AI Video Prompts

Cinematic prompts for AI video generation — Seedance, MiniMax H3, Kling, Hailuo, Runway and more.

Explore AI video prompts with real generated clips. Every prompt is tested, tagged by model and style, and ready to copy into your video generator.

All Images Videos Audio

It must be obviously a computer-generated game cinematic, not live-action, photographed humans, cosplay, ordinary gameplay, 2D animation, or cel shading; all close-ups of characters' faces, hair strands, the giant's body, and the burning city uniformly use the same stylized realistic AAA game CG aesthetic. Story: In a dim basement, a long-haired young man with one eye wrapped in bandages shakes hands with a blond man; golden lightning pours out from the long-haired young man and passes through their clasped hands; the lightning engulfs the long-haired young man, and a massive golden lightning pillar strikes down from the stormy night sky onto the city; on a stage in a city square, a speaker in a gray long coat spreads his arms wide, the stage floor suddenly explodes, and a giant skinless muscular giant rises from the flames roaring; the speaker is swept up by the explosion, screaming as he is hurled into the air; the giant stands up amid the burning ruins, swinging its arms and roaring; finally, in slow motion, the speaker falls in front of the giant's glowing eyes and open maw. The entire film has no dialogue, no red blood splatter, no close-ups of wounds, no dismemberment. This is a fast-cut trailer-style montage, strictly 15 shots, with hard cuts or flash-white transitions along the timeline. "ACTIVE REFERENCES" No reference images; everything is built from text. Scene 1: A dim basement, wooden walls and door frame, a warm oil lamp is the only light source. Scene 2: A European-style city on a stormy night, with rows of brick and stone buildings and rooftops in the distance, the sky filled with rolling deep blue thunderclouds. Scene 3: A wooden stage in a city square, with tall dark red curtains hanging behind the stage and dark gray strips of cloth among the curtains. Scene 4: The burning ruins after the stage explosion, broken wooden beams, rubble, and brick walls, with flames, thick smoke, and flying sparks everywhere. "Identity Lock | Long-Haired Young Man" No reference image; fixed by text: an adult male about 25 years old, thin face, dark brown semi-long straight hair falling to his jaw and shoulders, one eye wrapped in white gauze bandages, the other exposed eye originally green but emitting golden light; a beige long coat. Ability: golden lightning belongs only to him — it pours from his body, hands, and exposed eye, glowing, crackling, and coiling around his whole body. Maintain the same face, same bandage, same hairstyle, and clothing throughout; lightning and strong light must not become a mask for face-swapping or deformation; he is the same person throughout, not duplicated. "Identity Lock | Blond Man" No reference image; fixed by text: an adult male about 27 years old, short blond hair, square jaw, light-colored eyes, old scars on his cheeks, red-rimmed eyes and tear tracks on his face; a beige coat. He has no abilities. Maintain the same face and clothing throughout; he is the same person throughout, not duplicated. "Identity Lock | Speaker" No reference image; fixed by text: an adult male about 40 years old, shoulder-length golden long hair, well-proportioned face; a dark gray high-collared long coat, belted at the waist, gray trousers. Maintain the same face, same hairstyle, and clothing throughout; he is the same person throughout, not duplicated. "Identity Lock | Giant" No reference image; fixed by text: a humanoid giant about 15 meters tall, body without skin, revealing dark red and orange tight muscle fibers, slender yet strong build; dark long hair on its head; both eyes emitting yellow light; a huge mouth that reveals a full row of teeth when opened; when appearing from flames and steam, its body gives off heat and fire. Always the same giant, bipedal, one head, one torso, two arms, two legs, not duplicated. "Space" Position tracking: the handshake takes place in the basement, with the blond man standing opposite the long-haired young man; in the city exterior, the lightning pillar strikes the rooftop of a distant building; the stage is located at the center of the square, with the speaker standing at the center of the stage; the giant bursts up from directly beneath the stage, its head and upper body rising behind the speaker; the speaker is thrown upward by the explosion and finally falls in front of the giant's face; the giant remains standing in the ruins at the original stage location. Rubble, flames, and ruins only accumulate, never reset. "First Frame" Close-up of the blond man's face, looking tearfully at the other in the dim basement, the warm light of the oil lamp shining on his face. "Timeline" SHOT 1 | 0.00–0.45 sec | Close-up of the blond man's face, tearful, heavy expression; CUT. SHOT 2 | 0.45–2.10 sec | Extreme close-up of the long-haired young man's exposed eye, half his face hidden in shadow, his green eye gradually lighting up, golden light appearing in the pupil; CUT. SHOT 3 | 2.10–3.75 sec | Close-up of the two shaking hands: the blond man's and the long-haired young man's hands clasped tightly, tiny golden lightning pouring from the long-haired young man's hand, crawling across their clasped hands, growing stronger, the image illuminated by golden light; CUT. SHOT 4 | 3.75–4.90 sec | Close-up of the blond man's face, illuminated by golden light, tear tracks clear, looking ahead in disbelief; CUT. SHOT 5 | 4.90–6.45 sec | Medium shot: the long-haired young man stands at the basement doorway, with the blond man's back in the foreground; golden lightning bursts from the long-haired young man's entire body, swirling around him, his long hair and coat blown up by the air current; CUT. SHOT 6 | 6.45–7.75 sec | Close-up of the long-haired young man's face, the entire face engulfed by golden lightning and intense light, the exposed eye emitting dazzling golden light; CUT. SHOT 7 | 7.75–8.50 sec | In two brief flash-white frames, a negative silhouette of a huge skull-like face appears, then golden lightning explodes across the image, filling it with intense light; CUT. SHOT 8 | 8.50–9.55 sec | City exterior wide shot: in the stormy night sky, a massive golden lightning pillar splits down from the thunderclouds, striking the rooftop of a distant building, the rooftop bursting with intense light; CUT. SHOT 9 | 9.55–11.10 sec | The camera rushes at high speed through exploding flames, flying wood chunks, and rubble, with sparks and lightning dancing across the frame; CUT. SHOT 10 | 11.10–14.20 sec | Medium shot of the square stage: the speaker in a dark gray long coat stands at the center of the stage in front of dark red curtains, gesturing as he speaks, one hand reaching forward, then at 14.00–14.20 sec spreading both arms wide; CUT. SHOT 11 | 14.20–17.70 sec | At 14.20–14.80 sec the stage floor violently explodes from below, with wooden planks, rubble, and flames shooting skyward; at 14.80–17.70 sec the upper body of a giant skinless muscular giant rises from the flames, arms spread, head tilted back, mouth wide open roaring, its whole body giving off fire and heat; CUT. SHOT 12 | 17.70–19.70 sec | Close-up with tilted composition: the speaker is swept up by the explosion, body tilted, golden long hair on fire streaming backward, mouth wide open screaming in terror, gray coat lifted by the blast wave; CUT. SHOT 13 | 19.70–21.70 sec | A massive dark silhouette sweeps diagonally across the lens, with sparks flying and light flickering in the frame; CUT. SHOT 14 | 21.70–26.90 sec | Wide shot of the burning ruins, camera shaking violently: the giant rises from broken beams and rubble in a half-crouch; at 21.70–23.80 sec it slowly straightens up, swinging both arms and roaring with its head tilted back; at 23.80–26.90 sec it moves through flames and thick smoke, pushing aside burning debris, one arm raised high, with several brief flash-whites in the frame; CUT. SHOT 15 | 26.90–30.00 sec | Slow motion: the speaker is hurled through the air, limbs spread, falling slowly, sparks dancing around him; the camera follows his fall, and behind him the giant's enormous face is gradually revealed — both eyes emitting yellow light, the open maw revealing a full row of teeth, roaring; at the end of 30.00 sec the speaker is still falling in front of the giant's face. "Physics" Lightning emits from the long-haired young man, travels along the clasped hands, glows, and illuminates surrounding surfaces. During the explosion, wooden planks and rubble are first lifted by impact force, then fall with weight; flames and thick smoke continuously surge. The giant has immense weight: the ruins are pushed aside as it rises, and the rubble beneath its feet trembles. The speaker falls under gravity after being thrown by the explosion; only SHOT 15 is slow motion, and the body still continuously falls, not hovering. The giant appears from directly beneath the stage and remains in the same ruins throughout. Rubble, flames, and ruins accumulate in one direction only. "Camera" The 15 shots are executed along the timeline: close-up, extreme close-up, hand close-up, close-up, medium shot, close-up, flash-white transition, city wide shot, rushing through flames, stage medium shot, explosion and giant rising, tilted close-up, dark silhouette sweeping past, ruins wide shot with handheld shake, slow-motion fall and the giant's face. The entire film uses the same virtual ARRI Alexa 35 and 35mm Cooke anamorphic lens; shot size changes are achieved only through camera distance and height. Only SHOT 15 is slow motion; the image briefly shakes during massive impacts; the camera never passes through characters' bodies. "Lighting/Color" Basement: warm orange oil lamp light and dark shadows, then washed pale by golden lightning. City exterior: strong contrast between the cold blue stormy night sky and the golden lightning pillar. Stage: dark red curtains and cold gray light. After the explosion: the entire frame is shrouded in orange-red and golden firelight, with several brief flash-whites amid thick smoke and sparks. The giant's muscles appear dark red and orange in the firelight, its eyes yellow points of light. Overall high contrast, fine grain, restrained bloom. "Sound" Background music is strictly prohibited: at no point in the entire film may background music, film score, music track, melody, rhythmic percussion, chorus, song, musical sustained tone, or tonal ambient bed be generated. Only diegetic audio synchronized with the image and physically belonging to the scene is allowed: ; ; ; ; ; ; ; . No dialogue, no narration, no intelligible shouted words, no songs, no subtitles; pulse sounds, orchestral hits, melodic sound design, or rhythmic sound effects must not be used to fill the absence of music, and impact or explosion sounds must not be arranged into drumbeats. The appearance of any background music or score is judged unqualified. music=0; no_music=1; strict_no_music=1; audio=diegetic_only; "Lock" The entire film has only four characters: the long-haired young man, the blond man, the speaker, and the giant; there are no other people. Long-haired young man: one-eye white bandage, dark brown semi-long hair, beige coat, golden lightning; blond man: short blond hair, cheek scars, tear tracks, beige coat; speaker: shoulder-length golden long hair, dark gray high-collared long coat; giant: skinless muscles, dark long hair, yellow glowing eyes, huge mouth. Characters never merge, swap faces, or exchange features; hands always remain normal five-fingered hands. No red blood splatter, no close-ups of wounds. The ending stops on the continuous motion of the speaker falling in front of the giant's face, without black screen, without fade, without end credits. Native full frame, no black bars, no on-screen text, subtitles, titles, readable markings, logo, watermark, interface, or watermark.

