, cardboard boxes. No ads or recognizable brands. Camera / Visual Style: Common for all shots: Handheld old consumer digital camera held by a friend under the eaves. Natural shake, imperfect framing, occasional focus hunting, exposure fluctuations due to rain darkness, light motion blur, subtle noise, slightly muted colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (In order, approx. 2 seconds each, all hard cuts): 1. Under the eaves of the rainy shopping street. Talking with his umbrella on his shoulder, he suddenly notices something in the back of the alley. 2. A kitten in a cardboard box getting wet in the corner of the alley. He squats in front of the box. 3. Keeping his sharp gaze, he stares intently at the kitten. The kitten meows softly. 4. With his rugged hand, he timidly and gently pets it. The kitten rubs its head against his palm. 5. After petting for a while, his sharp gaze softens and he smiles slightly. 6. Standing up, he opens his vinyl umbrella and fixes it over the cardboard box as rain protection. 7. Leaving the umbrella behind, a shot of his back as he runs away through the rain. Midway, around 00:14, the recording suddenly cuts to blackout. No fade out. Physical Realism: Maintain realistic physics. Hands, fingers, hair, clothes, rain, umbrella, cardboard, and kitten behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing items, or sudden deformations. The kitten moves naturally on four legs. The umbrella stays where it was placed. Maintain wet clothes and hair, road reflections, and foot grounding. Keep the subject consistent across all shots. Audio: Natural ambient sounds only. Sound of rain, water dripping from eaves, kitten's soft meow, sandal footsteps, distant car sounds. No music. No narration. No artificial sound effects. Final Mood: A record of a scary-looking boy's kindness that was never meant to be seen by anyone, caught by chance. Not a commercial work. Not a scene from a drama. Running away represents his shyness. Rugged, awkward, smelling of rain, warm, and deeply human. Prioritize the feeling that the camera just happened to be there.
Main Subject: Young Spanish woman, 25, natural everyday appearance, shoulder-length dark-brown hair worn loose with slightly messy bangs, realistic skin texture, minimal makeup, relaxed after-work personality. Wearing a faded terracotta T-shirt, lightweight beige cardigan, high-waisted dark-blue jeans, worn white sneakers, and carrying a simple canvas tote bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Ordinary Madrid residential neighborhood on a warm weekday evening. Small local grocery shop, apartment buildings with balconies, parked compact cars, scooters, plane trees, tiled sidewalks, recycling bins, and residents returning home from work. No famous landmarks, tourist streets, or staged activity. Visual Style: Ultra-realistic documentary realism. Genuine everyday behavior, natural body language, spontaneous local interactions, authentic Spanish neighborhood atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting between shelves and her face, exposure pumping when entering and leaving the shop, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks down the residential sidewalk carrying an empty canvas tote. She checks a handwritten grocery list while approaching a small neighborhood shop. 00:03–00:06 Inside, she picks up tomatoes and oranges, comparing them casually before placing them into her basket. Autofocus briefly locks onto the colorful produce. 00:06–00:09 She chooses a loaf of bread and a carton of milk. The shopkeeper greets her from behind the counter, and she responds with a friendly smile. 00:09–00:12 Outside, she rearranges the groceries inside her tote while standing beneath a tree. A scooter passes slowly behind her. 00:12–00:15 She notices the camcorder, laughs softly, lifts the grocery bag as if showing what she bought, and continues toward her apartment. The operator follows for a few steps before accidentally pointing at the pavement and cutting to black. Audio: Natural ambience only–Spanish conversations, shop door bell, grocery bags rustling, footsteps, scooters, distant traffic, birds, apartment sounds, and light neighborhood chatter. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing an ordinary after-work grocery run in Madrid–local, casual, imperfect, warm, nostalgic, and completely believable.
Create a 15-second Vlog-style home video of a Japanese middle school boy who is usually playful but becomes serious only during baseball practice, as if filmed by a teammate. 480p. The 15 seconds consist of a hard-cut montage of 7 short shots (approx. 2 seconds each). Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since a close teammate is filming, he looks relaxed and natural. Main Subject: Same Japanese middle school boy throughout all shots. A refreshing, handsome boy. Thick, sharp eyebrows, large double-lidded eyes, straight nose, large mouth with upturned corners, sharp jawline. Realistic sun-tanned skin texture, showing white teeth when laughing. Short black hair. Wearing a white practice undershirt, muddy baseball uniform pants, baseball cap, and a well-used glove. Completely consistent face, physique, hairstyle, and clothing throughout. Location: Countryside middle school ground on a summer evening. Backstop, benches, white dust, distant mountains, and sunset. No ads or recognizable brands. Camera / Visual Style: Common for all shots: Handheld old consumer digital camera. Natural shake, imperfect framing, occasional focus hunting, exposure fluctuations, light motion blur, subtle noise, slightly muted colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (In order, approx. 2 seconds each, all hard cuts): 1. In front of the bench, posing strangely with a bat like a sword, trying to make the camera laugh. 2. Drinking barley tea in one go with his hat backwards, making an exaggerated face. 3. Going out to the field and fixing his hat to the front. His expression changes instantly. 4. Practice swing. Serious eyes in the evening light. Stopping perfectly in the follow-through pose. 5. Another swing. Sweat from his forehead drops to the soil. Silent. 6. Chasing a grounder, sliding catch in the dust. Not even a grin. 7. End of practice, returning to his usual smile and showing the ball in his glove to the camera jokingly. Midway, around 00:14, the recording suddenly cuts to blackout. No fade out. Physical Realism: Maintain realistic physics. Hands, fingers, feet, hair, sweat, bat, ball, glove, and dust behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing items, or sudden deformations. Bat swings and ball trajectories remain realistic. Keep the subject consistent across all shots. Audio: Natural ambient sounds only. Sound of bat swinging through air, ball hitting glove, footsteps kicking soil, cicadas, distant shouting. No music. No narration. No artificial sound effects. Final Mood: The transition between his playful face and serious eyes is the coolest part; a record of an ordinary day at club activities. Not a commercial work. Not a sports CM. Dedicated, youthful, nostalgic, warm, improvisational, and deeply human. Prioritize the feeling that the camera just happened to be there.
Young American woman in her early 20s, naturally attractive, realistic skin texture, light natural makeup, warm curious traveler personality. Wavy chestnut-brown hair slightly damp from rain, falling loosely past her shoulders. Wearing a fitted olive-green oversized raincoat over a plain white t-shirt, denim shorts, white sneakers now damp at the edges, and a small canvas crossbody bag. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout. LOCATION A busy Mumbai street during a warm monsoon evening. Wet asphalt reflecting neon and streetlights, crowded narrow lanes, old buildings with balconies, hanging wires, colorful shop signs, steam rising from a nearby chai stall, umbrellas bobbing through the crowd, auto-rickshaws splashing through puddles. CAMERA / VISUAL STYLE Raw personal footage casually recorded by a friend on an early-2000s consumer DV camcorder. Strong handheld shake, imperfect framing, autofocus hunting, faded colors, soft digital detail, slight exposure shifts, mild digital noise, occasional motion blur, water droplets on the lens and accidental zooms. No stabilization, drone footage, gimbal movement or polished commercial cinematography. — UNDER AN AWNING She stands under a shop awning, sheltering from the rain, watching the street with a delighted smile, clearly unused to monsoon weather. She holds her hand out past the awning's edge to feel the rain, laughing slightly at how heavy it is. — STEPPING INTO THE RAIN She pulls her raincoat hood up and steps out into the rain, walking along the wet street. The camera follows shakily beside her, rain visible streaking across the lens. — CHAI STALL She notices a small steaming chai stall on the corner. She walks over, watches the vendor pour tea from height between two cups. She hands over some cash, receives a small clay cup of chai, and wraps both hands around it for warmth. — DRINKING CHAI She takes a careful sip, eyes widening slightly at the taste and heat. She looks toward the camera, smiling and nodding in approval. Steam rises from the cup as rain continues falling around her. — WALKING THROUGH THE CROWD She continues down the street, weaving gently past umbrellas, splashing lightly through shallow puddles. Reflections of shop lights ripple across the wet ground beneath her sneakers. — MOMENT OF PLAY She jumps once, playfully, into a puddle, laughing as water splashes up near her shoes. She glances back at the camera with a mischievous grin, hair sticking slightly to her damp forehead. — FINAL MOMENT She stops beneath a flickering streetlight, rain still falling around her, chai cup now empty in her hand. She turns to the camera, wipes a few raindrops from her cheek, and smiles warmly. She says: "This is amazing!" She laughs, turns, and walks off into the crowd as the rain continues and the camera lingers on the street
Create a highly photorealistic rural South Korean village in 1995, authentic and lived-in, with traditional homes, rice fields, misty mountains, vegetable gardens, stone paths, clay jars and period-accurate farming tools. 0–4s | Home: A young Korean woman in her early 20s wakes inside a modest traditional Korean farmhouse. Long dark hair in a simple low braid with a fabric ribbon. She wears an authentic 1995 rural outfit: loose cream cotton blouse, long muted-brown skirt, white ankle socks and simple canvas slip-ons. An analog clock shows 5:45 AM; an old radio plays softly. 4–8s | Window: She opens the wooden window. Misty rice fields and distant mountains glow in early sunrise. Her same friendly medium-sized village dog waits outside. 8–12s | Chickens: She walks outside with her woven basket, the same dog beside her. She scatters grain for chickens while passing traditional village houses, wooden fences and clay jars. 12–16s | Garden: She picks dew-covered fresh vegetables and places them in the basket. The same dog waits nearby. 16–20s | Village Walk: She walks along a quiet dirt-and-stone path with the dog beside her. She gently pats its head. Traditional farmhouse, firewood, clay jars and wooden fences surround them. 20–25s | Rice Fields: She and the dog walk between green-golden rice paddies. Misty mountains, birds and distant farmers create an authentic 1995 Korean countryside atmosphere. Subtle 35mm film grain and natural lens flare. 25–28s I Stream: She kneels beside a small wooden bridge and washes the vegetables in a clear stream. The dog waits beside her and looks curiously at the water. 28–30s | Home: She walks back toward the village with her basket, the same dog happily beside her. Warm sunlight fills the road as she looks toward the mountains and smiles peacefully. AUDIO: rooster calls, chickens, birds, gentle dog sounds, flowing water, wind, village ambience and faint old-radio music. STRICT CONSISTENCY: Same woman, face, braid, outfit, shoes, basket and same dog throughout. Dog must keep identical breed, size, fur and markings. NO: modern cars, smartphones, modern buildings, modern clothing, scooters, contemporary objects or post-1995 technology. CAMERA: ONE continuous cinematic take; no cuts, transitions, montage or time jumps. Natural handheld camera movement.
