Prompt Video untuk Anime

TITLE The Lost Wind Chime REFERENCE Use the uploaded storyboard board and character sheet as the main visual reference. Keep all character designs, environment details, wind chime design, kitten appearance, countryside lighting, and emotional story beats consistent with the provided references.

Create a 10-second cinematic anime-style sequence set in a peaceful Japanese town on a bright summer morning. Start with a wide shot of a quiet residential street with Japanese houses, greenery, utility poles and soft blue skies → show a schoolgirl waking up in a sunlit bedroom, stretching beside the window → close-up of breakfast cooking in a warm kitchen with gentle steam → she grabs her school bag and runs outside to catch the school bus → show her walking along a sunny street before meeting a schoolboy riding a bicycle → they travel together toward school, with natural wind moving their hair and clothes → end with the girl entering a bright classroom and sitting beside the window as sunlight fills the room. Beautiful anime visuals, detailed backgrounds, expressive characters, soft golden lighting, smooth camera movement, natural animation, subtle motion blur, nostalgic coming-of-age atmosphere, consistent character appearance, no text, subtitles or watermark.

Create a 30-second premium cinematic 2.5D anime samurai battle in 16:9 widescreen. High-budget Japanese anime movie style, fluid animation, realistic physics, dramatic lighting, strong 2.5D depth/parallax, cinematic camera movement. CHARACTERS: Warrior A: adult male, long black ponytail, black-red samurai outfit, black katana with red handle, calm and precise. Warrior B: adult male, silver-white hair, dark navy samurai outfit, dark katana with blue handle, aggressive and extremely fast. Keep faces, hairstyles, outfits and weapons consistent throughout. 0–3s: HOOK: Extreme close-up of rain sliding down Warrior A's katana. Lightning flashes. Warrior B suddenly attacks from behind. A blocks at the last second. Their swords lock inches from their faces. 3–7s:FAST DUEL: Explosive katana battle across the dojo: slashes, parries, spinning attacks, dodges and counters. Sparks fly and the wooden floor cracks. Fast tracking camera. 7–10s:SLOW MOTION: Warrior B delivers a powerful slash. A bends backward and narrowly dodges. Rain freezes in the air as the camera performs a cinematic 360° orbit. Suddenly return to full speed. 10–15s: HAND-TO-HAND: A disarms B. The fight instantly becomes close-range martial arts: punch, block, elbow, knee, spinning kick and shoulder throw. B recovers, grabs his katana and attacks again. 15–19s: DOJO BREAK: Their swords lock with massive force. The floor cracks and they crash through the dojo wall into the heavy rain outside. They immediately continue fighting. 19–23s: AERIAL CLASH: Both sprint toward each other and leap. Their katanas collide mid-air in dramatic slow motion. Sparks, rain and debris freeze around them before a powerful impact throws them apart. 23–27s: FINAL SPEED: They rush toward each other at extreme speed: slash → parry → punch → dodge → elbow → sword clash → spinning kick → final counter. Use low angle, tracking, close-up and overhead shots. 27–30s: EPIC ENDING: Silence. One rain droplet falls between them. Both raise their katanas and attack simultaneously. Massive final clash, shockwave, flying rain, leaves and debris. Camera pulls back to reveal the entire ancient Japanese temple beneath storm clouds and lightning. Cut to black on a lightning flash. STYLE: Professional martial-arts choreography, realistic weight and momentum, authentic katana movements, cinematic slow/fast speed ramps, volumetric lighting, rain reflections, atmospheric fog, dynamic hair and clothing, detailed Japanese architecture, movie-quality anime visuals.

Create a vertical lyric video featuring the lyrics as the main character. Sync the lyrics perfectly with the song. Use an Evangelion title card style. Show me the direction plan before making it.

10-second seamless looping animation, 9:16 vertical. Locked-off static camera, frame perfectly still for the entire shot. A lone weathered concrete sky tower rises out of soft teal fog against a solid flat teal backdrop. At its crown sits a glass-walled lofi bedroom glowing warm amber, with a pink neon sign reading "madpencil". The tower continuously reconfigures itself mechanically between four forms matching the reference images, like a precise transforming machine. Every section is a rigid engineered part that slides, hinges, rotates, telescopes and locks into place. Timing: each form holds for 1 second, then transforms over 1.5 seconds, cycling Form 1, Form 2, Form 3, Form 4, then back into Form 1, so the final frame matches the first frame exactly. Transformation mechanics: concrete wall panels split along seams and slide apart on hidden rails. Glass window frames fold and pivot into new angles. The balcony deck ratchets outward or retracts while railings flip up from its edges. Rooftop AC units, water tanks and generators unbolt, lift on small robotic arms, shuffle positions and clamp down. Antennas telescope up or collapse. Pipes and cables reroute and snap into new couplings. Plates on the lower shaft rotate like gears, revealing machinery beneath. The neon sign glides along a track to its new spot with a flicker. Inside, the bed, shelves and desk fold and slide into each new layout. Motion style: weighty, crisp and mechanical at a steady constant pace, parts moving in overlapping waves from roof to base. Small puffs of dust and steam at the joints, tiny sparks at locking points. The tower stays centered at the same scale throughout. Look: stylized isometric 3D illustration with painterly anime textures, soft volumetric fog, warm interior glow against cool teal, rust stains, dense fine detail. Audio: servo whirs, hydraulic hisses, heavy metal clunks, ratchet clicks, faint neon hum, soft high-altitude wind.

