Architecture / Interior

@Image1 is responsible for the composition, clothing, and location. @Image2 is a three-view facial close-up sheet, responsible only for facial identity. The hairstyle, clothing, and location follow @Image1. A cinematic 15-second music video filmed in a [late-night supermarket aisle].

15-second realistic life short film, Reference-to-Video (R2V) driven. Use Image 1 to lock protagonist's identity: shoulder-length black curly hair, light blue hairpin, lavender knit cardigan, white top, indigo jeans, white canvas shoes. Use Image 2 to lock prop: large white plastic laundry detergent bottle with light blue cap. Scene: Daytime laundromat, narrow aisle, front-loading washing machine on the right, folding table in back. Cool white overhead lighting mixed with natural light. Style: 2000s home MiniDV, casually filmed by a friend. Non-professional composition, obvious handheld shake, slow panning, hunting autofocus, slight digital noise, faded low contrast. No stabilizers or cinematic moves. 00:00-00:03: Girl walks across aisle holding the bottle. Friend films from behind, camera starts on her shoes before tilting up. 00:03-00:06: She places the bottle on the machine and tries to unscrew the cap. It doesn't budge. She frowns. 00:06-00:09: She tries again with more force. The cap suddenly pops loose, she lurches back, taking a large step to regain balance. The bottle stays upright. 00:09-00:12: She pauses in shock, then breathes out in relief/embarrassment. Camera pushes in slightly too late/too far. 00:12-00:15: She places the cap on the machine and looks back at her friend with a wry smile. Camera tilts down toward her shoes and the bottle before cutting to black. Audio: Authentic laundromat ambient sounds, machine hums, plastic clicks, her short intake of breath, and the friend's muffled laughter in the distance. No voiceover or music.

A single continuous high-speed FPV drone shot, one unbroken take with no cuts, 15 seconds, 16:9. All three reference images show real locations, preserve their architecture, geometry, materials, colors and lighting exactly as shown, do not redesign or alter any structure. The camera is an aggressive wide-angle FPV racing drone with subtle natural motion shake, holding constant high forward velocity the entire time, no speed ramps, no slow motion. The shot opens skimming centimeters above [LOW FOREGROUND SURFACE: water, sand, rooftops, road, grass] in reference @/Image 1, racing toward [PRIMARY STRUCTURE], pulling up sharply and threading through [NARROW APERTURE: arch, gateway, gap, colonnade, canyon mouth] at full speed. Exiting, the camera bursts into the [LIGHTING CONDITION] of reference @/Image 2, banking hard right in a low arc across [OPEN GROUND: plaza, field, courtyard, water] and weaving between [PAIRED VERTICAL ELEMENTS : towers, spires, chimneys, rock stacks, trees], with [SECONDARY LANDMARK] sweeping past on the right. The camera then climbs steeply up [ELEVATED TERRAIN] of reference @/Image 3, spiraling once around [HILLTOP / SUMMIT FEATURE] in [LIGHTING CONDITION], before nosing over the far edge to reveal [WIDE PANORAMA BELOW]. Each segment keeps the exact lighting of its own reference image, with transitions hidden inside the aperture pass, the vertical weave, the crest and the dive. Audio is diegetic only: rushing wind, [AMBIENT LAYER 1], [AMBIENT LAYER 2], [FAINT DISTANT DETAIL] at the end. Photorealistic, real-world physics, no visible drone, no morphing or warped architecture, no text, no watermarks.

Create a cinematic 3D CGI time-lapse animation of a modern two-story townhouse complex being built from an empty dirt lot into a fully completed residential neighborhood. Show foundations, concrete columns, steel frames, walls, roof panels, windows, balconies, glass elements, wood accents, exterior paint, fences, and gates assembling rapidly with smooth transitions. Include scaffolding, fast-moving construction workers, paved driveways, green landscaping, and trees appearing in the final stage. Use realistic lighting, sunny skies, dynamic camera movements, high-detail architectural visualization, and an upbeat, energetic atmosphere with seamless construction effects in ultra-realistic 4K quality.

[Subject] Traditional Chinese Door God figure, holding weapons, with intricate armor patterns and a solemn, majestic gaze. [Scene] In front of the gates of an ancient mansion at night, red lanterns flickering slightly, Door God patterns painted on the door panels, one pattern per door, with paper slightly damaged and yellowed. [Camera Movement] Fixed surveillance perspective, with slight noise texture, simulating real security camera footage.