Use exactly one reference image for the woman. Preserve her identity, face, skin tone, hairstyle, body proportions and wardrobe consistently throughout. Format: 15s, 1080p, 16:9 Style: Ultra-realistic candid home-cooking footage, handheld smartphone or consumer camera style, as if filmed casually by someone in the kitchen. Natural imperfect framing, slight autofocus shifts, soft realistic grain, gentle handheld sway. No CGI, beauty filter, or overly polished commercial look. Warm natural kitchen lighting — soft daylight from a window mixed with warm indoor light, realistic exposure. Character: Young Korean woman, mid-20s, casual home outfit (oversized t-shirt or simple hoodie, apron loosely tied over it), hair tied up in a loose bun or ponytail, natural no-makeup look. Relaxed, focused expression, soft smile, easy unhurried movements. Setting: A cozy home kitchen — wooden countertop, a few pots and ingredients laid out, soft daylight coming through a nearby window, faint ambient sounds of chopping, sizzling, and kitchen background noise. 00:00–00:03 — Starting Prep She stands at the counter, tying her apron strings behind her back, glancing down at ingredients laid out in front of her — vegetables, a cutting board, a bowl. 00:03–00:06 — Chopping She picks up a knife and begins chopping vegetables with calm, practiced movements, occasionally glancing up with a small content smile, natural kitchen sounds in the background. 00:06–00:09 — Stirring the Pan She moves to the stove, stirring something in a pan, steam rising gently. She leans in slightly to smell the aroma, closing her eyes briefly with a satisfied expression. 00:09–00:12 — Tasting She dips a small spoon into the pot, tastes it, and reacts with a pleased nod and soft smile, wiping her hands on her apron. 00:12–00:15 — Plating She scoops the finished dish onto a plate, setting it down on the counter, stepping back slightly to admire her work with a warm, satisfied smile as natural light catches the steam rising from the food. now generatre this images face korian girl to natch this prompt start scene changes dress keep faces
CAMERA/LOOK: DV 16mm tape-camcorder vlog aesthetic, POV alternating between CHASE and PARTNER, sometimes propped on gym equipment. Handheld shake, imperfect framing, delayed focus, clumsy zooms, occasional face cutoffs. Soft blurry tape texture, faint noise, bloomed warm highlights, flickering exposure, muted contrast, realistic skin. Sweat and flushed faces intensify throughout. Camcorder never visible. CHARACTERS: CHASE: Korean idol, 20s, long black high ponytail, expressive eyes, flushed cheeks, slim athletic build. Lightweight modest summer workout top + high-waisted leggings/knee-length shorts, sneakers. PARTNER: Korean woman, 20s, similar age/energy, tied-back hair, athletic build, lightweight modest athletic outfit, sneakers. No jewelry. Both visibly sweaty. SETTING: Hot summer gym with broken AC, warm harsh lighting, fan blowing warm air, open door, racks, mats, mirrors, water bottles. 30s STORYBOARD — 15 CUTS: 1. 0–2s: Propped camera. Both enter fanning themselves. CHASE: “Okay, it is way too hot in here today.” 2. 2–4s: Handheld. PARTNER points at broken AC: “The AC's been out since this morning.” 3. 4–6s: At rack, CHASE loads bar, PARTNER spots. “Let’s just push through it.” 4. 6–8s: Propped shot. CHASE lifts while PARTNER spots. 5. 8–9.5s: Macro hands gripping sweaty bar, sweat dripping. Ambient sound. 6. 9.5–11.5s: PARTNER lifts, CHASE spots: “You've got it, come on!” 7. 11.5–13.5s: Both catch breath, fan shirts, laugh. PARTNER: “Okay, I'm already soaked.” 8. 13.5–15.5s: Walking to mats with water. CHASE: “Water break, mandatory.” 9. 15.5–17.5s: Propped shot. Both drink, sigh, laugh. 10. 17.5–19.5s: Both plank competitively. PARTNER: “Who’s giving up first?” 11. 19.5–21.5s: Straining, sweat dripping. CHASE: “Not—me—” 12. 21.5–23.5s: Macro sweat hitting mat, heavy breathing. 13. 23.5–25.5s: Both collapse laughing. PARTNER: “Okay, that's officially a tie.” 14. 25.5–27.5s: Sitting up, jokingly fanning each other with towels. CHASE: “This heat is actually insane.” 15. 27.5–30s: Arm’s-length selfie. Both sweaty, grinning, tired high-five. CHASE: “Okay, we survived — see you guys!” TONE: Playful, sweaty, energetic gym vlog. Competitive but supportive banter, genuine exhaustion and laughter. Heat and sweat visibly escalate from beginning to end.
In a heartwarming home video style, a joyful toddler discovers music at a vintage piano. An adorable 2-year-old boy with curly dark hair, bright eyes, and a wide smile, wearing a white t-shirt and diaper, sits on a beige bench. He gently presses keys...
Ultra-realistic 30-second, 1080p personal home-video, an ordinary autumn afternoon in the life of a young Korean woman, no reference image. MAIN SUBJECT: early 20s, realistic skin texture, minimal makeup, relaxed genuine personality. Dark-brown hair loosely tied back. Oversized cream knit sweater, blue jeans, white sneakers, small canvas shoulder bag. Same face, hair, and outfit held throughout. SETTING: quiet older Seoul residential neighborhood, cool autumn afternoon. Narrow concrete streets, aging brick houses, fallen leaves, parked bicycles, faded walls, small neighborhood shops. Lived-in and unplanned - no tourist spots, no visible brands. CAMERA: raw handheld footage from an early-2000s MiniDV camcorder, held by a friend. Autofocus hunting, exposure fluctuations, awkward zooms, mild tape noise, natural camera-handling imperfections. No stabilization, no gimbal, no cinematic choreography. BEATS: she leaves home, buys a roasted sweet potato from a street stall, burns her mouth and laughs about it. Keeps walking, notices a bike passing, waves at a dog. A leaf lands on her shoulder - she says Why me? and laughs it off. She sits on a low wall, finishes eating, watches the street in silence for a few seconds -camera just keeps rolling. She stands, walks off, turns back once -Are you coming? - then disappears around the corner as the tape cuts to black. AUDIO: wind, leaves on pavement, footsteps, bicycle bells, distant scooters, doors closing, subtle camera-handling noise. No music, no narration. Only the two lines above. STYLE: nothing dramatic happens on purpose. No posing, no exaggerated acting, no cinematic hero shots -realism comes from awkward laughter, imperfect framing, and dead air nobody bothered to cut. The moment she starts performing for the lens instead of her friend, the whole "found tape" illusion breaks. This one never does.
Main Subject: Young French woman, 23, natural everyday appearance, shoulder-length chestnut-brown hair loosely tied with wispy bangs, realistic skin texture, minimal makeup, relaxed personality. Wearing a faded navy cardigan over a white cotton T-shirt, high-waisted straight-leg blue jeans, worn beige sneakers, and a small brown leather shoulder bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Ordinary residential neighborhood in Lyon on a cool Saturday morning. Small open-air produce market, local bakeries, apartment façades, bicycles, parked cars, reusable shopping bags, elderly residents, narrow sidewalks, and plane trees. No famous landmarks, tourists, or staged scenes. Visual Style: Ultra-realistic documentary realism. Genuine local behavior, natural body language, imperfect everyday interactions, authentic French neighborhood atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping between sunlight and shade, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks through the neighborhood carrying a reusable shopping bag, stopping at a fruit stall. The camera briefly focuses on peaches before finding her face. 00:03–00:06 She chooses several tomatoes and casually chats with the elderly vendor. She laughs at something he says while placing the vegetables into her bag. 00:06–00:09 She walks to a nearby bakery and buys a fresh baguette. The camera struggles to focus through the bakery window. 00:09–00:12 Outside, she breaks off a small piece of bread and tastes it while walking beneath the trees. A cyclist passes behind her. 00:12–00:15 She notices the camcorder, smiles naturally, lifts the baguette playfully, and continues down the residential street. The operator pans toward passing bicycles and accidentally cuts the recording to black. Audio: Natural ambience only–French conversations, footsteps, bicycle bells, paper bags, market vendors, distant cars, birds, light wind, bakery door sounds. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing a completely ordinary Saturday morning in a French neighborhood–local, imperfect, intimate, nostalgic, and genuinely believable.
30s, 1080p, 9:16, nostalgic handheld home-video style, friend filming w/ old digicam. Korean woman (cream cardigan, sage blouse, jeans) buys groceries, bag rips on the walk home, apples spill, she laughs, stranger helps, bites an apple: "now we're safe." Natural audio only, no music/text/logo.\nUse exactly one reference image for the woman. Preserve her identity, face, skin tone, hairstyle, body proportions and wardrobe consistently.\n\nCharacter:\n\nYoung Korean woman, early 20s, cream cardigan, sage-green blouse, blue jeans, white sneakers, brown shoulder bag, silver earrings. Natural makeup, realistic skin and hair.\n\nStyle:\n\nCasual friend-recorded smartphone footage. Handheld, imperfect framing, autofocus shifts, natural exposure, slight motion blur/compression. Real Seoul neighborhood and morning light. No CGI, beauty filter or polished commercial look.\n\nREALISM:\n\nProgressive bag tearing, believable item weight and gravity, accurate hands, payment, walking and object continuity. No teleporting, duplication, disappearing objects, warped hands, extra fingers or wardrobe changes.\n\nAUDIO:\n\nNatural grocery store ambience, refrigeration hum, plastic bag rustling, footsteps, traffic, register beeps, payment sounds, rolling apple sounds, fabric movement and genuine laughter. No music, narration, subtitles, logos or watermark.\n\nVideo:\n\n00:00–00:04 — Grocery Store: She walks through a small neighborhood grocery store, picks up apples and eyes them, says, "These look fresh." Grabs a few items — apples, a carton of eggs, a bag of rice — and puts them in a plastic shopping bag.\n\n00:04–00:08 — Payment: She pays at the counter, thanks the cashier, picks up the full bag with both hands and heads out the door.\n\n00:08–00:12 — Drop: Walking down the street, the bag's handle slowly stretches and rips. An apple rolls out. She doesn't notice; the camera catches it.\n\n00:12–00:16 — Discovery: The sound behind her makes her stop. She turns, sees the apple and the torn handle. "Oh no…" She crouches down.\n\n00:16–00:21 — Chaos: As she lifts the bag, the eggs carton tips and more apples spill out. She catches one apple and chases another rolling toward the curb. She laughs nervously; the camera shakes naturally.\n\n00:21–00:25 — Help: A shopkeeper or passerby comes over with a sturdier bag. They gather everything together, double-checking the eggs are intact. She checks the bag's strength before standing.\n\n00:25–00:30 — Payoff: She walks away, pulls out one apple, takes a bite and smiles: "Okay… now we're safe." She glances at the eggs carton, relieved it survived. The camera operator quietly laughs. Cut naturally while moving.
Create a 15-second Vlog-style home video of a junior high school girl in a brass band club in the countryside after school, filmed by a friend from the same section. The 15 seconds consists of a montage of 7 short shots (approx. 2 seconds each) with hard cuts. Each shot is a different moment, one shot = one small event. Do not use transitions or fades. Since it's being filmed by a close friend, she is relaxed and shows her natural expressions. Main Subject: The same Japanese junior high school girl throughout all shots. A beautiful girl with a sense of transparency. Large double eyelids that tend to droop slightly, eyelashes long enough to cast shadows when looking down, thin natural eyebrows, realistic skin texture that looks white and transparent, no makeup, a small straight nose, and thin cherry-blossom colored lips. A beautiful oval-shaped face. Her straight black hair is tied in a low ponytail. Usually has a modest and calm atmosphere. Wearing a white short-sleeved sailor uniform, a navy collar, a knee-length navy pleated skirt, and indoor shoes. The instrument is a well-used silver trumpet. The face, body type, hairstyle, uniform, and instrument must be completely consistent from beginning to end. Location: A music room in a rural junior high school after school in summer. Music stands, lined-up chairs, open windows, the school grounds and mountains outside. The evening light gradually deepens. No advertisements or recognizable brands. Camera / Visual Style: Common to all shots: An old handheld home digital camera. Natural shaking, imperfect framing, occasional focus hunting, exposure fluctuations, light motion blur, subtle noise, and slightly suppressed colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (in order, approx. 2 seconds each, all hard cuts): 1. She enters the music room holding her instrument case, notices the camera, and waves shyly and small. 2. A close-up of her hands carefully polishing the trumpet with a soft cloth after opening the case. 3. Singing the melody to herself while making small notes in pencil on the sheet music on the stand. 4. Sitting with a friend, talking about something, and laughing while covering her mouth (no words audible). 5. The moment she holds the trumpet, her expression changes. A dignified and serious profile in the music room with the evening sun shining in. 6. A long tone. Eyes staring straight ahead. Voices from club activities in the distance outside the window. 7. After finishing the note, she breathes out and smiles bashfully at the camera. During that, at approximately 00:14, the recording suddenly cuts to black. No fade-out. Physical Realism: Maintain plausible real-world physics. Hands, fingers, hair, uniform, trumpet, and music stands behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing objects, or sudden transformations. Instrument posture and finger positions remain realistic. The subject remains consistent across all shots. Audio: Natural environmental sounds only. Clear long tones of the trumpet, the sound of cloth rubbing, the sound of the pencil, distant voices of club activities, the sound of cicadas. No music (BGM). No narration. No artificial sound effects. Final Atmosphere: The record of an after-school session where you see both the modest girl and the moment she becomes a different person, dignified, when she holds her instrument. Not a commercial work. Not a music video. Quiet, dedicated, nostalgic, warm, improvisational, and deeply human. Prioritize the feeling that the camera happened to be there.
Create a 25–30 second ultra-realistic cinematic sequence inside a photorealistic 1950s American diner. Chrome stools, deep red booths, checkerboard floor, warm window light and buzzing neon. Premium film grain with natural handheld texture. GIRL: Use the uploaded reference image as the exact character reference. Young woman with consistent face, hair, skin tone and body proportions, wearing a cream quarter-zip sweater, black pants and white sneakers. She sits calmly at the counter, completely focused on a thick milkshake. MAN: Young male waiter wearing a classic white diner shirt, dark trousers and apron, carrying a tray with a burger and large glass jug of orange juice. She slowly sips her milkshake as the waiter approaches behind her. A man rising from a nearby booth accidentally bumps into him. The tray, burger and orange juice launch into the air. Orange juice explodes into suspended droplets while the camera smoothly orbits around the frozen moment. Everyone freezes in shock. The girl at the counter remains completely unfazed, still slowly drinking her milkshake. The camera makes a full orbit around the frozen diner. Floating burger, tray and orange juice droplets hang in the air while she takes another deliberate sip. Time suddenly rewinds. The food, waiter and orange juice smoothly return to their original positions. The waiter regains his balance. The girl looks up just before the collision happens and quietly moves her milkshake out of the way. The accident is avoided. Final extreme close-up: she takes one last sip, gives a tiny knowing smile toward the camera and continues drinking. CAMERA: 35mm anamorphic look, handheld realism transitioning into a smooth 360° bullet-time orbit during the freeze, shallow depth of field, realistic motion blur, warm film grain, natural skin texture, photorealistic physics. AUDIO: Diegetic only — straw suction, ice moving inside the glass, tray clatter, glass impact, orange juice splash, diner ambience, brief silence during the freeze, reversed sound during rewind. No music. NEGATIVE: No gore, injuries, distorted faces, extra limbs, floating characters outside the freeze effect, unrealistic liquid physics, product deformation, text, subtitles or watermark.