KAZEMIRU — WILD-WIND NIGHT HUNT — 5 SAMURAI Duration: 15s | 16:9 | No Music STYLE: Ultra-photorealistic REAL LIVE-ACTION, AAA Japanese dark-action cinema, restrained semi-CGI VFX. ARRI ALEXA 65, IMAX, Panavision anamorphic. Nighttime Edo Japan, cold moonlight, warm lanterns, deep shadows, mist, realistic atmosphere. @Image1 — STRICT IDENTITY LOCK: Preserve exact male face, facial geometry, white hairstyle, body proportions, torn-white outfit, tattoo, accessories and identity. Exactly ONE male Kazemiru, TWO real metal swords, FIVE adult samurai. Kazemiru ALWAYS remains a photorealistic real human male. COMBAT: Wild, aggressive, acrobatic anime-inspired dual-sword choreography translated into live action. BURST → CROSS-SLASH → PIVOT → REVERSE CUT → WEAVE → DOUBLE SLASH → RE-BURST. Both swords remain physical and clearly visible. ZERO idle, posing, waiting or neutral resets. SUPERSONIC WIND: Kazemiru physically crosses every distance; NO teleportation. Each short-range burst creates restrained emerald-green wind trails, subtle particles, air distortion, dust, leaves, bending lantern flames and realistic clothing reaction. LOCATION: Edo castle district at night: broad dirt road, wooden houses, stone walls, gates, tiled roofs, lanterns and trees. Five samurai surround Kazemiru. CAMERA: Strong 25–35° Dutch angle. Camera is always moving and intentionally slower than Kazemiru. Kazemiru moves first → camera reacts 0.1–0.3s late → whip-pan → overshoots → corrects → reacquires at contact. Use rear OTS, 3/4 tracking, aggressive side tracking and low-angle pursuit. NEVER static, floating or robotic. 00:00–00:03 — #1: Five samurai rush from different directions. Kazemiru bursts forward, air blast throws dust and leaves. Camera loses him, whip-pans, reacquires. He reaches #1 and delivers a brutal dual-sword CROSS-SLASH. Clear contact. #1 collapses. No blood/gore. 00:03–00:06 — #2: #2 attacks. Kazemiru weaves beneath the blade, redirects it with one sword and reverse-slashes with the second. Clear contact. He plants one foot on a stone wall and explosively pushes off. Wind and dust erupt. Camera overshoots toward #3. 00:06–00:09 — #3: Kazemiru flies into frame. Camera catches him mid-air. Real human body twists through a descending dual-blade attack. Both swords remain readable. Clear contact. He lands low and instantly bursts again. 00:09–00:12 — #4: Low Dutch tracking above dirt. #4 charges. Kazemiru weaves past by centimeters, pivots and performs two distinct reverse-slashes. Clear contact. Pressure wave throws dirt outward. Camera loses him and violently reacquires. 00:12–00:15 — #5: #5 searches desperately. Emerald wind crosses background. Kazemiru bursts from the side. He ducks the sword, rotates upward, redirects the weapon with blade one, then executes an opposite-direction CROSS-SLASH with blade two. Clear contact. #5 collapses. Kazemiru decelerates several steps away. Camera reacquires from rear 3/4. He looks toward more samurai entering the distant gate. Battle continues at 15s. AUDIO: Realistic sword clashes, compressed-air bursts, footsteps, dirt impacts, wind, clothing, lantern flames and Edo ambience. NO dialogue. NO music. NEGATIVE: female Kazemiru, feminine body, altered face, duplicate character, duplicate/missing swords, teleportation, clones, CGI human, anime rendering, plastic skin, static camera, robotic tracking, slow combat, floating, random contacts, missed attacks, meaningless spinning, giant green aura, neon VFX, blood, gore, wounds, subtitles, logos, watermark.

Create a deeply emotional, photorealistic cinematic short film about a woman grieving the loss of her beloved fluffy ginger tabby cat. On a gloomy rainy evening, inside a dimly lit apartment, the woman wearing a dark beige trench coat kneels beside an empty grey pet bed, gently picks up a red feather toy, holds it tightly against her chest, and begins crying as rain streaks down the window. Transition into warm, golden flashbacks showing her happiest memories with the cat: the cat approaching her on the couch for affection, playfully weaving between her legs in the hallway, happily playing with a feather teaser wand while she laughs, gently nuzzling the cat, and lovingly cradling it beside a sunlit window. Use warm sunlight, soft lens flare, shallow depth of field, and nostalgic golden tones for the memories, contrasting with the cold blue-gray lighting of the present. Suddenly return to reality as she breaks down in uncontrollable tears, then curls up on the wooden floor beside the empty pet bed, tightly hugging a white pillow or blanket while sobbing. Slowly pull the camera back to emphasize her loneliness, then shift focus to a framed photograph of the ginger cat in the foreground, leaving the grieving woman blurred in the background. End with the photograph in sharp focus as rain continues outside, creating a powerful feeling of love, memory, loneliness, and loss, with realistic facial expressions, natural tears, detailed cat fur, cinematic camera movement, subtle film grain, realistic lighting, 4K quality, and no text, subtitles, logos, or watermarks.

A sleek blue Porsche Panamera speeds along a scenic mountain road beside a vast lake before dramatically driving down a narrow track as giant walls of water part on either side. Dynamic cinematic close-ups highlight the car's spinning wheels, rear "Panamera" emblem, and Porsche hood badge while it hurtles through the parted sea and ascends a dusty cliffside trail. Reaching a circular lookout point high above the water, the luxury car drifts in a cloud of dust near an eagle perched on a rock face. A smiling woman in driving gloves winks from the driver's seat as the eagle takes flight into the open sky, leaving the Porsche parked at the summit overlooking the landscape.

Cinematic video of a young woman in an elegant white medieval dress opening large wooden doors from a dark castle interior to reveal a breathtaking sunny landscape with lush green fields a lake and distant mountains She runs out across the grassy field towards a large grand castle The camera follows her as she leaps into the air, gracefully floating into a magical fantasy sky filled with floating islands cascading waterfalls above clouds, and a large glowing pink moon in the surreal sky, 8k resolution, ultra detailed, cinematic lighting.

Create an explainer video about Odysseus’s journey in a claymation style. Use the Kling MCP and any helpful skills or rules available.

FORMAT: 16:9 landscape, 15 seconds, photorealistic live-action, cinematic lifestyle fashion film. CHARACTER CONSISTENCY: Use the uploaded character sheet as the master character reference. Keep the girl’s face, facial proportions, long wavy brown hair, hairstyle, hair clip, gold earrings, body proportions, burgundy pinstriped fitted shirt, wide-leg dark denim, and white sneakers exactly consistent throughout every shot. Do not change her outfit, hairstyle, age, or appearance. SHOT 1 — 0:00–0:05 A cozy rustic café in warm afternoon sunlight. The girl enters naturally carrying a small shoulder bag. Camera follows her from behind at waist height as her long wavy brown hair moves gently while she walks. She approaches a small wooden table near a sunlit window. Camera: smooth handheld tracking shot, natural movement, shallow depth of field. SHOT 2 — 0:05–0:10 She sits comfortably, crosses one leg over the other, picks up a simple white ceramic coffee cup, and takes a relaxed sip. Cut to intimate close-ups of her gold earrings, fingers around the cup, burgundy striped shirt, and flowing hair. Camera: subtle push-in, realistic handheld micro-movement, warm sunlight across her face and hair. SHOT 3 — 0:10–0:15 Side-profile shot as she looks peacefully toward the café window. She notices something outside, gives a tiny natural smile, then stands and walks toward the door. Final shot follows her from behind as she exits into warm daylight, her hair moving naturally. VISUAL STYLE Soft feminine lifestyle aesthetic, cozy European café atmosphere, warm beige and brown surroundings, natural sunlight, realistic skin texture, detailed hair strands, subtle film grain, authentic candid expressions, understated fashion editorial feeling. IMPORTANT: No exaggerated posing, no slow motion, no beauty-filter effect, no outfit changes, no face changes, no additional accessories, no cartoon/CGI appearance. Keep the performance natural and effortless. 16:9 LANDSCAPE • 15 SECONDS • PHOTOREALISTIC • CINEMATIC • NATURAL CAMERA MOVEMENT

Young Korean man, 24, naturally attractive, realistic skin, minimal/no makeup, medium-long dark hair loosely styled. Oversized maroon hoodie, loose casual pants, simple canvas shoulder bag. Preserve his exact identity, facial features, hairstyle and body proportions throughout. Quiet older Seoul residential neighborhood in the early morning: narrow street, pedestrian crossing, low-rise apartments, modest shops, bicycles, utility poles, parked cars and a softly glowing convenience store. Cool blue-gray daylight, warm window/storefront light, overcast sky, muted colors, slightly underexposed, peaceful and lived-in. Ultra-realistic early-2000s Sony MiniDV home video filmed by another person. Completely candid and unstaged. Natural handheld movement, subtle shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle digital noise and natural microphone noise. No stabilization or cinematic camera movement. 00:00–04: He walks casually toward the crossing, camcorder following a few steps behind. He slows at the curb. 04–07: He waits for the signal, adjusts his bag and looks down the quiet street. A distant car passes. 07–10: He opens his bag, briefly searches, takes out his phone and checks it. 10–12: The signal changes. He puts the phone away and steps forward. 12–15: He crosses at a relaxed pace. Halfway across, he briefly looks toward the camcorder with a tiny sleepy smile, then looks ahead. Natural audio only: footsteps, faint traffic, tires, fabric/bag rustling and quiet morning ambience. Smooth real-time movement, natural walking rhythm, realistic weight shifts and bag movement. Hair moves naturally in the light breeze. No stuttering, frame skipping, duplicated frames, excessive motion blur or artificial low-frame-rate effect. The moment should feel ordinary and spontaneously captured on an old camcorder. No dramatic traffic, posing or camera movement. The MiniDV aesthetic comes from authentic camera behavior and image texture, not artificial choppiness.