Create an ultra-realistic cinematic lifestyle video featuring the same young East Asian woman throughout the entire sequence. Maintain identical facial features, long soft ash-brown wavy hair, glowing skin, body proportions, and outfit in every shot. She wears a fitted white ribbed crop top, high-waisted blue denim jeans, white sneakers, and carries a cream canvas shoulder bag. Bright summer morning, modern Japanese neighborhood, premium beauty studio with elegant lighting, luxury makeup stations, large mirrors, realistic reflections, soft neutral interiors, and a relaxed lifestyle aesthetic. The video opens with her standing in front of her bedroom mirror, gently brushing her hair and applying lip balm before smiling at herself. She grabs her cream shoulder bag, phone, sunglasses, and keys before leaving the apartment. She walks through peaceful Japanese streets lined with cafés, flower planters, boutique stores, and vending machines. Smooth handheld tracking shots follow her while the warm morning sunlight filters through the trees and a gentle breeze moves her hair naturally. She arrives at a luxurious Japanese makeup studio where the receptionist warmly welcomes her. She meets the makeup artist, browses a makeup inspiration lookbook together, and they happily discuss a fresh, glowing natural look. She sits comfortably in the makeup chair while the artist gently prepares her skin using toner, moisturizer, and primer. Close-up cinematic shots capture soft makeup brushes, beauty sponges, glowing skin, delicate powder particles, and premium cosmetic products arranged neatly on the vanity. The makeup artist carefully applies foundation, blush, soft eyeshadow, eyeliner, mascara, highlighter, and a glossy lip tint using smooth professional techniques. She smiles naturally as the transformation progresses while the large vanity mirror reflects the elegant studio. The stylist lightly curls and smooths the front sections of her hair before adding the final finishing touches. She admires her glowing makeup from different angles, takes a mirror selfie, thanks the makeup artist with a warm smile, and leaves the studio feeling confident. Outside, she walks through the sunny Japanese streets with her fresh makeup glowing beautifully in the natural light. She pauses at a boutique window, catches her reflection, smiles proudly, then looks toward the camera and gives a playful wink before continuing her walk as the camera slowly pulls back to reveal the vibrant Japanese neighborhood. Natural ambient audio only: footsteps, city ambience, café chatter, soft conversations, makeup brushes, cosmetic bottles opening, powder brush sounds, hair tools, camera shutter, door chimes, birds chirping, gentle breeze, distant traffic. No background music, no subtitles, no logos, no watermarks, and no on-screen text. Premium commercial-quality cin

iPhone handheld shooting, authentic scene at the front counter of a budget noodle shop, third-person eye-level angle. Fully automatic camera: auto-exposure/autofocus/auto-white balance. Slight handheld shake + breathing sensation, occasional brief autofocus hunting, white balance adjusting naturally to warm yellow indoor lighting. Flat image, slight edge chromatic aberration, minor motion blur. No post-processing, color grading, filters, or effects. Natural ambient sound: noisy background, clinking bowls, distant chatter, faint radio music. Price list and dumpling posters on the background wall, 'hole-in-the-wall' texture. 0:00 Video starts. A male customer stands at the counter in profile, wearing a T-shirt and small earrings. Opposite is the landlady, wearing the outfit from image_20260720112517_1238_183, holding a large blue and white porcelain bowl of noodles. Camera is behind and to the side of the male customer at shoulder height. Handheld shake, breathing rise and fall. 0:02 Customer: 'Boss, why are there three prices for the small noodles?' Landlady looks up, raising an eyebrow. Camera still. 0:04 Customer points to the bowl: 'How much for that bowl in your hand?' Landlady: 'This? 8 yuan.' Casual tone. 0:06 Customer: 'And the 10 yuan one?' Landlady lowers the bowl, grabs a tiny pinch of scallions from the seasoning station, and sprinkles them in. She looks up expressionless. 0:08 Customer pauses: 'What about the 15 yuan one?' Landlady looks at him meaningfully, takes a pair of chopsticks, and picks up a large mouthful of noodles. 0:10 Landlady eats the noodles herself, chews, swallows calmly, then hands the bowl forward. Background music beat gets heavier. 0:12 Customer is stunned for a half-second, then his eyes light up. He lunges for the bowl, shouting: 'I want this one! I want this one!' Landlady smirks knowingly. 0:14 Customer holds the bowl like a treasure. Camera shake increases sharply as if the person filming is laughing uncontrollably. 0:15 Video ends on the exchange, still shaking. Natural environmental sounds throughout. No subtitles or watermarks.