Create a premium cinematic lifestyle advertisement using the provided reference image as the exact visual reference. Preserve the woman’s identity, facial features, hairstyle, outfit, blue lace clothing, white headscarf, daisy flower, pink vintage compact camera, proportions, and the beautiful wildflower meadow environment. Do not redesign or alter the subject. SCENE: A young woman is sitting peacefully in a sunlit field of white daisies during golden hour, holding a pink vintage compact camera. The atmosphere is warm, romantic, nostalgic, elegant and authentic, resembling a high-end lifestyle camera commercial. ACTION: Begin with a gentle cinematic push-in toward the woman as she looks naturally into the camera with a warm, confident smile. She slowly lowers the camera slightly from her face, revealing her expression, then looks down at the camera affectionately as if appreciating its design. She gently rotates the camera in her hands to showcase its pink body, compact form and vintage aesthetic. She then raises the camera back toward her eye, takes a photograph, and gives a subtle satisfied smile. Add a brief, elegant product-focused moment where the camera is clearly visible in her hands. Her movements should be natural, graceful and realistic, with delicate finger movement and subtle breathing. CAMERA DIRECTION: Start with a medium-wide shot and slowly dolly/push toward the subject. Transition into a smooth close-up of her face and the camera. Use a gentle cinematic orbit around her hands and camera. Finish with a beautiful close-up product shot of the pink camera in her hands while the background falls into creamy bokeh. LIGHTING: Warm natural golden-hour sunlight, soft backlighting, subtle lens flare, delicate rim light around her hair, realistic skin illumination, soft highlights and gentle shadows. VISUAL STYLE: Luxury lifestyle advertising, nostalgic analog photography aesthetic, dreamy editorial cinematography, premium commercial production, soft film texture, shallow depth of field, creamy bokeh, natural skin texture, realistic fabric detail, photorealistic, sophisticated color grading, subtle 35mm film character. MOTION: Natural human movement, realistic hand and finger articulation, subtle facial expressions, gentle hair movement from a light breeze, softly moving flowers and grass, physically accurate motion, smooth cinematic camera movement. PRODUCT PRIORITY: The pink vintage camera must remain visually consistent throughout the entire video. Preserve its shape, proportions, lens, buttons, colors and overall appearance from the reference image. Make the camera clearly recognizable and desirable without making it look oversized or artificially exaggerated. ENDING: End on a clean cinematic close-up of the camera held elegantly in her hands, with the woman softly out of focus in the background and warm sunlight creating a beautiful glow. Hold the product
Create a 15-second ultra-photorealistic vertical travel vlog with six fast candid shots, recorded on a small consumer compact camera from around 2010. It must feel like a real friend desperately trying to catch the last ferry, not a commercial.\n\nCHARACTER LOCK: One adult man in his late 20s, lean build, tan skin, short windblown black hair, faded coral overshirt over a white T-shirt, khaki shorts, worn navy sneakers, canvas backpack and one paper bag of takeaway food. Preserve his face, outfit, backpack, food bag and proportions throughout.\n\n0–2s — IMMEDIATE HOOK: The ferry ramp is already lifting as he bursts into frame sprinting down the harbor pier, waving one arm and clutching the food bag. The departing ferry and widening gap must be visible in the first frame.\n\n2–4.5s: Shaky camera runs beside him. His backpack bounces, wind hits the microphone and the food bag almost slips. A deckhand sees him and urgently lowers the ramp a final few centimeters.\n\n4.5–7s: Low angle at the ramp. He makes one believable forward leap across the small remaining gap, lands on both feet and stumbles safely against the rail without dropping anything.\n\n7–9.5s: The ramp closes behind him. He bends over catching his breath, checks the crushed food bag and begins laughing with relief while the camera struggles to refocus.\n\n9.5–12s: He walks onto the windy open deck. The harbor recedes behind him as gulls cross the sky and ropes vibrate against the rail.\n\n12–15s: Natural arm’s-length selfie. Still breathless, he opens the bag and reveals that the takeaway meal survived. He grins, turns the camera toward the island on the horizon and the clip ends abruptly.\n\nVISUAL STYLE: 9:16, early-2010s compact-camera video, imperfect stabilization, occasional optical micro-zoom, mild compression, clipped highlights on water, natural focus delay and cool coastal colors. No drone, gimbal, cinematic crane or polished advertising look.\n\nAUDIO: Harbor wind, footsteps, gulls, ferry engine, ramp hydraulics, bag rustle, breathing and natural laughter. No music, narration or scripted dialogue.\n\nCONSTRAINTS: One traveler, one backpack and one food bag only. Realistic running, jump distance, ferry motion and landing weight. No fall into water, injury, duplicated people, changing clothes, disappearing props, logos, readable signs, subtitles or watermark.
Create a 15-second Vlog-style home video of a 'mild yankee' style Japanese high school boy meeting a kitten in a cardboard box on a rainy day, filmed casually by a friend from under the eaves. 480p. The 15 seconds consist of a hard-cut montage of 7 short shots (approx. 2 seconds each). Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since a close friend is filming, he remains his natural self, unconcerned about being recorded. Main Subject: Same Japanese high school boy throughout all shots. Short hair dyed bright brownish-gold, a small silver earring in one ear. Thin, groomed eyebrows and sharp slanted eyes with hidden double lids, but upon closer look, long eyelashes, a straight nose, and a sweet face with well-shaped thin lips that looks much younger when he smiles. Realistic sun-tanned skin texture, slim jawline. Wearing an oversized black T-shirt, baggy black pants, sandals, and a transparent vinyl umbrella. Completely consistent face, physique, hairstyle, clothing, and umbrella from start to finish. Kitten: A tiny white kitten in a cardboard box partially getting wet in the rain. Location: An alleyway on the edge of a rural shopping street on a rainy evening. Closed storefronts, wet asphalt, eaves, cardboard boxes. No ads or recognizable brands. Camera / Visual Style: Common for all shots: Handheld old consumer digital camera held by a friend under the eaves. Natural shake, imperfect framing, occasional focus hunting, exposure fluctuations due to rain darkness, light motion blur, subtle noise, slightly muted colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (In order, approx. 2 seconds each, all hard cuts): 1. Under the eaves of the rainy shopping street. Talking with his umbrella on his shoulder, he suddenly notices something in the back of the alley. 2. A kitten in a cardboard box getting wet in the corner of the alley. He squats in front of the box. 3. Keeping his sharp gaze, he stares intently at the kitten. The kitten meows softly. 4. With his rugged hand, he timidly and gently pets it. The kitten rubs its head against his palm. 5. After petting for a while, his sharp gaze softens and he smiles slightly. 6. Standing up, he opens his vinyl umbrella and fixes it over the cardboard box as rain protection. 7. Leaving the umbrella behind, a shot of his back as he runs away through the rain. Midway, around 00:14, the recording suddenly cuts to blackout. No fade out. Physical Realism: Maintain realistic physics. Hands, fingers, hair, clothes, rain, umbrella, cardboard, and kitten behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing items, or sudden deformations. The kitten moves naturally on four legs. The umbrella stays where it was placed. Maintain wet clothes and hair, road reflections, and foot grounding. Keep the subject consistent across all shots. Audio: Natural ambient sounds only. Sound of rain, water dripping from eaves, kitten's soft meow, sandal footsteps, distant car sounds. No music. No narration. No artificial sound effects. Final Mood: A record of a scary-looking boy's kindness that was never meant to be seen by anyone, caught by chance. Not a commercial work. Not a scene from a drama. Running away represents his shyness. Rugged, awkward, smelling of rain, warm, and deeply human. Prioritize the feeling that the camera just happened to be there.
Create a 15-second Vlog-style home video of a Japanese middle school boy who is usually playful but becomes serious only during baseball practice, as if filmed by a teammate. 480p. The 15 seconds consist of a hard-cut montage of 7 short shots (approx. 2 seconds each). Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since a close teammate is filming, he looks relaxed and natural. Main Subject: Same Japanese middle school boy throughout all shots. A refreshing, handsome boy. Thick, sharp eyebrows, large double-lidded eyes, straight nose, large mouth with upturned corners, sharp jawline. Realistic sun-tanned skin texture, showing white teeth when laughing. Short black hair. Wearing a white practice undershirt, muddy baseball uniform pants, baseball cap, and a well-used glove. Completely consistent face, physique, hairstyle, and clothing throughout. Location: Countryside middle school ground on a summer evening. Backstop, benches, white dust, distant mountains, and sunset. No ads or recognizable brands. Camera / Visual Style: Common for all shots: Handheld old consumer digital camera. Natural shake, imperfect framing, occasional focus hunting, exposure fluctuations, light motion blur, subtle noise, slightly muted colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (In order, approx. 2 seconds each, all hard cuts): 1. In front of the bench, posing strangely with a bat like a sword, trying to make the camera laugh. 2. Drinking barley tea in one go with his hat backwards, making an exaggerated face. 3. Going out to the field and fixing his hat to the front. His expression changes instantly. 4. Practice swing. Serious eyes in the evening light. Stopping perfectly in the follow-through pose. 5. Another swing. Sweat from his forehead drops to the soil. Silent. 6. Chasing a grounder, sliding catch in the dust. Not even a grin. 7. End of practice, returning to his usual smile and showing the ball in his glove to the camera jokingly. Midway, around 00:14, the recording suddenly cuts to blackout. No fade out. Physical Realism: Maintain realistic physics. Hands, fingers, feet, hair, sweat, bat, ball, glove, and dust behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing items, or sudden deformations. Bat swings and ball trajectories remain realistic. Keep the subject consistent across all shots. Audio: Natural ambient sounds only. Sound of bat swinging through air, ball hitting glove, footsteps kicking soil, cicadas, distant shouting. No music. No narration. No artificial sound effects. Final Mood: The transition between his playful face and serious eyes is the coolest part; a record of an ordinary day at club activities. Not a commercial work. Not a sports CM. Dedicated, youthful, nostalgic, warm, improvisational, and deeply human. Prioritize the feeling that the camera just happened to be there.
Create a highly photorealistic rural South Korean village in 1995, authentic and lived-in, with traditional homes, rice fields, misty mountains, vegetable gardens, stone paths, clay jars and period-accurate farming tools. 0–4s | Home: A young Korean woman in her early 20s wakes inside a modest traditional Korean farmhouse. Long dark hair in a simple low braid with a fabric ribbon. She wears an authentic 1995 rural outfit: loose cream cotton blouse, long muted-brown skirt, white ankle socks and simple canvas slip-ons. An analog clock shows 5:45 AM; an old radio plays softly. 4–8s | Window: She opens the wooden window. Misty rice fields and distant mountains glow in early sunrise. Her same friendly medium-sized village dog waits outside. 8–12s | Chickens: She walks outside with her woven basket, the same dog beside her. She scatters grain for chickens while passing traditional village houses, wooden fences and clay jars. 12–16s | Garden: She picks dew-covered fresh vegetables and places them in the basket. The same dog waits nearby. 16–20s | Village Walk: She walks along a quiet dirt-and-stone path with the dog beside her. She gently pats its head. Traditional farmhouse, firewood, clay jars and wooden fences surround them. 20–25s | Rice Fields: She and the dog walk between green-golden rice paddies. Misty mountains, birds and distant farmers create an authentic 1995 Korean countryside atmosphere. Subtle 35mm film grain and natural lens flare. 25–28s I Stream: She kneels beside a small wooden bridge and washes the vegetables in a clear stream. The dog waits beside her and looks curiously at the water. 28–30s | Home: She walks back toward the village with her basket, the same dog happily beside her. Warm sunlight fills the road as she looks toward the mountains and smiles peacefully. AUDIO: rooster calls, chickens, birds, gentle dog sounds, flowing water, wind, village ambience and faint old-radio music. STRICT CONSISTENCY: Same woman, face, braid, outfit, shoes, basket and same dog throughout. Dog must keep identical breed, size, fur and markings. NO: modern cars, smartphones, modern buildings, modern clothing, scooters, contemporary objects or post-1995 technology. CAMERA: ONE continuous cinematic take; no cuts, transitions, montage or time jumps. Natural handheld camera movement.