CAMERA/LOOK: DV 16mm tape camcorder POV, handheld/propped shots. Shaky framing, imperfect focus, clumsy zooms, occasional face cut-offs. Soft blurry tape quality, faint noise, bloomed gym lights, flickering exposure, muted contrast, realistic skin tones. Camcorder never visible. STYLE: Playful, self-deprecating gym vlog. Genuine strain, humor, quick energetic cuts, lighthearted rather than exhausted. CHARACTER: CHASE, Korean idol in her 20s. Long black high ponytail, glowing slightly sweaty skin, expressive eyes, slim athletic build. Modest long-sleeve athletic top, joggers/leggings, socks, no jewelry. SETTING: Evening gym mat area, nearby mirrors, water bottle on floor, soft overhead lighting, equipment in background. 15s / 6 CUTS: 1. (~2.5s) Propped medium shot. CHASE lies on mat, propped on elbows, sighing dramatically. "Okay, core day — my least favorite day." 2. (~2.5s) Plank, slight arm shaking, strained expression. "Why does this get harder every single time—" 3. (~2.5s) Crunches, breathing hard and complaining between reps. "Nobody warns you how much this actually burns." 4. (~2s) Macro close-up, shallow DOF. Hands grip mat during leg raises, abs visibly working. No dialogue, gym ambience. 5. (~2.5s) Handheld/propped shot. Finishes leg raises, flops onto mat laughing. "Okay— that's it, I'm done—" 6. (~3s) Arm's-length selfie while lying on mat, tired grin. "Core day never gets easier — see you guys tomorrow, hopefully."

Create a 15-second high-quality 3D animated family-friendly comedy sequence set in a cozy seaside fishing harbor town on a bright, breezy morning. Begin with a wide establishing shot of a colorful harbor lined with pastel houses, wooden docks, little fishing boats, hanging lanterns, crates of fish, lighthouse on the hill, and seagulls gliding overhead → reveal a cheerful curly-haired little boy in a yellow raincoat and blue boots sitting on a dock beside a giant silver fish on a wooden crate, while a jolly old fisherman with a big white beard and a captain's hat proudly shows off his catch of the day → transition into a smooth tracking shot along the busy dock as the boy skips between nets and barrels, the fisherman strolling behind him, townspeople waving and laughing → suddenly cut to a dynamic side shot as a mischievous baby pelican snatches a fish and waddles-flaps down the dock, past stacked crates and coiled ropes → transition to a fast playful chase as the boy and fisherman dash after the pelican across the harbor, dodging barrels and fishing nets while fishmongers and sailors turn to watch in amusement → cut to a dramatic low-angle shot of the fisherman tripping over a rope and spinning comically, the giant fish flying overhead against a bright sky of boats and flags → transition back to the dock where the boy sits happily on the crate, the pelican perched beside him, sheepishly holding the fish, as flags and laundry lines sway in the sea breeze → final shot becomes a warm wide-angle view of the boy and fisherman laughing together with the pelican between them, as the harbor, boats, lighthouse, and townspeople create a joyful, sun-drenched ending. Visual style: polished high-end 3D animated feature-film quality, expressive stylized characters, detailed facial expressions, realistic cloth, beard, and hair movement, vibrant seaside environment, soft golden morning light, sparkling water reflections, playful physical comedy, smooth character animation, detailed wood and fish textures, natural depth of field, dynamic camera movement, clean rendering, consistent characters and proportions throughout, family-friendly adventure-comedy atmosphere, 4K quality, no text, no subtitles, no watermark.

Create a cinematic, ultra-realistic 30-second live-action food sequence showing the complete preparation of crispy Korean-style glazed chicken in a warm home kitchen. Begin with an overhead close-up of raw chicken pieces being carefully cut into bite-sized chunks on a wooden cutting board. Transition smoothly to a stainless-steel bowl as the chicken is coated with a creamy white seasoned mixture, showing realistic hand movements and detailed food textures. Move into a dynamic close-up of the coated chicken being lowered into hot oil. Capture the bubbling oil, golden batter, steam, sizzling particles, and gradual transformation as the pieces become deeply golden and crispy. Use macro shots to emphasize the crunchy exterior and realistic frying physics. Cut to a dark pan as thick glossy red Korean-style sauce is poured in, followed by finely chopped garlic. Show the sauce slowly heating and bubbling, becoming rich, sticky, and glossy. Add the crispy fried chicken into the pan and toss it repeatedly with chopsticks until every piece is evenly coated in the vibrant red glaze. End with a beautiful close-up of the finished crispy chicken arranged on a white ceramic plate, covered in shiny red sauce and topped with sliced green onions and sesame seeds. Slowly push the camera toward the dish as the glaze catches the warm kitchen light, emphasizing the crunchy texture and appetizing details. Ultra-photorealistic cinematic live-action food commercial, realistic human hands, authentic Korean-style cooking, detailed food textures, crispy batter, bubbling hot oil, realistic steam and heat, glossy sauce, natural kitchen lighting, warm wooden surfaces, macro food photography, shallow depth of field, smooth camera movement, overhead shots, close-ups, realistic frying physics, rich colors, subtle film grain, appetizing presentation, physically accurate ingredients, 30 seconds, widescreen 16:9, no text, no logos, no watermark, no cartoon look, no plastic CGI appearance, no distorted hands, no artificial food textures.

30 sec | 16:9 | One continuous generation | English dialogue | No BGM | No subtitles STYLE: Ultra-photorealistic live-action premium smartphone commercial with the cinematic visual language of a coming-of-age movie. Real actress, real environment, natural practical lighting, subtle 35mm film grain, realistic skin texture, physically accurate reflections, natural handheld imperfections. The first half must feel like a movie scene, while the product is gradually revealed as the reason the moment exists. CHARACTER LOCK: YOUNG WOMAN from the provided reference image. Same actress throughout. Long messy wavy dark-brown hair, natural skin texture, grey fitted cropped T-shirt, black high-waisted jeans. Preserve her exact facial appearance, hairstyle, clothing, body proportions and styling from the reference image. Natural micro-expressions, subtle acting, realistic movement. PRODUCT LOCK: VELORA V1, fictional premium smartphone based exactly on the provided phone reference image. Deep burgundy metallic body, ultra-thin flat frame, minimal black dual-camera module, subtle silver "V" logo centered on the back, premium glass finish. Keep the exact same phone design, proportions, color, camera placement and logo throughout the entire video. No real-world smartphone branding. LOCATION: Outdoor rooftop terrace at blue hour. Deep navy evening sky with a faint warm pink horizon, distant trees and soft city lights. Weathered concrete ledge. Gentle natural wind. Quiet cinematic atmosphere. SOUND: Natural location sound only. Evening wind, distant traffic, footsteps, fabric movement, subtle breathing, realistic phone camera sounds and interface clicks. No music. STORY: The commercial begins as if it is a scene from a real movie. The audience does not immediately realize they are watching a smartphone advertisement. 00:00–05:00 — SETTING THE CAMERA Extreme close-up of a hand carrying the burgundy VELORA V1. The hand places the phone carefully on a concrete ledge. Close-up of the phone's burgundy metallic back catching the blue-hour light. The girl reaches toward the phone. She taps the screen. The front camera opens. The phone screen shows her live preview. She adjusts the phone angle slightly until the composition matches the provided girl reference image. She steps backward. A small realistic recording indicator appears: "REC 00:00" Camera remains fixed as if the phone itself is recording. 05:00–11:00 — THE REFERENCE PHOTO COMES ALIVE The recorded footage now becomes the main visual. Recreate the exact composition and appearance of the provided girl reference image: Low-angle perspective. Deep blue evening sky. Long messy wavy hair. Grey cropped T-shirt. Black jeans. Natural direct-camera expression. She stands still for a moment. A gentle gust of wind moves her hair naturally across her face. She looks directly into the front camera. She gives a tiny genuine smile. She quietly says: "Okay... this looks good." Natural autofocus subtly tracks her face. No beauty filter. No artificial skin smoothing. 11:00–17:00 — THE MOVIE MOMENT She stops posing. She looks toward the distant city. The wind becomes slightly stronger. She walks slowly away from the phone. The phone remains recording her from the ledge. The camera exposure naturally adapts as the sky gets darker. She stops several steps away. She turns back toward the phone. For a moment she simply looks into the lens. She smiles. Then she starts walking back. The scene should feel emotional and cinematic without exaggerated acting. 17:00–22:00 — PRODUCT FEATURE REVEAL She reaches the ledge and picks up the VELORA V1. Macro close-up of the phone in her hand. Her thumb touches the screen. The recorded footage appears. Show the exact moment from 05:00–17:00 playing on the phone screen. The footage looks sharp, cinematic and natural. She scrubs backward slightly.

Create a 30-second ultra-realistic fictional home-video featuring an adult Korean man in his late 20s spending a cheerful afternoon in an older Seoul residential neighborhood. CHARACTER: A fictional adult Korean man in his late 20s with medium-to-long dark hair tied in a casual low ponytail, natural masculine facial features, realistic skin texture and a friendly expressive personality. Keep his appearance consistent throughout the entire video. OUTFIT: He wears a bold, fashionable summer outfit consisting of a vivid red fitted T-shirt, high-waisted relaxed-fit white denim shorts, clean casual sneakers, a simple bracelet, small understated earrings and a small shoulder bag. The outfit is youthful, colorful and stylish, appropriate for a warm summer day. SCENE 1 — LEAVING HOME He steps out of an older Seoul apartment building carrying a small reusable shopping bag. He closes the gate behind him, notices the camera and gives a spontaneous smile before walking down the quiet residential lane. SCENE 2 — LOCAL BAKERY He enters a tiny neighborhood bakery, looks through the pastry display and chooses a small baked treat. He pays the shopkeeper with coins, thanks them and walks back outside. SCENE 3 — FRIENDLY ENCOUNTER While walking through the narrow lane, he suddenly sees his adult male friend approaching from the opposite direction. They smile, greet each other warmly and share a quick friendly hug. They chat and laugh for a moment before waving goodbye and continuing in opposite directions. SCENE 4 — FRUIT STAND He stops at a small roadside fruit stall and chooses a peach. He pays the vendor, places it inside his shopping bag and continues walking. SCENE 5 — EVERYDAY NEIGHBORHOOD MOMENT He walks beneath trees while eating his pastry. A bicycle passes nearby, and he naturally steps aside. He looks around at the quiet houses and smiles as the camera follows him from a short distance. SCENE 6 — ENDING He reaches the end of the lane, turns toward the camera and gives a cheerful wave. He smiles naturally and says, “Bye bye!” He then turns around and walks away down the residential street while carrying his bag and peach. The camera stays behind him until he disappears around the corner. CAMERA STYLE: Authentic early-2000s consumer MiniDV home-video footage. Handheld camera shake, imperfect framing, autofocus hunting, automatic exposure fluctuations, soft digital detail, mild digital noise, slight compression artifacts, realistic motion blur and occasional awkward zooms. It should feel like a genuine recording made by a friend or family member, not a professional production. AUDIO: Only natural neighborhood sounds: footsteps, bicycles, distant traffic, bakery activity, casual conversations, birds, children playing and light wind. No music, no narration, no subtitles, no text overlays, no beauty filter, no sexualized posing, no CGI appearance, no cinematic lighting and no polished commercial cinematography.