Create a 30-sec hand-painted 2D anime cooking film in the peaceful Korean countryside. Warm storybook lighting, soft watercolor textures, delicate backgrounds, gentle cel shading, natural hand-drawn motion, cozy cinematic atmosphere, appetizing food close-ups and steam. STYLE/SETTING: Authentic Korean world: hanok homes, gray giwa roofs, stone walls, onggi jars, wooden fences, changhoji lattice windows, rice fields and green hills. No Japanese architecture, torii, tatami-focused interiors, Japanese text, CGI, logos, watermarks, UI, titles, captions, subtitles, or any on-screen text. FOOD: Authentic Japchae (잡채): sweet-potato glass noodles, beef, carrot, onion, red pepper, spinach, shiitake, egg strips, soy-garlic sauce, sesame oil/seeds. Serve with white rice and kimchi. Keep the same home, hands, food design, lighting and visual style throughout. 0–3s: Hands carry a bamboo basket of fresh spinach, carrot, red pepper and shiitake through a Korean garden; hanok and onggi jars behind, warm sunlight, breeze, birds. 3–6s: Hands soak dangmyeon in a wooden bowl inside a traditional Korean kitchen. 6–9s: Close-up slicing carrot, onion and red pepper into thin strips. 9–12s: Slice shiitake, spinach, beef and thin egg omelette ribbons. 12–15s: Boil dangmyeon, rinse in cold water and drain; steam and translucent chewy noodles. 15–18s: Stir-fry beef with soy sauce, then carrot, pepper, mushrooms and spinach; sizzling steam. 18–22s: Mix soy-garlic sauce. Toss noodles, vegetables, beef and egg until glossy; add sesame oil and sesame seeds. 22–26s: Plate steaming Japchae on Korean ceramicware; colorful noodles, vegetables, beef and egg. 26–30s: Wide hanok interior: Japchae, white rice and kimchi on a low wooden table. Changhoji window reveals Korean hills, rice fields and distant hanok rooftops. Warm afternoon light, slow pull-back, hold final frame. CAMERA: Mostly static illustrated close-ups, clean short cuts, gentle push-ins/pull-backs, minimal shake, no rapid cuts. AUDIO: Birds, breeze, leaves, water, chopping, boiling and sizzling. No voiceover or dialogue. Optional very soft distant gayageum. MOOD: Peaceful, nostalgic, intimate Korean countryside cooking memory. Consistent hand-painted 2D anime style from start to finish.

Cinematic anime clip, 15 seconds. Narrow streets and rooftops of Dhaka, Bangladesh — tight alleyways, colorful buildings, dust and chaos, civilians scattering, warm golden light throughout. One location throughout. TYLER: Use uploaded character sheet

6x6グリッド画像の1コマを開始フレームとして左上から右下へかけて順次参照して、流れるようなアニメキャラのダンス動画を生成。生成動画にはグリッド画像自体は含めず、キャラが1名でダンスしているシーンとする

Cinematic cel-shaded 3D anime, semi-realistic CGI, 15-second Korean action sequence at a modern Korean university campus at night during a student festival. CHARACTERS: Jun-ho, 22, messy black hair, dark oversized varsity jacket, white T-shirt, loose black trousers, sneakers, bruised cheek. Athletic, determined. So-yeon, 21, long dark hair, cream university jacket, jeans, sneakers, kidnapped by four masked men in dark streetwear. ACTION: Jun-ho spots So-yeon being dragged through a neon-lit campus corridor and immediately chases them. He ducks a punch, slams one attacker into lockers, spins and kicks another through a classroom doorway. So-yeon breaks free and runs toward the stairwell, but an attacker grabs her. Jun-ho swings around the stair railing and knocks him away. The chase continues into the underground parking garage, where Jun-ho dodges attacks between cars and defeats the final attacker with a fast hand-to-hand combination. Jun-ho and So-yeon sprint toward the campus exit as security lights flash and campus security approaches. STYLE & CAMERA: Unreal Engine-quality cinematic CGI, Korean action-anime aesthetic, bold cel-shaded shadows, dramatic rim lighting, realistic cloth and hair physics, dynamic tracking shots, low-angle action camera, fast camera movement, motion blur, cinematic depth of field, detailed Korean campus environment. AUDIO: Intense Korean action-thriller orchestral score, heavy footsteps, shouting, locker impacts, realistic fight sounds and distant campus ambience. NEGATIVE: No live-action, no flat 2D anime, no guns, no gore, no superpowers, no impossible physics, no duplicated characters, no distorted anatomy, no changing faces/outfits, no teleportation, no subtitles, no watermark, no text artifacts.