CAMERA/LOOK: DV 16mm tape-camcorder vlog aesthetic, POV alternating between CHASE and PARTNER, sometimes propped on gym equipment. Handheld shake, imperfect framing, delayed focus, clumsy zooms, occasional face cutoffs. Soft blurry tape texture, faint noise, bloomed warm highlights, flickering exposure, muted contrast, realistic skin. Sweat and flushed faces intensify throughout. Camcorder never visible. CHARACTERS: CHASE: Korean idol, 20s, long black high ponytail, expressive eyes, flushed cheeks, slim athletic build. Lightweight modest summer workout top + high-waisted leggings/knee-length shorts, sneakers. PARTNER: Korean woman, 20s, similar age/energy, tied-back hair, athletic build, lightweight modest athletic outfit, sneakers. No jewelry. Both visibly sweaty. SETTING: Hot summer gym with broken AC, warm harsh lighting, fan blowing warm air, open door, racks, mats, mirrors, water bottles. 30s STORYBOARD — 15 CUTS: 1. 0–2s: Propped camera. Both enter fanning themselves. CHASE: “Okay, it is way too hot in here today.” 2. 2–4s: Handheld. PARTNER points at broken AC: “The AC's been out since this morning.” 3. 4–6s: At rack, CHASE loads bar, PARTNER spots. “Let’s just push through it.” 4. 6–8s: Propped shot. CHASE lifts while PARTNER spots. 5. 8–9.5s: Macro hands gripping sweaty bar, sweat dripping. Ambient sound. 6. 9.5–11.5s: PARTNER lifts, CHASE spots: “You've got it, come on!” 7. 11.5–13.5s: Both catch breath, fan shirts, laugh. PARTNER: “Okay, I'm already soaked.” 8. 13.5–15.5s: Walking to mats with water. CHASE: “Water break, mandatory.” 9. 15.5–17.5s: Propped shot. Both drink, sigh, laugh. 10. 17.5–19.5s: Both plank competitively. PARTNER: “Who’s giving up first?” 11. 19.5–21.5s: Straining, sweat dripping. CHASE: “Not—me—” 12. 21.5–23.5s: Macro sweat hitting mat, heavy breathing. 13. 23.5–25.5s: Both collapse laughing. PARTNER: “Okay, that's officially a tie.” 14. 25.5–27.5s: Sitting up, jokingly fanning each other with towels. CHASE: “This heat is actually insane.” 15. 27.5–30s: Arm’s-length selfie. Both sweaty, grinning, tired high-five. CHASE: “Okay, we survived — see you guys!” TONE: Playful, sweaty, energetic gym vlog. Competitive but supportive banter, genuine exhaustion and laughter. Heat and sweat visibly escalate from beginning to end.
Ultra-realistic 30-second, 1080p personal home-video, an ordinary autumn afternoon in the life of a young Korean woman, no reference image. MAIN SUBJECT: early 20s, realistic skin texture, minimal makeup, relaxed genuine personality. Dark-brown hair loosely tied back. Oversized cream knit sweater, blue jeans, white sneakers, small canvas shoulder bag. Same face, hair, and outfit held throughout. SETTING: quiet older Seoul residential neighborhood, cool autumn afternoon. Narrow concrete streets, aging brick houses, fallen leaves, parked bicycles, faded walls, small neighborhood shops. Lived-in and unplanned - no tourist spots, no visible brands. CAMERA: raw handheld footage from an early-2000s MiniDV camcorder, held by a friend. Autofocus hunting, exposure fluctuations, awkward zooms, mild tape noise, natural camera-handling imperfections. No stabilization, no gimbal, no cinematic choreography. BEATS: she leaves home, buys a roasted sweet potato from a street stall, burns her mouth and laughs about it. Keeps walking, notices a bike passing, waves at a dog. A leaf lands on her shoulder - she says Why me? and laughs it off. She sits on a low wall, finishes eating, watches the street in silence for a few seconds -camera just keeps rolling. She stands, walks off, turns back once -Are you coming? - then disappears around the corner as the tape cuts to black. AUDIO: wind, leaves on pavement, footsteps, bicycle bells, distant scooters, doors closing, subtle camera-handling noise. No music, no narration. Only the two lines above. STYLE: nothing dramatic happens on purpose. No posing, no exaggerated acting, no cinematic hero shots -realism comes from awkward laughter, imperfect framing, and dead air nobody bothered to cut. The moment she starts performing for the lens instead of her friend, the whole "found tape" illusion breaks. This one never does.
30s, 1080p, 9:16, nostalgic handheld home-video style, friend filming w/ old digicam. Korean woman (cream cardigan, sage blouse, jeans) buys groceries, bag rips on the walk home, apples spill, she laughs, stranger helps, bites an apple: "now we're safe." Natural audio only, no music/text/logo.\nUse exactly one reference image for the woman. Preserve her identity, face, skin tone, hairstyle, body proportions and wardrobe consistently.\n\nCharacter:\n\nYoung Korean woman, early 20s, cream cardigan, sage-green blouse, blue jeans, white sneakers, brown shoulder bag, silver earrings. Natural makeup, realistic skin and hair.\n\nStyle:\n\nCasual friend-recorded smartphone footage. Handheld, imperfect framing, autofocus shifts, natural exposure, slight motion blur/compression. Real Seoul neighborhood and morning light. No CGI, beauty filter or polished commercial look.\n\nREALISM:\n\nProgressive bag tearing, believable item weight and gravity, accurate hands, payment, walking and object continuity. No teleporting, duplication, disappearing objects, warped hands, extra fingers or wardrobe changes.\n\nAUDIO:\n\nNatural grocery store ambience, refrigeration hum, plastic bag rustling, footsteps, traffic, register beeps, payment sounds, rolling apple sounds, fabric movement and genuine laughter. No music, narration, subtitles, logos or watermark.\n\nVideo:\n\n00:00–00:04 — Grocery Store: She walks through a small neighborhood grocery store, picks up apples and eyes them, says, "These look fresh." Grabs a few items — apples, a carton of eggs, a bag of rice — and puts them in a plastic shopping bag.\n\n00:04–00:08 — Payment: She pays at the counter, thanks the cashier, picks up the full bag with both hands and heads out the door.\n\n00:08–00:12 — Drop: Walking down the street, the bag's handle slowly stretches and rips. An apple rolls out. She doesn't notice; the camera catches it.\n\n00:12–00:16 — Discovery: The sound behind her makes her stop. She turns, sees the apple and the torn handle. "Oh no…" She crouches down.\n\n00:16–00:21 — Chaos: As she lifts the bag, the eggs carton tips and more apples spill out. She catches one apple and chases another rolling toward the curb. She laughs nervously; the camera shakes naturally.\n\n00:21–00:25 — Help: A shopkeeper or passerby comes over with a sturdier bag. They gather everything together, double-checking the eggs are intact. She checks the bag's strength before standing.\n\n00:25–00:30 — Payoff: She walks away, pulls out one apple, takes a bite and smiles: "Okay… now we're safe." She glances at the eggs carton, relieved it survived. The camera operator quietly laughs. Cut naturally while moving.
A 2000s studio-comedy film shot, 16:9, 35mm, moderate film grain, bright American daylight, tracking camera at chest height following a man along a city sidewalk. Smooth dolly/track with him, no handheld phone, no gimbal whip, no drone, no cuts. The camera stays with him the whole 30 seconds, medium-wide, the street readable behind him. IMAGE REFERENCES [image_ref] is the opening frame AND the identity lock: the bald man with the thick dark beard, open grey plaid flannel over a white t-shirt, mid-stride on this exact sunlit sidewalk. Keep his exact face, bald scalp, beard, body. Keep this street: Sherman Brothers shop, cafe table, stone steps and arched doorway, red fire hydrant, American flag, storefronts. Start on this composition, then the camera travels with him down the block. Do not redesign his face. He sings out loud, diegetic, the lyrics "I've got the power" in a loud off-key enthusiastic voice, the whole walk. No extra score under it. Street air, footsteps, then the gags. TIMELINE 0-4s: [Tracking medium-wide, opening on image_1] He is already walking, already singing, mouth wide, chest out, a little strut. The camera slides with him. Daylight, grain. He is having the time of his life. 4-8s: [Tracking, he twists his torso toward the hydrant without stopping] He points two fingers at the red fire hydrant on the sidewalk. The hydrant cap blows and three hard jets of water blast out in different directions, high, violent, real water physics, mist in the sun. He keeps walking and singing, does not look back for long. Camera stays on him, hydrant geysers in the background. 8-13s: [Tracking, still singing] He keeps the strut. Water still arcing behind him. Pedestrians flinch at the spray. He grins, points at the sky on a lyric, never breaks stride. 13-18s: [Tracking as he passes a woman coming the other way] A woman in a knee-length dress walks toward him. As they cross, a sudden gust hits only her: the hem lifts a little, Marilyn sidewalk-vent style but modest, a brief flip then it drops. She grabs the fabric, startled. He keeps walking, still singing, a tiny glance, no contact. Camera never leaves him. 18-23s: [Tracking slows as he reaches a shop window] He stops in front of a big storefront glass, still humming. Leans in. We see him and his reflection clearly: bald head, beard, plaid, white tee. He studies himself, tilts his chin. 23-28s: [Held on him and the reflection] In the glass and on his body at the same time, the clothes change in one continuous morph: the flannel and tee become a sharp white open-collar suit, jacket, tailored trousers, a gold chain. No cut, no flash, the fabric rewrites itself. He checks the new look in the window, pleased, shoulders back. 28-30s: [Medium, still on him] He licks the tip of his index finger, taps it to his hip, and a little puff of white steam hisses off the fabric like a hot iron being quenched. He mouths the last "power," smug. Clip ends on that
Main Subjects: Three Italian university roommates in their early 20s, natural everyday appearances, realistic skin texture, minimal makeup. Woman 1: long dark-brown hair in a loose ponytail, wearing a faded red T-shirt and loose jeans. Woman 2: short curly brown hair, wearing an oversized cream sweater and dark trousers. Man 1: messy dark hair, wearing a grey T-shirt and navy lounge pants. Maintain consistent identities, clothing, hairstyles, and appearance throughout. Location: Modest shared apartment in Bologna on an ordinary weekday evening. Small kitchen, worn wooden cabinets, tiled floor, drying dishes, grocery bags, old refrigerator, open window overlooking neighboring apartments, simple dining table, and everyday household clutter. No luxury styling. Visual Style: Ultra-realistic documentary realism. Genuine roommate interaction, spontaneous laughter, natural body language, believable domestic details. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping near the kitchen window, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 The roommates unpack groceries onto the kitchen counter. One pulls out tomatoes and pasta while another struggles to open a stubborn grocery bag. 00:03–00:06 Woman 1 chops tomatoes while Woman 2 stirs sauce in an old saucepan. The camera moves closer and autofocus briefly locks onto the steam. 00:06–00:09 The man tastes the sauce directly from the wooden spoon and immediately makes an exaggerated face. Everyone laughs. 00:09–00:12 They sit around the small table eating pasta, talking over one another and casually passing bread between them. 00:12–00:15 Someone notices the camera and raises a fork toward the lens while everyone laughs. The operator backs away, bumps lightly into the kitchen doorway, and the recording abruptly cuts to black. Audio: Natural ambience only–pots clattering, chopping, sizzling sauce, running water, chairs scraping, Italian conversation, laughter, refrigerator hum, dishes and forks. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing an ordinary dinner with Italian university roommates–warm, messy, youthful, intimate, and completely believable.
Create a photorealistic 30-second 1990s multi-camera sitcom scene, 9:16 vertical, shot like genuine 35mm television footage. Bright cosy apartment, warm tungsten lighting, soft even fill, subtle film grain, evening blue dusk outside, authentic sitcom staging and natural audience laughter. A young man enters his apartment carrying groceries and freezes when he discovers 12 real cats having a “book club.” Cats are naturally scattered across the red sofa, armchair, rug and coffee-table area with open books nearby. His chubby white cat, wearing a backwards burgundy cap, rectangular glasses and red-black plaid flannel, sits proudly in the middle of the sofa. All cats must remain completely realistic four-legged domestic cats; only the white cat speaks, with a posh British accent. 0:00–0:05 Man stares around in disbelief. MAN: “No. Nope. What is THIS?” CAT: “Book club.” MAN: “Book club?!” CAT: “Every Thursday.” 0:05–0:11 MAN: “There are ELEVEN cats in my living room!” CAT: “Twelve.” MAN: “Where’s twelve—?” Another cat suddenly pokes its head naturally from his grocery bag. MAN: “OH, COME ON!” 0:11–0:17 Man points at the books. MAN: “None of you can even READ!” Dead silence. All cats gradually turn and stare at him naturally. MAN, suddenly unsure: “…Right?” 0:17–0:22 White cat looks over its glasses. CAT: “And yet, somehow… you’re still the dumbest one here.” Huge audience laughter. Man gives the camera an exhausted stare. 0:22–0:27 MAN: “That’s it! Everybody OUT! Book club is OVER!” CAT: “We took a vote.” MAN: “And?!” CAT: “You’re leaving.” 0:27–0:30 Doorbell rings. Man opens the door and finds another real cat sitting outside with a paperback gently held in its mouth. CAT, from sofa: “Oh good. That’s Margaret.” Man closes his eyes in defeat. Freeze frame with huge laughter, applause and a short upbeat 90s sitcom ending sting. Ultra-realistic physical set, natural human acting, genuine cat fur and anatomy, believable physics and imperfect feline movements. No CGI/AI look, anthropomorphic cats, human-like cat gestures, extra limbs, cartoon styling, futuristic elements, dark cinematic grading, subtitles, logos or watermark.