Old VHS-style footage from inside an abandoned orbital station in the 1980s. The image is grainy, warped, with tracking lines, washed-out colors, and timestamp burn-in. The camera floats slowly through empty corridors, cables drifting in zero gravity, warning lights blinking silently. At the 2-second mark, the tape glitches and the corridor appears longer than before. A sealed airlock door opens by itself at the far end. The camera drifts closer, passing floating tools, old photographs, and frozen droplets of water. Final moment: the camera enters the airlock and reveals Earth outside the window ,but Earth is completely dark. Analog sci-fi horror, VHS noise, zero-gravity atmosphere, retro space realism, eerie silence, cinematic degraded footage.

Format: 16:9 Concept: "A Day Off in the Arcade" The entire video is a single continuous self-filmed vlog captured by the idol using a compact consumer camcorder. It should feel like genuine footage she'd upload privately rather than professionally produced content. The camera is always in her hand and never visible. Natural arm movement, occasional imperfect framing, realistic autofocus hunting, minor exposure adjustments, subtle walking bounce, and authentic human timing. No jump cuts or scene transitions. Visual Style Authentic early-2000s MiniDV look with soft detail, light digital noise, gentle highlight bloom, muted contrast, accurate skin tones, and slight tape compression. No cinematic color grading, no artificial blur, no beauty filters. Character JIWON, a Korean female idol in her twenties. Long black hair in a loose ponytail, natural makeup, warm smile, expressive eyes, casual oversized denim jacket over a simple T-shirt, relaxed jeans, sneakers, and a baseball cap. Location A lively retro arcade during the evening. Bright neon signs, claw machines, racing games, basketball arcade, photo booth, capsule toy machines, colorful carpets, cheerful background music, and other visitors naturally enjoying themselves. The recording begins just outside the arcade entrance. JIWON pushes open the glass door and laughs. "I promised myself I wouldn't work today... so this is today's mission." She slowly walks through the arcade, turning the camera to show rows of flashing machines and excited players. She stops in front of a claw machine filled with plush toys. "I've never actually won one of these." Holding the camera in one hand, she awkwardly controls the joystick with the other. The claw almost grabs a plush before dropping it. She bursts into genuine laughter. "That was definitely rigged." She wanders toward a rhythm game and watches someone playing. She quietly cheers for them before giving a thumbs-up when they finish. Next, she enters a small photo booth. The camera captures her fixing her hair while laughing at herself. A countdown begins. She quickly strikes a funny pose just as the photo is taken. Leaving the booth, she opens a capsule toy machine and twists the handle. The capsule drops. She excitedly opens it. "Actually... this one's kind of cute." As she continues exploring, she notices the arcade staff announcing that the venue will close in a few minutes. She looks around dramatically. "I think I lost track of time." Walking toward the exit, she turns the camera back to herself. The neon lights reflect softly behind her. "Days like this help me recharge. Next time I'll definitely win that plush." She smiles, waves goodbye, pushes open the arcade door, and steps outside into the cool evening air. The city sounds replace the arcade music as the recording ends naturally, as though she simply stopped filming after leaving. Generation Requirements One continuous uninterrupted take. Sta

00:00 – 00:02 The camera pans across the crowded mall atrium. People are shopping normally when loud crashing sounds echo through the building. The cameraman quickly zooms toward the opposite side of the ground floor where a giant crocodile, far larger than a normal crocodile, bursts into view, smashing through decorative displays and storefront entrances. Glass panels shatter realistically while people immediately begin running in every direction. Audio: Crowd gasps, breaking glass, terrified screams, footsteps, crocodile growls. 00:02 – 00:05 The crocodile charges through the mall at high speed, smashing display counters, toppling kiosks, knocking over mannequins, and tearing through store entrances. It lunges toward a clothing store, grabs a store mannequin in its powerful jaws, bites through it, and throws the broken pieces aside while continuing forward. Dust, shattered glass, and debris scatter across the polished floor. The camera shakes as the operator instinctively steps backward while continuing to zoom. Audio: People screaming: "Bhago!" "Arre bhaago!" Children crying. Loud crashing. Crocodile breathing and growling. 00:05 – 00:08 Hundreds of shoppers sprint toward escalators and exits. Some stumble while helping others escape. The crocodile accelerates through the atrium, weaving around pillars and broken kiosks, continuing to pursue the fleeing crowd without showing graphic injuries. Decorative walls crack as the animal's tail swings through storefronts, sending signs and merchandise flying. The camera operator struggles to keep the crocodile in frame while using digital zoom. Audio: Continuous panic. Someone shouting: "Security! Security!" "Neeche mat jao!" Echoing footsteps. Alarm sirens beginning. 00:08 – 00:10 The crocodile races toward another section of the mall as the crowd disappears into corridors and staircases. The camera zooms in one final time while shaking heavily. Broken glass, collapsed display racks, scattered shopping bags, and damaged storefronts fill the atrium. Dust hangs in the air as the crocodile roars and disappears around a corner, leaving the scene in complete chaos. Audio: People screaming. Store alarms. Glass continuing to fall. Heavy crocodile footsteps. Echoing roars. The cameraman breathing heavily in shock.