All facial close-ups, cavalry, flying mounts, and giant beasts use the same set of high-end pre-rendered AAA game CG aesthetics; skin maintains digitally sculpted forms and controlled subsurface scattering, never turning into live-action photography, cosplay, ordinary gameplay, 2D animation, or cel shading. Use a cinematic montage with clear cuts, including character reveals, cavalry charges, aerial sweeps, and two sides approaching; do not change it to a single continuous take, and do not add extra close-quarters combat or victory/defeat endings without buildup. Environment and space: an open, dry ochre-yellow battlefield with rolling low hills, trampled golden dry grass, brown earth, horse-hoof dust, and dense distant army formations; on one side is a huge low golden-white sun with thick amber clouds, on the other side are deep cyan-blue storm clouds and a bright cyan mist band on the horizon. Maintain a unified color palette of warm amber sunlight, burnt ochre earth, gunmetal armor, and cold teal storm; lighting is directional, and faces and dark armor remain readable. The giant beast and the closed-helmet commander are on the storm-army side; the female swordswoman, axe-wielding warrior, the two running shoulder-to-shoulder, cavalry, and white flying riders advance from the sunlight side toward the storm side. Ordinary soldiers, horses, spears, and dry grass in wide shots always provide scale reference for the giant beast. The mist band is volumetric, churning cloud-fog and does not turn into a portal or explosion on its own. Fixed character A, red-eyed iron-masked commander: a tall adult masculine warrior, always wearing the same fully enclosed dark gun-gray helmet, two red points of light within a narrow eye slit, a vertical grille mask, a dark red neck scarf, black iron layered breastplate, silver-gray worn edges, and outward-projecting spiked pauldrons; his face is never revealed. Fixed character B, red-cloak axe warrior: another independent adult male, exceptionally broad and strong, short black hair swept back and standing up, a square sculpted face, thick brows, and a tight jaw, never wearing a helmet throughout; black heavy plate armor with thick silver edging, round rivets, and huge shoulder spikes, a long deep-red cloak fixed to his shoulders and back, his right hand always gripping the same long-hafted wide-bladed double-sided battle axe. A and B never swap appearances; B is not what A looks like with the helmet removed. Fixed character C, braided female swordswoman: an adult woman, lean athletic build, warm light skin tone, chestnut-brown side-swept bangs and one long thick braid, her face a clearly refined game CG character; silver-gray segmented breastplate and pauldrons with warm gold reflections, a dark scarf, dark form-fitting combat underlayer, blue-black segmented waist skirt, leg guards, and combat boots; her right hand holds only one straight-edged silver longsword, with unchanging length, guard, and grip. Fixed character D, shoulder-carrying runner: an adult male, warm brown skin, upward-standing dark short hair, brass goggles pushed onto his forehead, teal-brown sleeveless combat tunic, leather straps, and arm guards; he keeps his torso stable while carrying a companion on his shoulders, and his arms swing naturally with running. Fixed character E, shoulder-mounted artificer: a small but clearly adult blonde woman, short messy blonde hair, forehead goggles, brown leather clothing, and a small amount of teal-green mechanical trim, always seated on D's shoulders; her left hand holds the same palm-sized dark spherical device with bright yellow-green ring patterns on its surface, her right hand steadies herself on D's shoulder to keep balance, and the sphere is never thrown or exploded. Fixed character F, flying rider: an adult rider, deep blue-purple hood and cloak, dark light armor, seated in the saddle on the back of a white-feathered flying beast, both hands holding the reins. Fixed giant beast G, crystal-crowned white-winged tiger: a massive quadruped feline creature, broad tiger face, thick white cheek mane, ice-blue eyes, long sword-like fangs, continuous dark gray-blue stripes on white fur, a red diamond-shaped crystal in the center of its forehead, a row of tall pink-to-deep-red crystal spikes along its shoulders and back, and one huge white feathered wing on each side; body, four legs, wing roots, and crystal spikes are always physically connected. Its shoulders and back are far taller than ordinary cavalry, its spread wings span a large number of soldiers, and it does not shrink into an ordinary tiger after a cut; it carries no rider. Fixed flying beast H is a different creature: curved black beak, red eyes, fluffy white feathered head and neck, broad feathered wings, a slender white tail, and folded clawed feet, carrying F on its back; it does not grow a tiger face, sword fangs, or a red back crystal crown. A small number of the same kind of flying riders accompany in the distance, changing size with distance. The cavalry are each independent adult warriors, silver-gray metal armor, blue cloaks or crests, riding brown and dark armored warhorses, carrying physical spears or longswords, with individual movements staggered, not cloned, not uniformly synchronized. 0.00–2.00 seconds: immediately use a low-angle medium-wide shot passing through black tattered-banner-like shadows and brown dust streams sweeping across the foreground; A stands at the center front of the army formation, and behind him the silhouettes of spears and soldiers gradually become clear. The camera slowly pushes forward, dust mist parts behind him, and G's massive white tiger face leans in from the upper background, ice-blue eyes revealed; A occupies only a very small area below the giant beast's face, A and G are two separate entities front and back, and the giant beast is not morphing out of his body. 2.00–4.00 seconds: cut to a close-up of G's head and neck; the giant beast raises its head, opens its massive jaws, and lets out one deep non-verbal roar, with sword fangs, tongue, and lower-jaw structure clearly visible. The camera rapidly pulls back to a wide shot as G's two wings fully spread from a folded state to both sides, feather segments opening in sequence, the wing roots driving the shoulders and back, wind pressure stirring the dust stream at its feet; A and rows of ordinary soldiers are in the lower foreground, maintaining the massive scale. The red crystal spikes move with the back, do not float, and do not emit extra energy. 4.00–6.50 seconds: hard cut to a frontal close-up of C from the chest up, with the golden-white sun and thick clouds behind her; her right arm is already extended upward, her right hand raising the silver longsword high, gazing firmly forward, her thick braid and blue-black waist skirt blown by the wind. The camera rapidly pulls back along the same axis to a full-body wide shot, revealing her stance with both feet planted firmly; multiple cavalry riders charge continuously from behind her on both left and right sides toward the camera and graze past the foreground, horse hooves kicking up dust. C maintains the sword-raising rallying pose, the cavalry genuinely charge forward, they must not stand as a static corridor, and they do not crash through her. 6.50–8.50 seconds: cut to a side-front tracking shot close to horse-chest height; three to four armored warhorses run staggered in parallel in the near foreground, with more cavalry continuously closing in behind; the camera retreats at high speed and moves laterally, capturing horse legs alternately striking the ground, riders rising and falling with the horses' backs, and blue cloaks whipping backward. The nearest rider lowers a long-hafted wide-bladed war spear forward, the spear blade sweeps across the front of the frame but strikes no target, the reins remain connected, and horse armor and saddlery stay fixed. Distant scenery moves slowly while nearby horse heads and weapons sweep past quickly, creating strong parallax. 8.50–10.60 seconds: cut to a low-angle half-body shot of A from the side-front; he is still on one side of the army formation, iron mask and red eyes facing the direction of the incoming attack, infantry running past behind him. G advances continuously from behind him from screen-right to screen-left, its massive tiger face, shoulders and back, and front legs passing by his side in sequence; the camera follows the giant beast moving left, A gradually exits the frame edge, G opens its mouth and bares its teeth, front feet landing and pushing dust aside. G passes by A rather than attacking A, and the giant beast's size and stripes are exactly the same as before. 10.60–12.60 seconds: cut to a low wide shot from behind B, his broad shoulders and deep-red long cloak forming the foreground, his right hand planting the long-hafted battle axe at his right side, knees bent and body lowered to face forward. G approaches B from the distant center with wings spread, front paws extended, hind limbs pushing off the ground, the distance continuously shortening along the ground; the red cloak spreads in the wind, the battle axe always connected to the right hand. This shot shows the threat approaching and B's preparation, cutting away before the two sides truly make contact, without凭空 adding axe-swing hits, falls, or injuries. 12.60–14.00 seconds: cut to an oblique tight close-up of B near his pauldron, composition with a slight tilt, the thick pauldron occupying the foreground; he lowers his head, then raises his gaze to stare forward, eyes tightening, a brief stubborn teeth-clenched expression appearing at the corner of his mouth, then his jaw tenses. The short black hair, square face, and the back view from the previous shot belong to the same helmetless warrior, and the face maintains a digitally sculpted AAA game CG texture, not turning into a live-action actor. 14.00–15.60 seconds: hard cut to a frontal low-angle bust shot of A, restoring the closed iron mask, dark red neck scarf, and red eyes, with thick dark clouds behind him. Several orange-white blazing fire bodies with long red-orange trails streak across the high background along different diagonal lines, passing in sequence rather than as one synchronized row; localized warm light sweeps across the edges of his armor plates. A maintains an imposing standing pose, the camera pushes in slightly, he does not raise a hand to cast spells, and the background fire bodies are not changed to emit from his eyes or body. 15.60–19.10 seconds: cut to an extremely wide aerial tracking shot with a clearly tilted horizon, below which a large mass of cavalry is galloping in the same direction across the ochre plain. F riding H sweeps in from the distant upper area, the camera flies alongside it at high speed from the side, clearly seeing the black curved beak, red eyes, fluffy white feathers, and the blue-purple-hooded rider leaning low and holding the reins. H banks with tilted wings, one broad feathered wing sweeping past the camera and briefly blocking the view; the camera follows through to behind it, the slender white tail sweeping out of the foreground as the mount flaps forward. The camera lowers to a position above and slightly behind the cavalry and gradually levels out, the herd continuing to run below, several white-feathered flying riders gliding above at different depths, ahead a large area of glowing cyan-blue storm mist band and distant black army formations. The flying rider's ascent, turn, and wingbeats are connected, it does not transform into a winged tiger, and no cut is used to make the mount teleport. 19.10–20.90 seconds: hard cut to a low retreating shot of G from front-side; the crystal-crowned white-winged tiger charges heavily toward the camera on all four legs, front paws bearing weight on the ground before hind legs push off, the body visibly rising and falling with the gait, the white feathered wings spread and beating with the charge to balance the massive body. It opens its mouth and roars, the red back crystals, blue eyes, and gray-blue stripes are clear, dust rolls backward from the actual footfalls; the camera retreats fast enough to keep the head, chest, and front paws readable, not letting it slide frictionlessly on the ground, and not filming it as a bird-headed flying mount. 20.90–23.10 seconds: cut to a medium close shot of them running side by side, C on screen-right, right hand holding the same longsword diagonally upright beside her right shoulder as she runs forward, gaze focused ahead; D runs in from screen-left, E always seated on his shoulders. D steps on the ground, torso leaning forward, arms swinging naturally with the run, E's legs straddling D's shoulders steadily, rising and falling with the stride and using her right hand on his shoulder to keep balance. E excitedly raises the green-ringed sphere in her left hand, briefly pulling it back beside her ear and then raising it outward and upward, the sphere remaining in her left hand the whole time, never released and never thrown. The camera moves in sync from their front-side, cavalry and flying riders behind continue to press forward, the three have independent bodies, hair, and equipment, do not share arms, do not turn into other characters, and have no speaking mouth shapes or intelligible dialogue. 23.10–26.00 seconds: cut to a tight frontal close-up of B and rapidly pull back to a medium-full shot; he advances with strides at the front of the army, short black hair, red cloak, and massive black iron pauldrons maintained. B raises the same battle axe with his right hand above his shoulder, body leaning forward, lets out one short non-verbal battle cry, then accelerates charging toward the camera, companions behind immediately following. The axe-wielding arm has weight, the axe haft does not extend or retract, raising the axe is leading the charge rather than swinging at empty air; B grazes past one side of the camera, his red cloak pulled up by inertia and sweeping across the entire frame, using real cloth occlusion to complete a wipe transition. 26.00–29.40 seconds: as the cloak leaves the frame, reveal a ground-hugging rear tracking shot; the camera follows behind B and his companions over golden dry grass, the cloak still connected from the near upper-left to his shoulders and back, forming a huge red arc in the foreground. B runs with the axe in the mid-front, C passes through the near-left foreground, her right-hand longsword held diagonally downward and avoiding companions; D with E on his shoulders runs on the right, and another adult companion carrying a long tube firearm at his side follows farther in the center but does not fire. Ahead, G faces them with white wings spread, the red crystal crown clearly emerging from the cyan-blue storm clouds and dust band, dense army formations arrayed on the horizon behind. The characters' forward motion is driven by boots pushing off the ground, the camera follows behind, they must not run backward or slide along the ground. The final approximately one second gradually slows into a poster-like confrontation composition, with the giant beast's wings, cloak, and dust still slightly moving, the two sides not yet colliding; do not add killing blows, explosions, or a victory ending. 29.40–30.00 seconds: continuing the same confrontation composition, a brief image-shattering transition begins from the lower-right edge of the frame, a small number of white-gray and original-picture-colored triangular shards flipping outward, gradually extending across the image surfaces of the dry grass, sky, and cloak, ending at 30.00 seconds at the moment when the shards have spread but the battlefield is still recognizable. This is a graphical transition of the cinematic image itself; character bodies and the real battlefield do not shatter or dismember, and no title, logo, menu, subtitles, or black end card appear. Action, camera, and continuity: character reveal shots are short and clear, cavalry and winged tiger charges are fast natural movements, flying riders sweeping past the camera maintain continuous trajectories, only the final confrontation composition slows slightly, and no extra ultra slow motion heavy impacts or full-film slow motion are added. The montage may switch between both sides' perspectives, but each time a character reappears their unique identity must be restored, and different faces must not be regenerated due to front view, back view, low angle, or close-up. A is fully helmeted with red eyes throughout, B is short black hair and exposed face with one battle axe throughout, C is chestnut-brown braid and one silver sword in the right hand throughout; D and E are always two people, E only on D's shoulders, the mechanism sphere only in E's left hand; H carries F on its back, G has no rider, and the tiger-faced blue-eyed red-crystal winged tiger and the bird-beaked red-eyed white-feathered mount are never mixed. Swords, axes, reins, and saddlery always have clear grip or fixation points, with no extra weapons, duplicated limbs, armor plates merging into skin, clipping through people or horses, or weapons switching hands without reason. Faces, giant beast fur, and wings all maintain the same set of refined AAA CG asset texture. The army continuously runs, closes in, and raises dust; do not let only the protagonists move while the background army stands still and makes way; dust streams follow real footprints, cloaks and hair lag behind acceleration, and the giant beast's weight affects its footfalls but does not without reason shatter the entire ground. Strictly prohibited background music: at no time in the entire film may background music, cinematic score, music tracks, melodies, rhythmic percussion, chorus, songs, musical sustained tones, or tonal ambient beds be generated. Only diegetic audio synchronized with the image and physically belonging to the scene is allowed: strong plains wind, flapping banners and cloaks, friction of armor plates and leather, dense but unsynchronized horse hooves and combat boots on earth, slight saddlery sounds, heavy footfalls and non-verbal roars of the winged tiger, wordless breathing and short exertion shouts of riders and warriors, massive wingbeats, air sound of close flybys, distant howling of high-altitude fire bodies, and sounds of sand and dry grass being stepped on. Near and far volume changes with camera distance, wind pressure increases when near wingbeats block the lens, and when the red cloak brushes the lens there is only real cloth rustling; the final image shattering still retains battlefield sound, without adding glass explosions or musical impacts. No dialogue, no narration, no intelligible shouted words, no songs, no subtitles; do not use pulsing sounds, orchestral hits, melodic sound design, or rhythmic sound effects to fill the absence of music, and do not arrange horse hooves, footsteps, roars, or impacts into drumbeats. The appearance of any background music or score is judged unqualified. music=0; no_music=1; strict_no_music=1; audio=diegetic_only; No readable text, emblems, brand logos, player controls, interface, or watermark throughout the film, no blood, no open wounds, no dismemberment.