Main Subject: Young Spanish woman, 25, natural everyday appearance, shoulder-length dark-brown hair worn loose with slightly messy bangs, realistic skin texture, minimal makeup, relaxed after-work personality. Wearing a faded terracotta T-shirt, lightweight beige cardigan, high-waisted dark-blue jeans, worn white sneakers, and carrying a simple canvas tote bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Ordinary Madrid residential neighborhood on a warm weekday evening. Small local grocery shop, apartment buildings with balconies, parked compact cars, scooters, plane trees, tiled sidewalks, recycling bins, and residents returning home from work. No famous landmarks, tourist streets, or staged activity. Visual Style: Ultra-realistic documentary realism. Genuine everyday behavior, natural body language, spontaneous local interactions, authentic Spanish neighborhood atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting between shelves and her face, exposure pumping when entering and leaving the shop, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks down the residential sidewalk carrying an empty canvas tote. She checks a handwritten grocery list while approaching a small neighborhood shop. 00:03–00:06 Inside, she picks up tomatoes and oranges, comparing them casually before placing them into her basket. Autofocus briefly locks onto the colorful produce. 00:06–00:09 She chooses a loaf of bread and a carton of milk. The shopkeeper greets her from behind the counter, and she responds with a friendly smile. 00:09–00:12 Outside, she rearranges the groceries inside her tote while standing beneath a tree. A scooter passes slowly behind her. 00:12–00:15 She notices the camcorder, laughs softly, lifts the grocery bag as if showing what she bought, and continues toward her apartment. The operator follows for a few steps before accidentally pointing at the pavement and cutting to black. Audio: Natural ambience only–Spanish conversations, shop door bell, grocery bags rustling, footsteps, scooters, distant traffic, birds, apartment sounds, and light neighborhood chatter. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing an ordinary after-work grocery run in Madrid–local, casual, imperfect, warm, nostalgic, and completely believable.
Young American woman in her early 20s, naturally attractive, realistic skin texture, light natural makeup, warm curious traveler personality. Wavy chestnut-brown hair slightly damp from rain, falling loosely past her shoulders. Wearing a fitted olive-green oversized raincoat over a plain white t-shirt, denim shorts, white sneakers now damp at the edges, and a small canvas crossbody bag. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout. LOCATION A busy Mumbai street during a warm monsoon evening. Wet asphalt reflecting neon and streetlights, crowded narrow lanes, old buildings with balconies, hanging wires, colorful shop signs, steam rising from a nearby chai stall, umbrellas bobbing through the crowd, auto-rickshaws splashing through puddles. CAMERA / VISUAL STYLE Raw personal footage casually recorded by a friend on an early-2000s consumer DV camcorder. Strong handheld shake, imperfect framing, autofocus hunting, faded colors, soft digital detail, slight exposure shifts, mild digital noise, occasional motion blur, water droplets on the lens and accidental zooms. No stabilization, drone footage, gimbal movement or polished commercial cinematography. — UNDER AN AWNING She stands under a shop awning, sheltering from the rain, watching the street with a delighted smile, clearly unused to monsoon weather. She holds her hand out past the awning's edge to feel the rain, laughing slightly at how heavy it is. — STEPPING INTO THE RAIN She pulls her raincoat hood up and steps out into the rain, walking along the wet street. The camera follows shakily beside her, rain visible streaking across the lens. — CHAI STALL She notices a small steaming chai stall on the corner. She walks over, watches the vendor pour tea from height between two cups. She hands over some cash, receives a small clay cup of chai, and wraps both hands around it for warmth. — DRINKING CHAI She takes a careful sip, eyes widening slightly at the taste and heat. She looks toward the camera, smiling and nodding in approval. Steam rises from the cup as rain continues falling around her. — WALKING THROUGH THE CROWD She continues down the street, weaving gently past umbrellas, splashing lightly through shallow puddles. Reflections of shop lights ripple across the wet ground beneath her sneakers. — MOMENT OF PLAY She jumps once, playfully, into a puddle, laughing as water splashes up near her shoes. She glances back at the camera with a mischievous grin, hair sticking slightly to her damp forehead. — FINAL MOMENT She stops beneath a flickering streetlight, rain still falling around her, chai cup now empty in her hand. She turns to the camera, wipes a few raindrops from her cheek, and smiles warmly. She says: "This is amazing!" She laughs, turns, and walks off into the crowd as the rain continues and the camera lingers on the street
Use exactly one reference image for the woman. Preserve her identity, face, skin tone, hairstyle, body proportions and wardrobe consistently throughout. Format: 15s, 1080p, 16:9 Style: Ultra-realistic candid home-cooking footage, handheld smartphone or consumer camera style, as if filmed casually by someone in the kitchen. Natural imperfect framing, slight autofocus shifts, soft realistic grain, gentle handheld sway. No CGI, beauty filter, or overly polished commercial look. Warm natural kitchen lighting — soft daylight from a window mixed with warm indoor light, realistic exposure. Character: Young Korean woman, mid-20s, casual home outfit (oversized t-shirt or simple hoodie, apron loosely tied over it), hair tied up in a loose bun or ponytail, natural no-makeup look. Relaxed, focused expression, soft smile, easy unhurried movements. Setting: A cozy home kitchen — wooden countertop, a few pots and ingredients laid out, soft daylight coming through a nearby window, faint ambient sounds of chopping, sizzling, and kitchen background noise. 00:00–00:03 — Starting Prep She stands at the counter, tying her apron strings behind her back, glancing down at ingredients laid out in front of her — vegetables, a cutting board, a bowl. 00:03–00:06 — Chopping She picks up a knife and begins chopping vegetables with calm, practiced movements, occasionally glancing up with a small content smile, natural kitchen sounds in the background. 00:06–00:09 — Stirring the Pan She moves to the stove, stirring something in a pan, steam rising gently. She leans in slightly to smell the aroma, closing her eyes briefly with a satisfied expression. 00:09–00:12 — Tasting She dips a small spoon into the pot, tastes it, and reacts with a pleased nod and soft smile, wiping her hands on her apron. 00:12–00:15 — Plating She scoops the finished dish onto a plate, setting it down on the counter, stepping back slightly to admire her work with a warm, satisfied smile as natural light catches the steam rising from the food. now generatre this images face korian girl to natch this prompt start scene changes dress keep faces
In a heartwarming home video style, a joyful toddler discovers music at a vintage piano. An adorable 2-year-old boy with curly dark hair, bright eyes, and a wide smile, wearing a white t-shirt and diaper, sits on a beige bench. He gently presses keys...
Main Subject: Young French woman, 23, natural everyday appearance, shoulder-length chestnut-brown hair loosely tied with wispy bangs, realistic skin texture, minimal makeup, relaxed personality. Wearing a faded navy cardigan over a white cotton T-shirt, high-waisted straight-leg blue jeans, worn beige sneakers, and a small brown leather shoulder bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Ordinary residential neighborhood in Lyon on a cool Saturday morning. Small open-air produce market, local bakeries, apartment façades, bicycles, parked cars, reusable shopping bags, elderly residents, narrow sidewalks, and plane trees. No famous landmarks, tourists, or staged scenes. Visual Style: Ultra-realistic documentary realism. Genuine local behavior, natural body language, imperfect everyday interactions, authentic French neighborhood atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping between sunlight and shade, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks through the neighborhood carrying a reusable shopping bag, stopping at a fruit stall. The camera briefly focuses on peaches before finding her face. 00:03–00:06 She chooses several tomatoes and casually chats with the elderly vendor. She laughs at something he says while placing the vegetables into her bag. 00:06–00:09 She walks to a nearby bakery and buys a fresh baguette. The camera struggles to focus through the bakery window. 00:09–00:12 Outside, she breaks off a small piece of bread and tastes it while walking beneath the trees. A cyclist passes behind her. 00:12–00:15 She notices the camcorder, smiles naturally, lifts the baguette playfully, and continues down the residential street. The operator pans toward passing bicycles and accidentally cuts the recording to black. Audio: Natural ambience only–French conversations, footsteps, bicycle bells, paper bags, market vendors, distant cars, birds, light wind, bakery door sounds. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing a completely ordinary Saturday morning in a French neighborhood–local, imperfect, intimate, nostalgic, and genuinely believable.
Create a 15-second Vlog-style home video of a junior high school girl in a brass band club in the countryside after school, filmed by a friend from the same section. The 15 seconds consists of a montage of 7 short shots (approx. 2 seconds each) with hard cuts. Each shot is a different moment, one shot = one small event. Do not use transitions or fades. Since it's being filmed by a close friend, she is relaxed and shows her natural expressions. Main Subject: The same Japanese junior high school girl throughout all shots. A beautiful girl with a sense of transparency. Large double eyelids that tend to droop slightly, eyelashes long enough to cast shadows when looking down, thin natural eyebrows, realistic skin texture that looks white and transparent, no makeup, a small straight nose, and thin cherry-blossom colored lips. A beautiful oval-shaped face. Her straight black hair is tied in a low ponytail. Usually has a modest and calm atmosphere. Wearing a white short-sleeved sailor uniform, a navy collar, a knee-length navy pleated skirt, and indoor shoes. The instrument is a well-used silver trumpet. The face, body type, hairstyle, uniform, and instrument must be completely consistent from beginning to end. Location: A music room in a rural junior high school after school in summer. Music stands, lined-up chairs, open windows, the school grounds and mountains outside. The evening light gradually deepens. No advertisements or recognizable brands. Camera / Visual Style: Common to all shots: An old handheld home digital camera. Natural shaking, imperfect framing, occasional focus hunting, exposure fluctuations, light motion blur, subtle noise, and slightly suppressed colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (in order, approx. 2 seconds each, all hard cuts): 1. She enters the music room holding her instrument case, notices the camera, and waves shyly and small. 2. A close-up of her hands carefully polishing the trumpet with a soft cloth after opening the case. 3. Singing the melody to herself while making small notes in pencil on the sheet music on the stand. 4. Sitting with a friend, talking about something, and laughing while covering her mouth (no words audible). 5. The moment she holds the trumpet, her expression changes. A dignified and serious profile in the music room with the evening sun shining in. 6. A long tone. Eyes staring straight ahead. Voices from club activities in the distance outside the window. 7. After finishing the note, she breathes out and smiles bashfully at the camera. During that, at approximately 00:14, the recording suddenly cuts to black. No fade-out. Physical Realism: Maintain plausible real-world physics. Hands, fingers, hair, uniform, trumpet, and music stands behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing objects, or sudden transformations. Instrument posture and finger positions remain realistic. The subject remains consistent across all shots. Audio: Natural environmental sounds only. Clear long tones of the trumpet, the sound of cloth rubbing, the sound of the pencil, distant voices of club activities, the sound of cicadas. No music (BGM). No narration. No artificial sound effects. Final Atmosphere: The record of an after-school session where you see both the modest girl and the moment she becomes a different person, dignified, when she holds her instrument. Not a commercial work. Not a music video. Quiet, dedicated, nostalgic, warm, improvisational, and deeply human. Prioritize the feeling that the camera happened to be there.