Main Subject: Young Korean woman, early 20s, natural everyday appearance, faded charcoal-grey sleeveless crop top, loose high-waisted light-wash jeans, black canvas sneakers, black cord necklace, black wavy hair in a messy side ponytail with wispy bangs. Realistic skin texture, minimal makeup, warm and approachable personality. Maintain identical identity, clothing, hairstyle, and appearance throughout. Weekend Cleaning Location: Small Korean home courtyard. 00:00–00:03 She sweeps fallen leaves from the concrete. 00:03–00:06 Camera accidentally frames only half of her while autofocus hunts. 00:06–00:09 She waters potted plants. 00:09–00:12 She wipes sweat from her forehead and laughs. 00:12–00:15 She carries the watering can inside as recording abruptly ends.

Vertical 9:16 aspect ratio, high-altitude overhead shot with realistic cinematic texture, warm twilight city light, slight atmospheric haze shrouding the city, 14mm wide-angle lens providing intense high-altitude pressure, natural shaking sensation of a handheld selfie stick throughout, urban skyscraper clusters filling the entire background, set in an extreme scene at the edge of a high-rise rooftop.

15 seconds. Japanese full-color anime. High-density 2D animation with a 500-million-yen budget scale. Detailed background art, smooth in-betweens, movie-quality cinematography processing. To keep the visual variety, develop appealingly by changing composition, camera angle, screen size, and character distance. No subtitles, no watermarks, no BGM. Ambient sound included. [Video Composition] After watching the end of an emotional movie, the water level in the room rises from the protagonist's tears. While crying, the protagonist continues to watch while floating on a swim ring; at the climax, the tears turn into a waterfall and flow out the window. Once the viewing is over, the water recedes and the room is dry as before. [Must include somewhere in Shot 5-7] As the end credits roll, the water recedes and all the drinks in the room have turned salty. Shot 1 (The Single Drop Hook): Long corridor of a karaoke shop. A single tear from the protagonist watching the end of an emotional movie falls to the floor with a sound like a pool dive. Expression with eyes full of tears. Shot 2 (Flooding): Tears won't stop, and the water level rises to ankles and knees. Slippers drift away like small boats. Protagonist stares at the screen while sobbing. Shot 3 (Continuation): Protagonist floats on a swim ring while continuing to watch through tears. Messily crying but eyes are glued to the screen. Shot 4 (Underwater): Camera goes underwater. Amidst floating daily necessities, wailing is heard from above the water surface. Sobbing with a trembling voice. Shot 5 (Breach): At the climax, tears become a waterfall and flow out of the window. A rainbow appears. Large tears falling in chunks. Shot 6 (Drying Up): The moment the viewing ends, the water recedes quickly. The room is mysteriously dry. The protagonist is still sniffing. Shot 7 (Aftermath): With bright red eyes, the protagonist blows their nose and says in a damp voice, "I'm watching it a second time."

Stylized anime haunted tea ceremony beat: an elderly woman pours tea inside an abandoned tatami room, steam rising from the cup and slowly forming the shape of a long-lost guest. Dust floats in golden afternoon light, paper doors rattling gently though no wind enters the house. Slow push-in across the floor, tea reflections rippling with impossible memories, the woman’s calm face mirrored in the porcelain cup. The ghostly figure leans closer and the silence holds one beat past comfort.