Cinematic Korean fantasy action scene in a bright, slightly worn high-school cafeteria. Students in dark navy uniforms sit at long metal tables with green stools, eating from compartment trays under fluorescent lights and spinning ceiling fans. A quiet, elegant young woman with long black hair in a traditional pale-blue and white floral hanbok walks down the aisle carrying a metal lunch tray. Her expression is calm and distant. A male student in a uniform and dirty white sneakers casually trips her. She stumbles, the tray flies, food and red sauce splash. She catches herself with one hand on the floor. She rises slowly. Cherry-blossom petals begin to drift through the air. A glowing teal mark appears on her cheek. Her hair falls loose. She draws a luminous teal energy blade that trails light and petals like a mix of lightsaber and spirit sword. She moves with sudden, graceful violence. She kicks a red-haired boy across the room; he slams into tables. She slashes, sending students flying, trays spinning, steam and petals exploding. A glowing arc of teal energy cuts through the air. She launches another boy so hard he crashes through a wall, leaving a jagged hole of daylight and dust. The floor cracks. Windows shatter. Other students keep eating or freeze in shock while she walks the aisle like a ghost in silk. Close-ups: her cold, beautiful face; the blade passing an inch from a boy’s chest as petals swirl; her hand pinning hair with a jade hairpin after the fight. Wide shots of the ruined cafeteria, two boys face-down on the cracked floor, her walking away in the flowing hanbok as dust and petals settle. Style: high-end K-drama / webtoon live-action, 24fps cinematic, shallow depth of field, warm-cool contrast, slow-motion on impacts and fabric, floating cherry blossoms, glowing teal VFX, grounded school lighting mixed with supernatural energy. Mood: quiet girl, loud consequences. You picked the wrong battle.

A cinematic K-drama-style heartbreak scene in a luxurious modern apartment at night during heavy rain: an East Asian woman in a beige trench coat enters happily carrying a gift bag, but her smile disappears when she sees her partner in a white shirt embracing another woman in a black silk dress inside the bedroom. The bag falls as she freezes in shock, followed by emotional close-ups of her tear-filled eyes and trembling face. The man looks guilty and reaches toward her, but she turns and runs out, slamming the door behind her as he desperately follows. Moody blue-and-warm lighting, realistic acting, dramatic atmosphere, 35mm cinematic lens, shallow depth of field, slow-motion emotional moments, photorealistic 4K film quality.

Create a high-quality cinematic 3D animated short film featuring adorable, stylized baby otter-like woodland creatures in a beautiful sunny meadow. Scene 1: A cute brown baby otter stands in a lush green meadow, happily holding a large shiny blue berry with both paws. It has soft brown fur, a round chubby body, huge glossy black eyes, rosy cheeks, and a tiny dark scarf around its neck. The character looks innocent and curious. Warm morning sunlight, soft grass, rolling green hills, tall trees, blue sky, cinematic depth of field. Scene 2: The blue berry slips from the otter's paws and rolls quickly down a gentle grassy slope. The little brown otter runs after it, trying desperately to catch it. The camera follows the rolling berry with a smooth dynamic tracking shot while the otter runs behind it. Scene 3: The berry rolls toward a large hollow fallen tree trunk lying in the meadow and stops near its entrance. The brown otter reaches the tree and looks around curiously, wondering where the berry went. Scene 4: The camera moves upward through the surrounding trees toward the bright sunlight shining through the leaves. A magical, peaceful atmosphere fills the scene with glowing sun rays, floating dust particles, and gentle wind moving the leaves. Scene 5: A second adorable baby otter appears — smaller and gray-colored, with soft gray fur, a round chubby body, huge expressive black eyes, rosy cheeks, and an innocent expression. It comes out near the fallen tree and notices the brown otter. Scene 6: The gray otter and brown otter interact playfully near the hollow tree. They look at each other with curiosity and surprise, then move around the tree together. Keep their character designs consistent throughout the entire video. Scene 7: The gray otter climbs onto a nearby tree branch and looks around. The camera follows from behind and slightly below, showing the bright green forest canopy and warm sunlight filtering through the leaves. Scene 8: The gray otter rests against a large moss-covered rock, looking sleepy and exhausted. Its eyes become heavy as it relaxes in the warm sunlight. Scene 9: The gray otter suddenly notices the shiny blue berry again. The camera cuts to a close-up as it happily picks up the berry with both paws. Its huge eyes sparkle with excitement. Scene 10: The gray otter proudly holds the blue berry close to its face and smiles innocently. The brown otter approaches from behind. Final scene: The brown otter gently jumps onto the gray otter in a playful, affectionate hug. They tumble softly onto the grass together beside the blue berry, laughing and cuddling. Tiny glowing sparkles appear around them as they lie peacefully in the meadow. Visual style: premium cinematic 3D animation, adorable family-friendly characters, soft detailed fur, expressive oversized eyes, rounded proportions, vibrant natural environment, warm golden sunlight, volumetric lighting, soft shadows, realistic grass and foliage, beautiful depth of field, smooth character animation, polished feature-film quality, gentle camera movements, emotionally expressive faces, whimsical magical atmosphere. Maintain consistent character appearance, fur color, facial features, body proportions, scarf, and environment throughout all scenes. No text, no subtitles, no watermark, no distorted anatomy, no extra limbs, no flickering, no character deformation.