Create a 25–30 second ultra-realistic cinematic sequence inside a photorealistic 1950s American diner. Chrome stools, deep red booths, checkerboard floor, warm window light and buzzing neon. Premium film grain with natural handheld texture. GIRL: Use the uploaded reference image as the exact character reference. Young woman with consistent face, hair, skin tone and body proportions, wearing a cream quarter-zip sweater, black pants and white sneakers. She sits calmly at the counter, completely focused on a thick milkshake. MAN: Young male waiter wearing a classic white diner shirt, dark trousers and apron, carrying a tray with a burger and large glass jug of orange juice. She slowly sips her milkshake as the waiter approaches behind her. A man rising from a nearby booth accidentally bumps into him. The tray, burger and orange juice launch into the air. Orange juice explodes into suspended droplets while the camera smoothly orbits around the frozen moment. Everyone freezes in shock. The girl at the counter remains completely unfazed, still slowly drinking her milkshake. The camera makes a full orbit around the frozen diner. Floating burger, tray and orange juice droplets hang in the air while she takes another deliberate sip. Time suddenly rewinds. The food, waiter and orange juice smoothly return to their original positions. The waiter regains his balance. The girl looks up just before the collision happens and quietly moves her milkshake out of the way. The accident is avoided. Final extreme close-up: she takes one last sip, gives a tiny knowing smile toward the camera and continues drinking. CAMERA: 35mm anamorphic look, handheld realism transitioning into a smooth 360° bullet-time orbit during the freeze, shallow depth of field, realistic motion blur, warm film grain, natural skin texture, photorealistic physics. AUDIO: Diegetic only — straw suction, ice moving inside the glass, tray clatter, glass impact, orange juice splash, diner ambience, brief silence during the freeze, reversed sound during rewind. No music. NEGATIVE: No gore, injuries, distorted faces, extra limbs, floating characters outside the freeze effect, unrealistic liquid physics, product deformation, text, subtitles or watermark.
Main Subjects: Three Italian university roommates in their early 20s, natural everyday appearances, realistic skin texture, minimal makeup. Woman 1: long dark-brown hair in a loose ponytail, wearing a faded red T-shirt and loose jeans. Woman 2: short curly brown hair, wearing an oversized cream sweater and dark trousers. Man 1: messy dark hair, wearing a grey T-shirt and navy lounge pants. Maintain consistent identities, clothing, hairstyles, and appearance throughout. Location: Modest shared apartment in Bologna on an ordinary weekday evening. Small kitchen, worn wooden cabinets, tiled floor, drying dishes, grocery bags, old refrigerator, open window overlooking neighboring apartments, simple dining table, and everyday household clutter. No luxury styling. Visual Style: Ultra-realistic documentary realism. Genuine roommate interaction, spontaneous laughter, natural body language, believable domestic details. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping near the kitchen window, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 The roommates unpack groceries onto the kitchen counter. One pulls out tomatoes and pasta while another struggles to open a stubborn grocery bag. 00:03–00:06 Woman 1 chops tomatoes while Woman 2 stirs sauce in an old saucepan. The camera moves closer and autofocus briefly locks onto the steam. 00:06–00:09 The man tastes the sauce directly from the wooden spoon and immediately makes an exaggerated face. Everyone laughs. 00:09–00:12 They sit around the small table eating pasta, talking over one another and casually passing bread between them. 00:12–00:15 Someone notices the camera and raises a fork toward the lens while everyone laughs. The operator backs away, bumps lightly into the kitchen doorway, and the recording abruptly cuts to black. Audio: Natural ambience only–pots clattering, chopping, sizzling sauce, running water, chairs scraping, Italian conversation, laughter, refrigerator hum, dishes and forks. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing an ordinary dinner with Italian university roommates–warm, messy, youthful, intimate, and completely believable.
Create a 15-second Vlog-style home video of a 'mild yankee' style Japanese high school boy meeting a kitten in a cardboard box on a rainy day, filmed casually by a friend from under the eaves. 480p. The 15 seconds consist of a hard-cut montage of 7 short shots (approx. 2 seconds each). Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since a close friend is filming, he remains his natural self, unconcerned about being recorded. Main Subject: Same Japanese high school boy throughout all shots. Short hair dyed bright brownish-gold, a small silver earring in one ear. Thin, groomed eyebrows and sharp slanted eyes with hidden double lids, but upon closer look, long eyelashes, a straight nose, and a sweet face with well-shaped thin lips that looks much younger when he smiles. Realistic sun-tanned skin texture, slim jawline. Wearing an oversized black T-shirt, baggy black pants, sandals, and a transparent vinyl umbrella. Completely consistent face, physique, hairstyle, clothing, and umbrella from start to finish. Kitten: A tiny white kitten in a cardboard box partially getting wet in the rain. Location: An alleyway on the edge of a rural shopping street on a rainy evening. Closed storefronts, wet asphalt, eaves, cardboard boxes. No ads or recognizable brands. Camera / Visual Style: Common for all shots: Handheld old consumer digital camera held by a friend under the eaves. Natural shake, imperfect framing, occasional focus hunting, exposure fluctuations due to rain darkness, light motion blur, subtle noise, slightly muted colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (In order, approx. 2 seconds each, all hard cuts): 1. Under the eaves of the rainy shopping street. Talking with his umbrella on his shoulder, he suddenly notices something in the back of the alley. 2. A kitten in a cardboard box getting wet in the corner of the alley. He squats in front of the box. 3. Keeping his sharp gaze, he stares intently at the kitten. The kitten meows softly. 4. With his rugged hand, he timidly and gently pets it. The kitten rubs its head against his palm. 5. After petting for a while, his sharp gaze softens and he smiles slightly. 6. Standing up, he opens his vinyl umbrella and fixes it over the cardboard box as rain protection. 7. Leaving the umbrella behind, a shot of his back as he runs away through the rain. Midway, around 00:14, the recording suddenly cuts to blackout. No fade out. Physical Realism: Maintain realistic physics. Hands, fingers, hair, clothes, rain, umbrella, cardboard, and kitten behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing items, or sudden deformations. The kitten moves naturally on four legs. The umbrella stays where it was placed. Maintain wet clothes and hair, road reflections, and foot grounding. Keep the subject consistent across all shots. Audio: Natural ambient sounds only. Sound of rain, water dripping from eaves, kitten's soft meow, sandal footsteps, distant car sounds. No music. No narration. No artificial sound effects. Final Mood: A record of a scary-looking boy's kindness that was never meant to be seen by anyone, caught by chance. Not a commercial work. Not a scene from a drama. Running away represents his shyness. Rugged, awkward, smelling of rain, warm, and deeply human. Prioritize the feeling that the camera just happened to be there.
Young American woman in her early 20s, naturally attractive, realistic skin texture, light natural makeup, warm curious traveler personality. Wavy chestnut-brown hair slightly damp from rain, falling loosely past her shoulders. Wearing a fitted olive-green oversized raincoat over a plain white t-shirt, denim shorts, white sneakers now damp at the edges, and a small canvas crossbody bag. Maintain the same face, hairstyle, clothing, body proportions and overall appearance throughout. LOCATION A busy Mumbai street during a warm monsoon evening. Wet asphalt reflecting neon and streetlights, crowded narrow lanes, old buildings with balconies, hanging wires, colorful shop signs, steam rising from a nearby chai stall, umbrellas bobbing through the crowd, auto-rickshaws splashing through puddles. CAMERA / VISUAL STYLE Raw personal footage casually recorded by a friend on an early-2000s consumer DV camcorder. Strong handheld shake, imperfect framing, autofocus hunting, faded colors, soft digital detail, slight exposure shifts, mild digital noise, occasional motion blur, water droplets on the lens and accidental zooms. No stabilization, drone footage, gimbal movement or polished commercial cinematography. — UNDER AN AWNING She stands under a shop awning, sheltering from the rain, watching the street with a delighted smile, clearly unused to monsoon weather. She holds her hand out past the awning's edge to feel the rain, laughing slightly at how heavy it is. — STEPPING INTO THE RAIN She pulls her raincoat hood up and steps out into the rain, walking along the wet street. The camera follows shakily beside her, rain visible streaking across the lens. — CHAI STALL She notices a small steaming chai stall on the corner. She walks over, watches the vendor pour tea from height between two cups. She hands over some cash, receives a small clay cup of chai, and wraps both hands around it for warmth. — DRINKING CHAI She takes a careful sip, eyes widening slightly at the taste and heat. She looks toward the camera, smiling and nodding in approval. Steam rises from the cup as rain continues falling around her. — WALKING THROUGH THE CROWD She continues down the street, weaving gently past umbrellas, splashing lightly through shallow puddles. Reflections of shop lights ripple across the wet ground beneath her sneakers. — MOMENT OF PLAY She jumps once, playfully, into a puddle, laughing as water splashes up near her shoes. She glances back at the camera with a mischievous grin, hair sticking slightly to her damp forehead. — FINAL MOMENT She stops beneath a flickering streetlight, rain still falling around her, chai cup now empty in her hand. She turns to the camera, wipes a few raindrops from her cheek, and smiles warmly. She says: "This is amazing!" She laughs, turns, and walks off into the crowd as the rain continues and the camera lingers on the street
CAMERA/LOOK: DV 16mm tape-camcorder vlog aesthetic, POV alternating between CHASE and PARTNER, sometimes propped on gym equipment. Handheld shake, imperfect framing, delayed focus, clumsy zooms, occasional face cutoffs. Soft blurry tape texture, faint noise, bloomed warm highlights, flickering exposure, muted contrast, realistic skin. Sweat and flushed faces intensify throughout. Camcorder never visible. CHARACTERS: CHASE: Korean idol, 20s, long black high ponytail, expressive eyes, flushed cheeks, slim athletic build. Lightweight modest summer workout top + high-waisted leggings/knee-length shorts, sneakers. PARTNER: Korean woman, 20s, similar age/energy, tied-back hair, athletic build, lightweight modest athletic outfit, sneakers. No jewelry. Both visibly sweaty. SETTING: Hot summer gym with broken AC, warm harsh lighting, fan blowing warm air, open door, racks, mats, mirrors, water bottles. 30s STORYBOARD — 15 CUTS: 1. 0–2s: Propped camera. Both enter fanning themselves. CHASE: “Okay, it is way too hot in here today.” 2. 2–4s: Handheld. PARTNER points at broken AC: “The AC's been out since this morning.” 3. 4–6s: At rack, CHASE loads bar, PARTNER spots. “Let’s just push through it.” 4. 6–8s: Propped shot. CHASE lifts while PARTNER spots. 5. 8–9.5s: Macro hands gripping sweaty bar, sweat dripping. Ambient sound. 6. 9.5–11.5s: PARTNER lifts, CHASE spots: “You've got it, come on!” 7. 11.5–13.5s: Both catch breath, fan shirts, laugh. PARTNER: “Okay, I'm already soaked.” 8. 13.5–15.5s: Walking to mats with water. CHASE: “Water break, mandatory.” 9. 15.5–17.5s: Propped shot. Both drink, sigh, laugh. 10. 17.5–19.5s: Both plank competitively. PARTNER: “Who’s giving up first?” 11. 19.5–21.5s: Straining, sweat dripping. CHASE: “Not—me—” 12. 21.5–23.5s: Macro sweat hitting mat, heavy breathing. 13. 23.5–25.5s: Both collapse laughing. PARTNER: “Okay, that's officially a tie.” 14. 25.5–27.5s: Sitting up, jokingly fanning each other with towels. CHASE: “This heat is actually insane.” 15. 27.5–30s: Arm’s-length selfie. Both sweaty, grinning, tired high-five. CHASE: “Okay, we survived — see you guys!” TONE: Playful, sweaty, energetic gym vlog. Competitive but supportive banter, genuine exhaustion and laughter. Heat and sweat visibly escalate from beginning to end.
Main Subject: Young French woman, 23, natural everyday appearance, shoulder-length chestnut-brown hair loosely tied with wispy bangs, realistic skin texture, minimal makeup, relaxed personality. Wearing a faded navy cardigan over a white cotton T-shirt, high-waisted straight-leg blue jeans, worn beige sneakers, and a small brown leather shoulder bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Ordinary residential neighborhood in Lyon on a cool Saturday morning. Small open-air produce market, local bakeries, apartment façades, bicycles, parked cars, reusable shopping bags, elderly residents, narrow sidewalks, and plane trees. No famous landmarks, tourists, or staged scenes. Visual Style: Ultra-realistic documentary realism. Genuine local behavior, natural body language, imperfect everyday interactions, authentic French neighborhood atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping between sunlight and shade, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks through the neighborhood carrying a reusable shopping bag, stopping at a fruit stall. The camera briefly focuses on peaches before finding her face. 00:03–00:06 She chooses several tomatoes and casually chats with the elderly vendor. She laughs at something he says while placing the vegetables into her bag. 00:06–00:09 She walks to a nearby bakery and buys a fresh baguette. The camera struggles to focus through the bakery window. 00:09–00:12 Outside, she breaks off a small piece of bread and tastes it while walking beneath the trees. A cyclist passes behind her. 00:12–00:15 She notices the camcorder, smiles naturally, lifts the baguette playfully, and continues down the residential street. The operator pans toward passing bicycles and accidentally cuts the recording to black. Audio: Natural ambience only–French conversations, footsteps, bicycle bells, paper bags, market vendors, distant cars, birds, light wind, bakery door sounds. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing a completely ordinary Saturday morning in a French neighborhood–local, imperfect, intimate, nostalgic, and genuinely believable.