Hyper-realistic cinematic action sequence, 15 seconds, aspect ratio 16:9. Night. Inside a vast grand old library, one person runs through a towering maze of bookshelves while the building begins falling apart around them. The library is dramatic and atmospheric, with tall wooden shelves, rolling ladders, upper balconies, iron railings, chandeliers, reading tables, scattered books, dust, and warm firelight spreading through the space. Smoke thickens in the air as the danger grows. Wide opening shot: the person runs through the main library floor between towering shelves while fire spreads in the background. Sparks drift through the air, smoke gathers near the ceiling, and the upper balconies shake as the structure starts failing. Tracking shot: the person sprints past long shelves as one row begins collapsing behind them like dominoes. Books fly outward, ladders fall, and the collapsing shelves send dust and debris across the floor. The person keeps moving toward a staircase or balcony route ahead. Side shot: the escape becomes more dangerous. The person climbs a rolling ladder or narrow staircase to an upper balcony while another line of shelves crashes down below. The balcony shakes, a railing bends, and burning debris falls into the path. The person runs along the upper level, using the railing for balance. Final 5 seconds: the action becomes extreme. A section of the balcony ahead begins breaking apart while more shelves collapse below in a chain reaction. The person accelerates, crosses the unstable balcony, jumps to the final platform or doorway, lands hard, and pushes through the exit just as another row of shelves crashes down and firelight bursts behind. Final moment: the person reaches the safer exit corridor or outer landing while the burning library behind continues collapsing in heat, smoke, sparks, and falling books. Style: hyper-realistic, cinematic, fast-paced, intense, stressful, clear readable action, strong sense of danger and urgency, grand old library atmosphere, collapsing bookshelves, ladders, balconies, smoke, firelight, falling debris, dynamic but readable camera movement, no text, no logos, no cartoon style, no slow motion, no famous celebrity faces, no recognizable actors, no movie-star resemblance, no public-figure likenesses, no clear facial close-ups. Keep proportions. Keep style and features. Aspect ratio 16:9.

A futuristic luxury residential skyscraper floating on a massive rock above a dark cloudy sky, glowing with warm lights. The camera flies toward the twin towers as a transparent sci-fi HUD interface appears with digital data panels, graphs, and scanning reticles selecting a penthouse unit. A holographic window labeled “LUXUMY LOGON” opens, showing a luxury living room preview; a cursor clicks and the camera seamlessly zooms through the glass into the real penthouse interior. Inside, seven elegantly dressed guests relax on plush sofas with drinks, surrounded by floor-to-ceiling windows, a city skyline at dusk, warm lighting, a modern fireplace, and ultra-modern minimalist décor. Cinematic, futuristic, high-end architectural visualization, photorealistic.

A cinematic 10-second music video filmed in a dark modern dance studio with smooth grey reflective floors, black walls, and horizontal neon tubes. Continuous dynamic camera movements, primarily medium shots and close-ups, never pulling too wide. The female lead is always moving, with no frozen or static poses.

[Scene Setting] Early 1970s, Japan's National Diet, House of Representatives Chamber. A policy speech at an extraordinary session. Standing at the rostrum is a Prime Minister around 60 years old. Gray hair neatly parted 70/30, wearing a dark suit with a white pocket square and a legislator's badge on the lapel. He possesses a calm dignity and is answering questions grandly with a manuscript before him. [Lip-sync/Dialogue] Japanese, Male, 60s, a low, relaxed, and resonant voice. The heavy oratorical style characteristic of Showa-era politicians. Stretching word endings and pausing at punctuation. "The stability of the people's lives is the greatest mission assigned to politics. The government intends to exert its full efforts toward price stability and economic development." [Movement Instructions — Everyone on screen must move constantly. No static figures] - Prime Minister (Speaker): * Synchronize mouth movements accurately with the dialogue. * Head sways slightly while speaking, and shoulders move up and down with breathing. * At "it is the greatest mission," raises and waves the right hand in an emphatic gesture. * Looks down at the manuscript at sentence breaks, then raises his head to look forward. * Natural blinking frequency. - Background Legislators (Assign individual movements to everyone): * Legislator on the left: Flipping through materials and leaning forward to take notes. * Legislator in the center background: Nodding while whispering with the person next to them, changing head direction. * Legislator on the right background: Removing hand from chin, adjusting posture, and touching glasses. * Everyone continues breathing, blinking, and making subtle posture changes, ensuring no one is frozen like a mannequin. [Camera/Visual Style] - Bust shot from slightly below front. Not perfectly fixed; always include very slight drift and shake like a handheld broadcast camera. - 1970s NHK Diet broadcast style: Black and white, scan lines, film grain, flicker, and CRT-specific vignetting. [Audio] - Slightly muffled sound through a microphone, chamber reverberation. - Ambient sounds: Murmurs, paper flipping, throat clearing. - Sparse shouts of "No objection!" and distant applause occur at the end of the dialogue.