Set up model routing for this repo: 1. List this month's task types and how long each answer was. Table only, change nothing 2. Anything that ended past 128K goes to Gemini 4 Argon as one call, no chunking > Terminal and shell work stays on Opus 5.5 > Fixes that failed twice go to GPT-6 Astra > Cache the repo context on Argon so every run reuses it 3. Price each task type at Argon's intro rate next to what it costs today 4. Print the routing table with the price column, then wait for my yes before switching anything.

15-second ultra-cinematic racing film, photorealistic, premium automotive cinematography.A high-speed race through rolling countryside just before a massive summer storm. The track is dry in some sections and soaked by rain in others. Two sleek performance cars battle for victory. 0-3s — The cars race beneath dramatic clouds. Sunlight breaks through onto the road. 3-6s — Rain suddenly sweeps across the circuit ahead.6-9s — The leader slows as the road becomes wet. The pursuing car stays committed. 9-12s — The silver car enters the rain at full speed, water exploding from the tires. 12-15s — It emerges from the storm back into golden sunlight and takes the lead.Gorgeous contrast between dark storm clouds and warm sunlight. Realistic wet-road physics. Powerful sense of acceleration. No crashes.

Create a 15-second cinematic film sequence of a young man walking slowly through a modern city at night. Light rain falls continuously, creating reflections of glowing streetlights, colorful neon signs, storefronts, and passing cars across the wet pavement. 0–5 seconds: Start with a wide cinematic shot from behind as the young man walks calmly down the rain-soaked street. His clothes and hair move naturally with the light breeze. Neon lights softly illuminate the surroundings. 5–10 seconds: The camera smoothly moves alongside him in a slow tracking shot. He briefly looks toward the glowing city lights while rain droplets pass naturally in front of the lens. Background pedestrians and vehicles move realistically, slightly blurred. 10–15 seconds: The camera slowly moves toward a front three-quarter close-up of his face. He continues walking with a peaceful, thoughtful expression while colorful city lights create beautiful soft bokeh behind him. End with a gentle cinematic push-in. Realistic human walking motion, natural body movement, realistic rain physics, wet pavement reflections, soft volumetric lighting, subtle atmospheric haze, shallow depth of field, realistic skin and clothing textures, smooth stabilized camera movement, cinematic 35mm lens, subtle film grain, high dynamic range, photorealistic 4K cinematic movie quality. Audio: Add soothing, relaxing cinematic background music throughout the entire sequence — soft ambient piano with gentle atmospheric pads, subtle rain ambience and distant city sounds. Music should feel peaceful, emotional and slightly nostalgic, remain low and unobtrusive, and smoothly build toward the final close-up. No vocals, no dialogue, no sudden beats, no dramatic music.

Create a 15-second fast-paced, smooth luxury fashion editorial video using the character sheet as the visual reference. Keep the same woman, face, brunette hair, fur jacket, red crop top, distressed denim, chains, makeup, and overall styling consistent throughout. Preserve her playful, confident, slightly mischievous personality. The video should feel like a fashion mugshot mixed with a playful “wanted for beauty” campaign. 0–3s — THE MUGSHOT Start with a sharp full-body mugshot composition in front of the height chart. She looks directly into camera. Quick smooth push-in → she gives a playful wink → instantly cuts to her holding the “WANTED FOR BEAUTY” board. She slowly tilts the board toward camera with attitude. 3–6s — BEAUTY DETAILS Move into a rapid but smooth beauty montage: wink → glossy lips → red nails → lollipop → fur jacket texture → chain details → sunglasses → playful smile. Use smooth snap zooms and seamless whip transitions. Each shot should be very short, around 0.3–0.6 seconds, but transitions should remain fluid and polished. 6–9s — PLAYFUL TROUBLEMAKER Return to the full mugshot. She casually leans toward one side while maintaining her confident stance. Quick smooth camera orbit around her → she puts on sunglasses → looks over the sunglasses directly at camera → gives a mischievous smile. Add subtle camera flash bursts like paparazzi photographers are surrounding her. 9–12s — FAST FASHION MONTAGE Rapidly showcase: fur coat → red top → belt and chains → distressed jeans → lollipop → lips → eyes → sunglasses. Use smooth continuous camera movement between each detail, with quick editorial cuts. Newspaper pages briefly fly across the frame, creating transitions. 12–15s — FINAL SHOT Return to the mugshot setup. She holds the board toward camera. The board now reads: “WANTED FOR BEING TOO BEAUTIFUL” She raises one eyebrow and smiles. Camera rapidly pushes toward her face. A newspaper suddenly sweeps across the lens. CUT TO BLACK. Motion & Editing FAST-PACED but SMOOTH. Use: 0.3–0.6 second cuts smooth snap zooms seamless whip transitions controlled camera orbit quick push-ins and pullbacks subtle speed ramps fashion-editorial motion blur paparazzi flash effects flowing newspaper transitions beat-synced editing Do NOT make it slow, dreamy, jittery, or chaotic. The camera should always feel controlled and fluid, while the editing stays fast. Overall feeling: playful troublemaker + luxury fashion campaign + cinematic mugshot + glossy magazine editorial.

Use the character sheet as the visual reference. Preserve the bride’s exact face, hairstyle, dress, body proportions, and accessories throughout the entire video. 16:9 landscape. 0–3 sec — THE ESCAPE A church wedding is happening when the bride suddenly bursts through the giant church doors and sprints down the steps, still holding her bouquet. Her expression is determined but hilariously excited. Her veil and dress fly wildly behind her. Camera rapidly tracks backward in front of her as she runs. A few confused wedding guests appear in the background, realizing what is happening. 3–5 sec — GET TO THE CAR She spots a bright red 1950s vintage car waiting at the curb. She kicks off one white bridal heel while running, then throws herself toward the driver's door. Fast whip-pan follows her movement. 5–8 sec — PEEL OUT She jumps into the car, slams the door, starts the engine and PEELS AWAY at ridiculous speed. Tires squeal, a tiny cloud of smoke appears, and her long white veil gets caught in the closing door and streams dramatically behind the car. The bouquet lands on the passenger seat. 8–11 sec — CHAOS Rapid comedic interior cuts: Bride gripping the steering wheel and laughing → her veil whipping around her face → bouquet bouncing around the passenger seat → her other bridal heel flying through the air → wedding guests running helplessly behind the disappearing car. 11–15 sec — SHE’S FREE Dynamic side tracking shot of the red car racing down a sunny vintage highway. The bride drives one-handed, completely carefree. She looks into the rearview mirror, sees the church disappearing in the distance, grins, then blows a huge pink bubblegum bubble. Final frame: The red car speeds toward the horizon, veil flying behind it. Style: fast-paced physical comedy, playful rebellious energy, 1950s Americana, saturated red vintage car, creamy white wedding dress, warm golden sunlight, cinematic vintage film grain, slightly painterly realism, realistic motion, energetic camera movement, whip pans, quick cuts, exaggerated but believable comedy. Important: No slow motion, no sad mood, no dramatic romance, no dialogue, no text, no extra brides, no face changes, no outfit changes, no distorted hands, no morphing.