A 2000s studio-comedy film shot, 16:9, 35mm, moderate film grain, bright American daylight, tracking camera at chest height following a man along a city sidewalk. Smooth dolly/track with him, no handheld phone, no gimbal whip, no drone, no cuts. The camera stays with him the whole 30 seconds, medium-wide, the street readable behind him. IMAGE REFERENCES [image_ref] is the opening frame AND the identity lock: the bald man with the thick dark beard, open grey plaid flannel over a white t-shirt, mid-stride on this exact sunlit sidewalk. Keep his exact face, bald scalp, beard, body. Keep this street: Sherman Brothers shop, cafe table, stone steps and arched doorway, red fire hydrant, American flag, storefronts. Start on this composition, then the camera travels with him down the block. Do not redesign his face. He sings out loud, diegetic, the lyrics "I've got the power" in a loud off-key enthusiastic voice, the whole walk. No extra score under it. Street air, footsteps, then the gags. TIMELINE 0-4s: [Tracking medium-wide, opening on image_1] He is already walking, already singing, mouth wide, chest out, a little strut. The camera slides with him. Daylight, grain. He is having the time of his life. 4-8s: [Tracking, he twists his torso toward the hydrant without stopping] He points two fingers at the red fire hydrant on the sidewalk. The hydrant cap blows and three hard jets of water blast out in different directions, high, violent, real water physics, mist in the sun. He keeps walking and singing, does not look back for long. Camera stays on him, hydrant geysers in the background. 8-13s: [Tracking, still singing] He keeps the strut. Water still arcing behind him. Pedestrians flinch at the spray. He grins, points at the sky on a lyric, never breaks stride. 13-18s: [Tracking as he passes a woman coming the other way] A woman in a knee-length dress walks toward him. As they cross, a sudden gust hits only her: the hem lifts a little, Marilyn sidewalk-vent style but modest, a brief flip then it drops. She grabs the fabric, startled. He keeps walking, still singing, a tiny glance, no contact. Camera never leaves him. 18-23s: [Tracking slows as he reaches a shop window] He stops in front of a big storefront glass, still humming. Leans in. We see him and his reflection clearly: bald head, beard, plaid, white tee. He studies himself, tilts his chin. 23-28s: [Held on him and the reflection] In the glass and on his body at the same time, the clothes change in one continuous morph: the flannel and tee become a sharp white open-collar suit, jacket, tailored trousers, a gold chain. No cut, no flash, the fabric rewrites itself. He checks the new look in the window, pleased, shoulders back. 28-30s: [Medium, still on him] He licks the tip of his index finger, taps it to his hip, and a little puff of white steam hisses off the fabric like a hot iron being quenched. He mouths the last "power," smug. Clip ends on that
Create a 15-second ultra-photorealistic vertical travel vlog with six fast candid shots, recorded on a small consumer compact camera from around 2010. It must feel like a real friend desperately trying to catch the last ferry, not a commercial.\n\nCHARACTER LOCK: One adult man in his late 20s, lean build, tan skin, short windblown black hair, faded coral overshirt over a white T-shirt, khaki shorts, worn navy sneakers, canvas backpack and one paper bag of takeaway food. Preserve his face, outfit, backpack, food bag and proportions throughout.\n\n0–2s — IMMEDIATE HOOK: The ferry ramp is already lifting as he bursts into frame sprinting down the harbor pier, waving one arm and clutching the food bag. The departing ferry and widening gap must be visible in the first frame.\n\n2–4.5s: Shaky camera runs beside him. His backpack bounces, wind hits the microphone and the food bag almost slips. A deckhand sees him and urgently lowers the ramp a final few centimeters.\n\n4.5–7s: Low angle at the ramp. He makes one believable forward leap across the small remaining gap, lands on both feet and stumbles safely against the rail without dropping anything.\n\n7–9.5s: The ramp closes behind him. He bends over catching his breath, checks the crushed food bag and begins laughing with relief while the camera struggles to refocus.\n\n9.5–12s: He walks onto the windy open deck. The harbor recedes behind him as gulls cross the sky and ropes vibrate against the rail.\n\n12–15s: Natural arm’s-length selfie. Still breathless, he opens the bag and reveals that the takeaway meal survived. He grins, turns the camera toward the island on the horizon and the clip ends abruptly.\n\nVISUAL STYLE: 9:16, early-2010s compact-camera video, imperfect stabilization, occasional optical micro-zoom, mild compression, clipped highlights on water, natural focus delay and cool coastal colors. No drone, gimbal, cinematic crane or polished advertising look.\n\nAUDIO: Harbor wind, footsteps, gulls, ferry engine, ramp hydraulics, bag rustle, breathing and natural laughter. No music, narration or scripted dialogue.\n\nCONSTRAINTS: One traveler, one backpack and one food bag only. Realistic running, jump distance, ferry motion and landing weight. No fall into water, injury, duplicated people, changing clothes, disappearing props, logos, readable signs, subtitles or watermark.
Main Subject: Young Spanish woman, 25, natural everyday appearance, shoulder-length dark-brown hair worn loose with slightly messy bangs, realistic skin texture, minimal makeup, relaxed after-work personality. Wearing a faded terracotta T-shirt, lightweight beige cardigan, high-waisted dark-blue jeans, worn white sneakers, and carrying a simple canvas tote bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Ordinary Madrid residential neighborhood on a warm weekday evening. Small local grocery shop, apartment buildings with balconies, parked compact cars, scooters, plane trees, tiled sidewalks, recycling bins, and residents returning home from work. No famous landmarks, tourist streets, or staged activity. Visual Style: Ultra-realistic documentary realism. Genuine everyday behavior, natural body language, spontaneous local interactions, authentic Spanish neighborhood atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting between shelves and her face, exposure pumping when entering and leaving the shop, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks down the residential sidewalk carrying an empty canvas tote. She checks a handwritten grocery list while approaching a small neighborhood shop. 00:03–00:06 Inside, she picks up tomatoes and oranges, comparing them casually before placing them into her basket. Autofocus briefly locks onto the colorful produce. 00:06–00:09 She chooses a loaf of bread and a carton of milk. The shopkeeper greets her from behind the counter, and she responds with a friendly smile. 00:09–00:12 Outside, she rearranges the groceries inside her tote while standing beneath a tree. A scooter passes slowly behind her. 00:12–00:15 She notices the camcorder, laughs softly, lifts the grocery bag as if showing what she bought, and continues toward her apartment. The operator follows for a few steps before accidentally pointing at the pavement and cutting to black. Audio: Natural ambience only–Spanish conversations, shop door bell, grocery bags rustling, footsteps, scooters, distant traffic, birds, apartment sounds, and light neighborhood chatter. No music. No narration. Goal: A forgotten MiniDV home video from 2004, capturing an ordinary after-work grocery run in Madrid–local, casual, imperfect, warm, nostalgic, and completely believable.
Create a highly photorealistic rural South Korean village in 1995, authentic and lived-in, with traditional homes, rice fields, misty mountains, vegetable gardens, stone paths, clay jars and period-accurate farming tools. 0–4s | Home: A young Korean woman in her early 20s wakes inside a modest traditional Korean farmhouse. Long dark hair in a simple low braid with a fabric ribbon. She wears an authentic 1995 rural outfit: loose cream cotton blouse, long muted-brown skirt, white ankle socks and simple canvas slip-ons. An analog clock shows 5:45 AM; an old radio plays softly. 4–8s | Window: She opens the wooden window. Misty rice fields and distant mountains glow in early sunrise. Her same friendly medium-sized village dog waits outside. 8–12s | Chickens: She walks outside with her woven basket, the same dog beside her. She scatters grain for chickens while passing traditional village houses, wooden fences and clay jars. 12–16s | Garden: She picks dew-covered fresh vegetables and places them in the basket. The same dog waits nearby. 16–20s | Village Walk: She walks along a quiet dirt-and-stone path with the dog beside her. She gently pats its head. Traditional farmhouse, firewood, clay jars and wooden fences surround them. 20–25s | Rice Fields: She and the dog walk between green-golden rice paddies. Misty mountains, birds and distant farmers create an authentic 1995 Korean countryside atmosphere. Subtle 35mm film grain and natural lens flare. 25–28s I Stream: She kneels beside a small wooden bridge and washes the vegetables in a clear stream. The dog waits beside her and looks curiously at the water. 28–30s | Home: She walks back toward the village with her basket, the same dog happily beside her. Warm sunlight fills the road as she looks toward the mountains and smiles peacefully. AUDIO: rooster calls, chickens, birds, gentle dog sounds, flowing water, wind, village ambience and faint old-radio music. STRICT CONSISTENCY: Same woman, face, braid, outfit, shoes, basket and same dog throughout. Dog must keep identical breed, size, fur and markings. NO: modern cars, smartphones, modern buildings, modern clothing, scooters, contemporary objects or post-1995 technology. CAMERA: ONE continuous cinematic take; no cuts, transitions, montage or time jumps. Natural handheld camera movement.
In a heartwarming home video style, a joyful toddler discovers music at a vintage piano. An adorable 2-year-old boy with curly dark hair, bright eyes, and a wide smile, wearing a white t-shirt and diaper, sits on a beige bench. He gently presses keys...
30s, 1080p, 9:16, nostalgic handheld home-video style, friend filming w/ old digicam. Korean woman (cream cardigan, sage blouse, jeans) buys groceries, bag rips on the walk home, apples spill, she laughs, stranger helps, bites an apple: "now we're safe." Natural audio only, no music/text/logo.\nUse exactly one reference image for the woman. Preserve her identity, face, skin tone, hairstyle, body proportions and wardrobe consistently.\n\nCharacter:\n\nYoung Korean woman, early 20s, cream cardigan, sage-green blouse, blue jeans, white sneakers, brown shoulder bag, silver earrings. Natural makeup, realistic skin and hair.\n\nStyle:\n\nCasual friend-recorded smartphone footage. Handheld, imperfect framing, autofocus shifts, natural exposure, slight motion blur/compression. Real Seoul neighborhood and morning light. No CGI, beauty filter or polished commercial look.\n\nREALISM:\n\nProgressive bag tearing, believable item weight and gravity, accurate hands, payment, walking and object continuity. No teleporting, duplication, disappearing objects, warped hands, extra fingers or wardrobe changes.\n\nAUDIO:\n\nNatural grocery store ambience, refrigeration hum, plastic bag rustling, footsteps, traffic, register beeps, payment sounds, rolling apple sounds, fabric movement and genuine laughter. No music, narration, subtitles, logos or watermark.\n\nVideo:\n\n00:00–00:04 — Grocery Store: She walks through a small neighborhood grocery store, picks up apples and eyes them, says, "These look fresh." Grabs a few items — apples, a carton of eggs, a bag of rice — and puts them in a plastic shopping bag.\n\n00:04–00:08 — Payment: She pays at the counter, thanks the cashier, picks up the full bag with both hands and heads out the door.\n\n00:08–00:12 — Drop: Walking down the street, the bag's handle slowly stretches and rips. An apple rolls out. She doesn't notice; the camera catches it.\n\n00:12–00:16 — Discovery: The sound behind her makes her stop. She turns, sees the apple and the torn handle. "Oh no…" She crouches down.\n\n00:16–00:21 — Chaos: As she lifts the bag, the eggs carton tips and more apples spill out. She catches one apple and chases another rolling toward the curb. She laughs nervously; the camera shakes naturally.\n\n00:21–00:25 — Help: A shopkeeper or passerby comes over with a sturdier bag. They gather everything together, double-checking the eggs are intact. She checks the bag's strength before standing.\n\n00:25–00:30 — Payoff: She walks away, pulls out one apple, takes a bite and smiles: "Okay… now we're safe." She glances at the eggs carton, relieved it survived. The camera operator quietly laughs. Cut naturally while moving.