Create an exactly 20 second ultra-realistic live-action comedy video, filmed as if recorded on an iPhone 18 Pro Max. Vertical 16:9, 1080×1920, 24fps. Everything must look like authentic real-world smartphone footage. The cat is a completely realistic domestic cat with natural fur, realistic anatomy, whiskers, eyes, paws, and believable movement. The cat wears only a realistic pizza-company delivery jacket. No pants, shoes, hat, or other clothing. SCENE 1 — 0.0–3.5s — PACKING THE PIZZA Inside a realistic neighborhood pizza shop. The cat stands at the preparation counter. The cat physically takes the freshly prepared pizza and places it into a pizza box. The cat then manually closes the pizza box. The cat picks up the closed pizza box and physically places it inside the pizza delivery bag. The cat then manually closes the delivery bag. Every action must be clearly visible and happen in the correct order. Pizza → pizza box → close pizza box → place box inside delivery bag → close delivery bag. Nothing appears or disappears automatically. SCENE 2 — 3.5–6.5s — SCOOTER AND DRIVING The cat carries the closed delivery bag to its scooter. The cat physically places the delivery bag onto the scooter, secures it, climbs onto the scooter, starts the engine, and rides away. Cut to a front-facing camera angle showing the cat and scooter driving toward the camera. The cat drives naturally through a realistic neighborhood road. The cat's face is normal and clean during the driving sequence. Natural iPhone handheld movement, autofocus, exposure changes, motion blur, realistic road movement, scooter engine and street ambience. SCENE 3 — 6.5–10.0s — ARRIVING AND TAKING THE PIZZA The cat arrives outside the customer's house. It stops the scooter and physically puts the scooter on its stand. The cat gets off and walks to the delivery bag. The cat manually opens the delivery bag, reaches inside, grips the closed pizza box, and physically pulls the pizza box completely out of the bag. The cat then closes the delivery bag. The cat carries the pizza box toward the customer's front door. As the cat approaches the house, clearly show a small amount of pizza sauce and a little melted cheese around its mouth, making it obvious that the cat has secretly eaten some pizza. The pizza residue must not appear suddenly. It must remain naturally visible. SCENE 4 — 10.0–12.0s — DOORBELL FIRST The cat reaches the front door while holding the pizza box. The door is completely closed. The cat raises its paw and physically presses the doorbell. Only after the doorbell is pressed, the customer opens the door. Strict order: Cat reaches closed door → cat presses doorbell → door opens. The door must NOT open before the bell is pressed. SCENE 5 — 12.0–14.5s — HANDING OVER THE PIZZA After the door opens, use a camera angle facing the cat from the customer's side. Do not show the customer's face or body. Only the cat should be visible. The cat holds the pizza box forward and says: Cat: "Here is your pizza." The cat physically hands the pizza box to the customer. The pizza box must visibly transfer from the cat's paws into the customer's hands. The pizza residue around the cat's mouth remains clearly visible. SCENE 6 — 14.5–17.0s — THE MISSING PIZZA Cut to the customer's POV. The customer is physically holding the same pizza box. The customer manually opens the pizza box. The cat is standing behind the open box and becomes naturally hidden by the box. Inside the box: - One pizza slice is missing. - Another remaining slice has a small realistic bite taken from it. - All other pizza remains physically present. - Nothing disappears during the shot. The customer looks shocked and says: Customer: "Where is my missing slice?" The customer manually closes the pizza box and looks toward the road. SCENE 7 — 17.0–20.0s — ESCAPE AND FLYING KISS The cat is already moving toward its scooter. The cat climbs onto the scooter, starts it, and physically rides away down the road. The customer runs out toward the road and shouts: Customer: "Stop! Stop!" The cat keeps riding farther away. While actively riding away, the cat turns its head back toward the customer and raises one paw, clearly making a flying-kiss gesture directly toward the customer. The flying kiss must happen mid-ride while the cat is moving away, not before riding away and not after stopping. The cat then faces forward and continues riding farther down the road. End naturally with the cat getting smaller in the distance while the customer remains on the road. STRICT PHYSICAL CONTINUITY Every action must happen physically and in logical order. Nothing may appear automatically. Nothing may disappear automatically. No teleportation, morphing, object replacement, duplicated objects, or sudden prop changes. The exact pizza box used in the shop must remain the same pizza box throughout the entire video. The exact delivery bag must remain the same bag throughout. The pizza must be physically packed into the box, the box physically placed into the bag, the bag physically placed on the scooter, the box physically removed from the bag, and the box physically handed to the customer. The door must remain closed until the cat physically presses the doorbell. The customer must physically open and close the pizza box. The missing pizza slice must simply not be present when the box is opened; it must not disappear during the shot. REALISM REQUIREMENTS - Exactly 20.0 seconds - 9:16 vertical - 1080×1920 - 24fps - iPhone 18 Pro Max realistic footage - Realistic domestic cat - Realistic fur and anatomy - Only pizza-company delivery jacket - Realistic scooter physics - Natural handheld camera movement - Natural autofocus and exposure - Realistic shadows and reflections - Realistic road and house - Natural environmental audio - No CGI appear

KOREA PREMIUM TRAVEL / FASHION FILM 20 seconds | 16:9 | Kling 4.0 Flash | MULTISHOT Premium travel music video × fashion travel film 2024–2026 commercial-grade live-action realism 24fps | natural motion blur | cinematic shutter CORE CONCEPT A young international traveler experiences South Korea through one continuous energetic journey: high-speed rail, Seoul street life, Korean food culture, traditional architecture, coastal landscapes and modern nighttime Seoul. The film feels like a premium Korean tourism campaign combined with an elite fashion travel film. The traveler must always physically exist inside the environment. Locations must feel photographed on real locations, with authentic pedestrians, commuters, vendors, vehicles, weather, reflections and environmental imperfections. The edit is driven by music, but every movement remains physically believable. CHARACTER LOCK ONE TRAVELER throughout the entire film. Young adult international traveler. Wardrobe: premium red Adidas travel jacket, neutral trousers, clean contemporary sneakers, compact crossbody bag. Maintain exactly the same: face, facial proportions, hair, skin texture, body proportions, jacket, trousers, sneakers, bag, accessories. Do not redesign or change the wardrobe between shots. Only use Adidas branding already visible on the clothing. Do not invent additional Adidas logos, storefronts, advertisements or products. JOURNEY Seoul → high-speed railway → traditional Korean neighborhood → Korean food street → mountain landscape → coastal road → Seoul at night. The locations should feel connected as one real journey rather than unrelated travel images. ──────────────────────── 00:00–02.5 — TRAIN WINDOW / HOOK 85mm intimate close-up. The traveler sits beside a high-speed train window. Warm morning sunlight falls naturally across one side of the face. Reflections of the Korean countryside slide continuously across the glass. The traveler watches the landscape. On the first musical beat, they slowly turn toward camera. Subtle breathing. Natural eye movement. Small facial reaction. Camera remains close and observational. Do not beautify the face. Preserve realistic pores, hair and skin texture. ──────────────────────── 02.5–05.0 — DEPARTURE 24mm wide platform shot. The traveler walks alongside a departing high-speed train. The train begins accelerating behind them. Wind pressure from the moving train pushes naturally against the red jacket and hair. Camera tracks laterally at walking speed. The traveler remains grounded on the platform. Real commuters move independently in the background. Cut on the movement of the train. ──────────────────────── 05.0–07.5 — SEOUL ARRIVAL 35mm handheld follow shot. The traveler exits a busy Seoul station into the street. Camera follows slightly behind and to one side. Do not perfectly center the subject. Pedestrians naturally cross between camera and traveler. Taxis, buses, bicycles and scooters move through the background. Small autofocus adjustment as a pedestrian briefly passes close to lens. Natural exposure adaptation from station interior to daylight. ──────────────────────── 07.5–10.0 — KOREAN STREET FOOD 50mm observational handheld shot. The traveler moves through a lively Korean food street. A vendor prepares steaming Korean street food beside them. The traveler slows down. Looks toward the cooking. Steam rises naturally and briefly crosses the lens. The vendor hands the traveler a freshly prepared dish. The traveler tastes it and gives a subtle genuine reaction. Background remains active: customers, vendors, passing pedestrians, street signage, cooking smoke, ambient movement. No staged crowd behavior. ──────────────────────── 10.0–12.5 — TRADITIONAL KOREA 24mm wide tracking shot. The traveler enters a traditional Korean neighborhood. Wooden hanok architecture. Stone pathway. Traditional tiled roofs. Small courtyard. Natural pedestrians. Camera follows the traveler across a small stone bridge. Late-afternoon sunlight enters between buildings. A pedestrian crosses the foreground, briefly obscuring the traveler. Use the obstruction as a natural transition. No artificial transition effect. ──────────────────────── 12.5–15.0 — HUMAN FOOD MOMENT 50mm close-up. A local vendor places freshly prepared Korean food in front of the traveler. Traveler picks up the food. Takes one bite. Subtle natural reaction. Shallow depth of field. Background remains visibly alive but softly defocused. Hands, food, steam and facial movement must remain anatomically correct. ──────────────────────── 15.0–17.5 — MOUNTAIN ASCENT 24mm deep-focus shot. The traveler walks upward along a long mountain staircase surrounded by dense Korean vegetation. Camera follows from behind. Footsteps have realistic weight. Clothing responds naturally to movement. Wind moves leaves and fabric independently. As the traveler reaches the upper section of the stairs, the camera gradually reveals a vast Korean mountain valley beyond. Cool atmospheric mist sits between distant mountains. The reveal happens through physical camera movement, not a digital zoom. ──────────────────────── 17.5–20.0 — FASHION / LANDSCAPE 50mm side-tracking shot. Golden-hour sunlight illuminates the traveler as they walk along a mountain viewpoint. Red jacket contrasts naturally against deep green vegetation. Warm rim light catches hair and shoulders. Wind moves the jacket realistically. Camera maintains approximately parallel movement. Natural lens flare from the low sun. No artificial beauty lighting. ──────────────────────── 20.0–22.5 — SCALE 24mm extremely wide environmental composition. The traveler becomes small within an enormous Korean mountain landscape. Distant peaks disappear into atmospheric haze. Clouds drift slowly throu

30-second comedy short. Two realistic house cats, a chunky orange tabby and a skinny black-and-white tuxedo cat, sit side by side on a dim rooftop ledge at night, city lights blurred behind them. Warm orange and blue lighting, shallow depth of field, mockumentary-style camera with sudden zoom-ins for comedic timing. Their mouths move naturally in sync with speech. They whisper in sad-angry, deadpan voices like two exhausted men at a bar, constantly glancing over their shoulders. Burned-in white English subtitles at the bottom of the frame, synced to speech. 0-5s: Close-up of the orange tabby, ears flat, one eye twitching. Long, dramatic sigh. Orange (whisper): "Bro... she woke me up at 5 AM to ask if I love her." Subtitle: "Bro... she woke me up at 5 AM to ask if I love her." Quick zoom-in on his tired face. 5-10s: Cut to the tuxedo, tail whipping, slowly shaking his head. Tuxedo (whisper): "Mine knocked a glass off the table, looked me dead in the eye, and blamed ME." Subtitle: "Mine knocked a glass off the table, looked me dead in the eye, and blamed ME." Orange nods slowly in the background: "Classic." 10-15s: Two-shot, both staring at the skyline. Orange (whisper): "She says I never listen. I'm a CAT. I don't listen to anybody." Subtitle: "She says I never listen. I'm a CAT. I don't listen to anybody." Tuxedo: "Respect the honesty, though." 15-20s: Tuxedo leans in, furious whisper, eyes wide. Tuxedo (whisper): "She told me to 'use my words.' I HAVE four words. All of them are 'feed me' and 'move.'" Subtitle: "She told me to 'use my words.' I HAVE four words. All of them are 'feed me' and 'move.'" Orange wheezes silently, shoulders shaking. 20-25s: Both go quiet. Orange stares into the distance. Orange (whisper): "That's it. I'm done. Tonight I'm leaving her." Tuxedo (whisper): "Finally. Say it again, louder." Orange (louder, voice cracking): "I'M LEAVING HER!" Subtitles match. 25-30s: A distant female voice calls out: "Dinnerrr!" Both cats' ears shoot up instantly. They stare at each other, then bolt off the ledge in opposite directions. Cut to the empty ledge, one tiny "meow" echoes. Orange (off-screen): "Coming, babe!" Tuxedo (off-screen): "Coming, honey!" Subtitles match. Fade to black. Style: photorealistic, 4K, cinematic color grade, subtle city ambience, light comedic sound effects (record scratch on the "four words" line, tiny whoosh on the bolt-off). No cartoon look, no text other than subtitles.

Character consistency: Same young adult female traveler throughout, same face, hairstyle, body proportions and outfit, realistic skin, natural expressions, cinematic photorealistic travel-vlog style, smooth camera movement, realistic lighting. No face changes, no outfit changes. 0–5 sec — Arrival 🇬🇧 Young female traveler arrives in London, walking out of Heathrow Airport with a small suitcase, excited expression, cinematic establishing shot of London atmosphere, natural handheld vlog camera movement. 5–10 sec — Big Ben & Westminster She walks near Big Ben and Westminster, looks at the landmark and smiles toward the camera, quick selfie-style vlog shot followed by a wide cinematic view of Big Ben and the River Thames. 10–15 sec — Tower Bridge She explores Tower Bridge, walking across the bridge while filming herself, London skyline in the background, natural tourist atmosphere, smooth tracking shot. 15–20 sec — London Street She walks through a beautiful London street with classic red buses, black cabs and historic buildings, briefly stops at a cozy café, takes a coffee and continues exploring. 20–25 sec — London Eye She stands beside the London Eye during golden hour, looks toward the camera with a happy travel-vlog expression, camera slowly circles around her with the London skyline behind. 25–30 sec — Final London Shot She walks along the River Thames at sunset, turns toward the camera and smiles, cinematic aerial pull-back revealing London skyline, warm golden-hour lighting, beautiful travel-vlog ending. Overall: photorealistic, cinematic 4K, natural movement, realistic London environment, smooth transitions between locations, consistent character, consistent clothes, consistent face, no text, no watermark.

Create an ultra-realistic cinematic Japanese lifestyle vlog featuring a young Japanese woman enjoying a peaceful rainy day in a quiet Japanese neighborhood. A young woman with black hair tied in a neat ponytail, wearing a white and navy striped oversized T-shirt, beige shorts, and white sneakers, stands under a traditional covered bus stop during light rain. She looks outside, gently extends her hand to feel the raindrops, then turns around and runs playfully along a quiet residential street. Show cinematic transitions of her running through the wet neighborhood, passing traditional Japanese houses, green trees, and a peaceful park. She eventually reaches a wooden shelter in the park, adjusts her ponytail, stretches her arms, and smiles naturally toward the camera. Visual Style: Photorealistic Japanese slice-of-life cinematography, soft overcast daylight, realistic rain reflections, natural human movements, beautiful greenery, peaceful atmosphere, authentic Japanese residential environment. Camera Direction: Start with a cinematic side-profile close-up, transition into a medium shot of her touching raindrops, followed by a smooth rear tracking shot while running. Finish with emotional close-ups and a warm natural smile. Technical: 4K, 9:16 vertical, 24fps, realistic facial expressions, consistent character identity, smooth camera movement, natural physics, detailed environment, cinematic color grading. Important: Maintain the same woman's face, hairstyle, outfit, and body proportions throughout every scene. No facial distortion, no outfit changes, no unnatural movements, no text or watermark.

Cinematic horror-action short film set aboard a moving metro train during the day, opens with an immediate strong hook, maximum dynamic camera work, grounded practical-effects style. Train car filled with passengers standing and seated, overhead handrails, glass doors between cars, city blurring past the windows. Muted authentic color grading, natural diegetic sound throughout, tension score entering immediately. > > **[0-1s]** Hard cut: a man standing near the doors suddenly jolts violently, gasping sharply. > > **[1-2s]** Close-up: his veins turn a deep red, spreading rapidly up his neck and across his face. > > **[2-3s]** His eyes snap open, now fully red — he lunges instantly, biting into a nearby woman's shoulder. > > **[3-4s]** She cries out, nearby passengers recoiling in shock, grabbing handrails as people scramble back. > > **[4-5s]** She convulses hard, veins spreading fast across her own neck and arms. > > **[5-6s]** She rises seconds later, eyes red, joining him, both turning toward the passengers around them. > > **[6-7s]** Panic spreads through the car, passengers screaming, pushing toward the connecting doors. > > **[7-8s]** Since the train can't stop, passengers scramble into the next car, sliding the connecting door shut behind them. > > **[8-9s]** The two infected pound against the glass door, passengers backing away on the other side. > > **[9-10s]** A passenger grabs a fire extinguisher from the wall mount, gripping it defensively. > > **[10-11s]** The door suddenly gives way, the infected pushing through into the crowded car. > > **[11-12s]** Passengers scatter, some climbing over seats, others pressing flat against the walls. > > **[12-13s]** A man grabs a metal pole torn loose from a luggage rack, stepping forward to face them. > > **[13-14s]** The infected man lunges first; he swings the pole hard, striking it across the shoulder. > > **[14-15s]** It staggers back into a seat, momentarily stunned. > > **[15-16s]** The infected woman charges from the side; he pivots fast, blocking her lunge with the pole. > > **[16-17s]** SLOW MOTION insert: he shoves her back hard, creating space between himself and both threats. > > **[17-18s]** The infected man recovers, charging again; he braces and swings the pole in a wide arc. > > **[18-19s]** The impact connects solidly, dropping it to the floor of the swaying train car. > > **[19-20s]** The infected woman lunges one final time; he sidesteps and strikes her down with a decisive blow. > > **[20-21s]** Both collapse motionless on the train floor, the car rocking gently with the train's motion. > > **[21-22s]** He stands over them, chest heaving, pole still raised, scanning for any more movement. > > **[22-24s]** Wide shot: passengers emerge cautiously from where they'd hidden, shaken but safe. > > **[24-26s]** He lowers the pole slowly, checking both infected to confirm they're down. > > **[26-28s]** A nearby passenger helps steady an elderly rider who'd stumbled during the chaos. > > **[28-30s]** Final shot: the train pulls into a bright station, doors opening, passengers filing out past him as he stands guard over the fallen pair. Cut to black. > > Natural diegetic sound throughout — gasping, screaming, train wheels on tracks, metal impacts, heavy breathing, station announcement chime — layered with a tense instrumental score building through the chaos and easing into relief at the end. No text overlay, no watermark. Maximum dynamic camera variety — close-ups, wide shots, tracking shots, slow motion reserved only for the final takedown blows. Realistic shake only during physical impacts, natural daylight metro color grading.

Create a 20-second vertical 16：9 photorealistic fashion-blogger reel with exactly 10 shots. Use @Image1 as the strict character reference: same face, skin tone, body proportions, long dark chestnut-brown hair, and starting white cropped tank + white pajama shorts. Use @Image2 as the strict wardrobe reference: moss-olive oversized sweater, olive satin lace mini skirt, brown belt with gold buckle, chocolate knee-high boots, structured brown tote, and gold jewelry. CAMERA: One fixed phone camera on a tripod for the entire video. Same doorway position, eye-level frontal angle, same framing, focus, exposure, and background geometry. Every transition is an instant HARD CUT. No camera movement. No morphing. No outfit changes inside a shot. STYLE: Ultra-photorealistic fashion creator reel, realistic skin and hair, detailed knit texture, natural satin and lace movement, warm dressing-room lighting. She treats the lens like a friend watching her get ready: relaxed, playful, natural smiles, light rhythmic energy. SETTING: Elegant compact dressing room, beige walls, gold mirror, stone vanity, warm wall sconces, a few clothing boxes. SHOT 1 | 0–1.7s She holds the olive satin lace mini skirt against her waist, lightly shifts her hips, smiles at camera. SHOT 2 | 1.7–3.4s She holds the oversized moss-olive sweater against her torso, gives it one small bounce, smiles. SHOT 3 | 3.4–5.0s Closer shot. She holds the brown belt horizontally with the gold buckle centered near camera, looking over it playfully. SHOT 4 | 5.0–5.8s Back at presentation distance. One quick natural hair flip. SHOT 5 | 5.8–7.5s Closer shot. She presents the structured brown tote in front of her chest, face visible between the handles. SHOT 6 | 7.5–10.2s She is already pulling on the oversized sweater. One continuous action: head through neckline → arms through sleeves → hem settles at upper hips → hair falls naturally back into place. SHOT 7 | 10.2–11.7s Closer shot. Wearing the sweater, she sprays perfume once beside her neck, closes her eyes briefly, then smiles. SHOT 8 | 11.7–14.0s After the hard cut she already wears the high-waisted olive satin lace mini skirt. She adjusts both sides once, then releases them. Sweater remains loose over the waist. SHOT 9 | 14.0–15.7s Closer shot. Gold necklace, ring and bangle are already on. She fastens one chunky gold hoop earring, then gives a quick playful smile. SHOT 10 | 15.7–20.0s Final full-body reveal. She wears the complete outfit: oversized moss-olive sweater, high-waisted olive lace mini skirt, brown belt, chocolate knee-high boots, gold jewelry, brown tote. Front center of sweater tucked beneath the belt; sides and back stay loose. She gives one lively final turn and settles into a confident full-body pose. Keep the exact same character, face, hair, room, camera, and wardrobe design throughout. No second person, no face drift, no body changes, no extra limbs, no clothing morph, no random accessories, no text, no subtitles, no watermark.

SCENE CONTEXT: Empty 24-hour coin laundromat in Osaka, 3am. A woman in an oversized grey coat sits alone. Each dryer window shows a different warm memory of her life instead of clothes. Photorealistic, melancholic, cinematic. ACTIVE REFERENCES: Woman (consistent face, black bob, grey coat). LOCATION MAP: Row of 6 front-load dryers left, folding table center, flickering fluorescent tube overhead, rainy glass door behind camera. FIRST FRAME / SPATIAL BLOCKING: Woman seated center-right on plastic bench, hands in pockets, facing the dryers 2m away. Dryer 3 glowing amber. FORMAT MODE: 9:16, 15 seconds, hard cuts only. OPTICS: 50mm, shallow DOF, soft halation on light sources. CAMERA: Handheld, slow drift, subtle breathing sway. ACTION TIMING: 0.0–2.5s | Wide: fluorescent flicker, she stares at a spinning dryer 2.5–5.0s | Hard cut, macro inside dryer 3: a child's birthday candle scene tumbles like laundry, warm light 5.0–7.0s | Hard cut, tight on her eyes, amber light reflecting, a tear forms 7.0–9.5s | Hard cut, she stands and walks to dryer 4, it glows with a different memory (hands holding at a train station) 9.5–12.0s | Hard cut, palm on the glass, light shifts across her face, her breathing slows 12.0–15.0s | Hard cut, all dryers stop one by one, windows go dark, her reflection smiles slightly