Create a premium cinematic lifestyle advertisement using the provided reference image as the exact visual reference. Preserve the woman’s identity, facial features, hairstyle, outfit, blue lace clothing, white headscarf, daisy flower, pink vintage compact camera, proportions, and the beautiful wildflower meadow environment. Do not redesign or alter the subject. SCENE: A young woman is sitting peacefully in a sunlit field of white daisies during golden hour, holding a pink vintage compact camera. The atmosphere is warm, romantic, nostalgic, elegant and authentic, resembling a high-end lifestyle camera commercial. ACTION: Begin with a gentle cinematic push-in toward the woman as she looks naturally into the camera with a warm, confident smile. She slowly lowers the camera slightly from her face, revealing her expression, then looks down at the camera affectionately as if appreciating its design. She gently rotates the camera in her hands to showcase its pink body, compact form and vintage aesthetic. She then raises the camera back toward her eye, takes a photograph, and gives a subtle satisfied smile. Add a brief, elegant product-focused moment where the camera is clearly visible in her hands. Her movements should be natural, graceful and realistic, with delicate finger movement and subtle breathing. CAMERA DIRECTION: Start with a medium-wide shot and slowly dolly/push toward the subject. Transition into a smooth close-up of her face and the camera. Use a gentle cinematic orbit around her hands and camera. Finish with a beautiful close-up product shot of the pink camera in her hands while the background falls into creamy bokeh. LIGHTING: Warm natural golden-hour sunlight, soft backlighting, subtle lens flare, delicate rim light around her hair, realistic skin illumination, soft highlights and gentle shadows. VISUAL STYLE: Luxury lifestyle advertising, nostalgic analog photography aesthetic, dreamy editorial cinematography, premium commercial production, soft film texture, shallow depth of field, creamy bokeh, natural skin texture, realistic fabric detail, photorealistic, sophisticated color grading, subtle 35mm film character. MOTION: Natural human movement, realistic hand and finger articulation, subtle facial expressions, gentle hair movement from a light breeze, softly moving flowers and grass, physically accurate motion, smooth cinematic camera movement. PRODUCT PRIORITY: The pink vintage camera must remain visually consistent throughout the entire video. Preserve its shape, proportions, lens, buttons, colors and overall appearance from the reference image. Make the camera clearly recognizable and desirable without making it look oversized or artificially exaggerated. ENDING: End on a clean cinematic close-up of the camera held elegantly in her hands, with the woman softly out of focus in the background and warm sunlight creating a beautiful glow. Hold the product
Create a photorealistic 30-second 1990s multi-camera sitcom scene, 9:16 vertical, shot like genuine 35mm television footage. Bright cosy apartment, warm tungsten lighting, soft even fill, subtle film grain, evening blue dusk outside, authentic sitcom staging and natural audience laughter. A young man enters his apartment carrying groceries and freezes when he discovers 12 real cats having a “book club.” Cats are naturally scattered across the red sofa, armchair, rug and coffee-table area with open books nearby. His chubby white cat, wearing a backwards burgundy cap, rectangular glasses and red-black plaid flannel, sits proudly in the middle of the sofa. All cats must remain completely realistic four-legged domestic cats; only the white cat speaks, with a posh British accent. 0:00–0:05 Man stares around in disbelief. MAN: “No. Nope. What is THIS?” CAT: “Book club.” MAN: “Book club?!” CAT: “Every Thursday.” 0:05–0:11 MAN: “There are ELEVEN cats in my living room!” CAT: “Twelve.” MAN: “Where’s twelve—?” Another cat suddenly pokes its head naturally from his grocery bag. MAN: “OH, COME ON!” 0:11–0:17 Man points at the books. MAN: “None of you can even READ!” Dead silence. All cats gradually turn and stare at him naturally. MAN, suddenly unsure: “…Right?” 0:17–0:22 White cat looks over its glasses. CAT: “And yet, somehow… you’re still the dumbest one here.” Huge audience laughter. Man gives the camera an exhausted stare. 0:22–0:27 MAN: “That’s it! Everybody OUT! Book club is OVER!” CAT: “We took a vote.” MAN: “And?!” CAT: “You’re leaving.” 0:27–0:30 Doorbell rings. Man opens the door and finds another real cat sitting outside with a paperback gently held in its mouth. CAT, from sofa: “Oh good. That’s Margaret.” Man closes his eyes in defeat. Freeze frame with huge laughter, applause and a short upbeat 90s sitcom ending sting. Ultra-realistic physical set, natural human acting, genuine cat fur and anatomy, believable physics and imperfect feline movements. No CGI/AI look, anthropomorphic cats, human-like cat gestures, extra limbs, cartoon styling, futuristic elements, dark cinematic grading, subtitles, logos or watermark.
Create a 15-second Vlog-style home video of a Japanese middle school boy who is usually playful but becomes serious only during baseball practice, as if filmed by a teammate. 480p. The 15 seconds consist of a hard-cut montage of 7 short shots (approx. 2 seconds each). Each shot is a different moment, 1 shot = 1 small event. No transitions or fades. Since a close teammate is filming, he looks relaxed and natural. Main Subject: Same Japanese middle school boy throughout all shots. A refreshing, handsome boy. Thick, sharp eyebrows, large double-lidded eyes, straight nose, large mouth with upturned corners, sharp jawline. Realistic sun-tanned skin texture, showing white teeth when laughing. Short black hair. Wearing a white practice undershirt, muddy baseball uniform pants, baseball cap, and a well-used glove. Completely consistent face, physique, hairstyle, and clothing throughout. Location: Countryside middle school ground on a summer evening. Backstop, benches, white dust, distant mountains, and sunset. No ads or recognizable brands. Camera / Visual Style: Common for all shots: Handheld old consumer digital camera. Natural shake, imperfect framing, occasional focus hunting, exposure fluctuations, light motion blur, subtle noise, slightly muted colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (In order, approx. 2 seconds each, all hard cuts): 1. In front of the bench, posing strangely with a bat like a sword, trying to make the camera laugh. 2. Drinking barley tea in one go with his hat backwards, making an exaggerated face. 3. Going out to the field and fixing his hat to the front. His expression changes instantly. 4. Practice swing. Serious eyes in the evening light. Stopping perfectly in the follow-through pose. 5. Another swing. Sweat from his forehead drops to the soil. Silent. 6. Chasing a grounder, sliding catch in the dust. Not even a grin. 7. End of practice, returning to his usual smile and showing the ball in his glove to the camera jokingly. Midway, around 00:14, the recording suddenly cuts to blackout. No fade out. Physical Realism: Maintain realistic physics. Hands, fingers, feet, hair, sweat, bat, ball, glove, and dust behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing items, or sudden deformations. Bat swings and ball trajectories remain realistic. Keep the subject consistent across all shots. Audio: Natural ambient sounds only. Sound of bat swinging through air, ball hitting glove, footsteps kicking soil, cicadas, distant shouting. No music. No narration. No artificial sound effects. Final Mood: The transition between his playful face and serious eyes is the coolest part; a record of an ordinary day at club activities. Not a commercial work. Not a sports CM. Dedicated, youthful, nostalgic, warm, improvisational, and deeply human. Prioritize the feeling that the camera just happened to be there.
Use exactly one reference image for the woman. Preserve her identity, face, skin tone, hairstyle, body proportions and wardrobe consistently throughout. Format: 15s, 1080p, 16:9 Style: Ultra-realistic candid home-cooking footage, handheld smartphone or consumer camera style, as if filmed casually by someone in the kitchen. Natural imperfect framing, slight autofocus shifts, soft realistic grain, gentle handheld sway. No CGI, beauty filter, or overly polished commercial look. Warm natural kitchen lighting — soft daylight from a window mixed with warm indoor light, realistic exposure. Character: Young Korean woman, mid-20s, casual home outfit (oversized t-shirt or simple hoodie, apron loosely tied over it), hair tied up in a loose bun or ponytail, natural no-makeup look. Relaxed, focused expression, soft smile, easy unhurried movements. Setting: A cozy home kitchen — wooden countertop, a few pots and ingredients laid out, soft daylight coming through a nearby window, faint ambient sounds of chopping, sizzling, and kitchen background noise. 00:00–00:03 — Starting Prep She stands at the counter, tying her apron strings behind her back, glancing down at ingredients laid out in front of her — vegetables, a cutting board, a bowl. 00:03–00:06 — Chopping She picks up a knife and begins chopping vegetables with calm, practiced movements, occasionally glancing up with a small content smile, natural kitchen sounds in the background. 00:06–00:09 — Stirring the Pan She moves to the stove, stirring something in a pan, steam rising gently. She leans in slightly to smell the aroma, closing her eyes briefly with a satisfied expression. 00:09–00:12 — Tasting She dips a small spoon into the pot, tastes it, and reacts with a pleased nod and soft smile, wiping her hands on her apron. 00:12–00:15 — Plating She scoops the finished dish onto a plate, setting it down on the counter, stepping back slightly to admire her work with a warm, satisfied smile as natural light catches the steam rising from the food. now generatre this images face korian girl to natch this prompt start scene changes dress keep faces
Ultra-realistic 30-second, 1080p personal home-video, an ordinary autumn afternoon in the life of a young Korean woman, no reference image. MAIN SUBJECT: early 20s, realistic skin texture, minimal makeup, relaxed genuine personality. Dark-brown hair loosely tied back. Oversized cream knit sweater, blue jeans, white sneakers, small canvas shoulder bag. Same face, hair, and outfit held throughout. SETTING: quiet older Seoul residential neighborhood, cool autumn afternoon. Narrow concrete streets, aging brick houses, fallen leaves, parked bicycles, faded walls, small neighborhood shops. Lived-in and unplanned - no tourist spots, no visible brands. CAMERA: raw handheld footage from an early-2000s MiniDV camcorder, held by a friend. Autofocus hunting, exposure fluctuations, awkward zooms, mild tape noise, natural camera-handling imperfections. No stabilization, no gimbal, no cinematic choreography. BEATS: she leaves home, buys a roasted sweet potato from a street stall, burns her mouth and laughs about it. Keeps walking, notices a bike passing, waves at a dog. A leaf lands on her shoulder - she says Why me? and laughs it off. She sits on a low wall, finishes eating, watches the street in silence for a few seconds -camera just keeps rolling. She stands, walks off, turns back once -Are you coming? - then disappears around the corner as the tape cuts to black. AUDIO: wind, leaves on pavement, footsteps, bicycle bells, distant scooters, doors closing, subtle camera-handling noise. No music, no narration. Only the two lines above. STYLE: nothing dramatic happens on purpose. No posing, no exaggerated acting, no cinematic hero shots -realism comes from awkward laughter, imperfect framing, and dead air nobody bothered to cut. The moment she starts performing for the lens instead of her friend, the whole "found tape" illusion breaks. This one never does.
Create a 15-second Vlog-style home video of a junior high school girl in a brass band club in the countryside after school, filmed by a friend from the same section. The 15 seconds consists of a montage of 7 short shots (approx. 2 seconds each) with hard cuts. Each shot is a different moment, one shot = one small event. Do not use transitions or fades. Since it's being filmed by a close friend, she is relaxed and shows her natural expressions. Main Subject: The same Japanese junior high school girl throughout all shots. A beautiful girl with a sense of transparency. Large double eyelids that tend to droop slightly, eyelashes long enough to cast shadows when looking down, thin natural eyebrows, realistic skin texture that looks white and transparent, no makeup, a small straight nose, and thin cherry-blossom colored lips. A beautiful oval-shaped face. Her straight black hair is tied in a low ponytail. Usually has a modest and calm atmosphere. Wearing a white short-sleeved sailor uniform, a navy collar, a knee-length navy pleated skirt, and indoor shoes. The instrument is a well-used silver trumpet. The face, body type, hairstyle, uniform, and instrument must be completely consistent from beginning to end. Location: A music room in a rural junior high school after school in summer. Music stands, lined-up chairs, open windows, the school grounds and mountains outside. The evening light gradually deepens. No advertisements or recognizable brands. Camera / Visual Style: Common to all shots: An old handheld home digital camera. Natural shaking, imperfect framing, occasional focus hunting, exposure fluctuations, light motion blur, subtle noise, and slightly suppressed colors. No stabilization, gimbal, drone, slow motion, or cinematic lighting. Shot List (in order, approx. 2 seconds each, all hard cuts): 1. She enters the music room holding her instrument case, notices the camera, and waves shyly and small. 2. A close-up of her hands carefully polishing the trumpet with a soft cloth after opening the case. 3. Singing the melody to herself while making small notes in pencil on the sheet music on the stand. 4. Sitting with a friend, talking about something, and laughing while covering her mouth (no words audible). 5. The moment she holds the trumpet, her expression changes. A dignified and serious profile in the music room with the evening sun shining in. 6. A long tone. Eyes staring straight ahead. Voices from club activities in the distance outside the window. 7. After finishing the note, she breathes out and smiles bashfully at the camera. During that, at approximately 00:14, the recording suddenly cuts to black. No fade-out. Physical Realism: Maintain plausible real-world physics. Hands, fingers, hair, uniform, trumpet, and music stands behave naturally. No extra fingers, fused hands, distorted bodies, floating objects, disappearing objects, or sudden transformations. Instrument posture and finger positions remain realistic. The subject remains consistent across all shots. Audio: Natural environmental sounds only. Clear long tones of the trumpet, the sound of cloth rubbing, the sound of the pencil, distant voices of club activities, the sound of cicadas. No music (BGM). No narration. No artificial sound effects. Final Atmosphere: The record of an after-school session where you see both the modest girl and the moment she becomes a different person, dignified, when she holds her instrument. Not a commercial work. Not a music video. Quiet, dedicated, nostalgic, warm, improvisational, and deeply human. Prioritize the feeling that the camera happened to be there.