ルール： - 予算5億円規模の劇場アニメ品質・日本の2Dセル画アニメ - マルチショット - 高速カット割り・作画枚数多め。スピード感と迫力を最優先 - VFXプロ品質 - カメラワークは毎ショット変える（同じ動きの繰り返し禁止） - BGMなし・環境音/効果音あり - 字幕なし - セリフは全て日本語 - 緩急：静かな芝居は間をとってじっくり見せ、見せ場で一気に動かす - 雨は細く速い線で描き、しぶき・水たまりの反射・濡れて束になった髪まで作画で描きこむ - 夜の雨。街灯やネオンの色を濡れた路面に映し、淡い水色と白のキャラが背景に溶けて灰色に沈まない配色にする - 主役は常に画面の大きな位置に置き、顔と衣装がはっきり見える。遠景で豆粒のように小さくしない - 画面に文字・ロゴ・数字を一切出さない @ Image1：被写体・シルヴィ @ Image2：被写体・アイル [一貫性] シルヴィ（白銀のボブで右目が前髪に隠れ、見えている目は黄緑。水色の悪魔の角とフリルのヘッドドレス、水色の小さなコウモリの翼と細いしっぽ、真っ白なフリルドレスに水色のリボン、水色と白のしましまの靴下）とアイル（青いぱっつんボブ、頭の両側に白い丸い羽根飾り、肩に青と白の小さな翼、白地に青い丸模様のドレス、後ろに長く垂れる青い羽根のすそ）の外見を全編で一貫させ、2人を混ぜない。アイルは雲の上の天使、シルヴィは地上の悪魔 [生成ゴール] 雨の日だけ、会える （6ステージ・1本の連続動画。雨の糸を伝って会いに来て、雨がやむまで） [S1] 雲の上。@ Image2のアイルが、雲のすき間から落ちていく雨の糸をつかみ、すべり台のように地上へすべり降りていく（うれしくて待ちきれない顔）。 カメラ：雨の糸に沿って、すべり降りるアイルを真上から追う高速ドリー [S2] 雨の夜の町の屋根の上。@ Image1のシルヴィが、傘もささずに空を見上げて待っている。雨粒が水色の角とコウモリの翼を伝って落ちる。 カメラ：屋根の低いアングルから、空を見上げるシルヴィの横顔 [S3] アイルがふわりと屋根に着地し、2人が向かい合う。シルヴィは照れてそっぽを向くが、しっぽの先がうれしそうに揺れている。 カメラ：2人を横から並べるツーショット。しっぽの揺れが見える引き アイル（はずむ声で）は言う：{きたよ} [S4] 2人は屋根の上に並んで座り、シルヴィがコウモリの翼を傘がわりに広げてアイルの上にかざす。雨の町の灯りが2人の下でにじんで光る。 カメラ：2人の背中越しに、雨の町の夜景を見下ろす [S5] 雨が弱まり、雲の切れ目から月の光が差す。アイルの体が光に引かれてふわりと浮き上がり、空へ戻っていく。手を伸ばすシルヴィ。2人の指先が離れる。 カメラ：離れていく指先の寄りから、見上げるシルヴィの顔へ アイル（泣き笑いで）は言う：{つぎの雨の日に} [S6] 雨の上がった屋根の上に、シルヴィがひとり。手のひらに、アイルの青い羽根が一枚残っている。シルヴィは羽根をぎゅっと握り、空を見上げて小さく笑う。 カメラ：羽根の寄りから、夜空を見上げるシルヴィの引きへ

Please keep the image sequence except for the last frame, as close to the exact original illustrations as possible. These are images of a specific band. The cat should be walking towards the camera, a hand reaches out to pet it but does not touch, the cat disappears before the hand can pet the cat. The green haired girl in the photo is revealed to be the person who reaches for a picture at the edge of the table. She picks up the picture and a tear falls on it from her starting to cry. As the tear falls, the camera zooms into the picture frame as if it's live at the original party - the cat stands up on her hind legs and looks at the camera. Please use the photorealistic Tanner picture as how she looks when she's standing up but please keep her in the same cartoon format as the rest of the sequence, thank you.

[MOTION STYLE] Emphasize snappy animation with lively energy, strong anticipation, overshoot, squash and stretch, and follow-through on hair and jacket. Give the movement a distinctive rhythm with variation in pacing: sharp compressions, sudden acceleration, delayed settle on hair and fabric. Physics are slightly exaggerated beyond reality, but the rider's footing and center of gravity don't break. Use motion blur, short afterimages and dramatic smear frames sparingly. ONE-SHOT (15s, 9:16) — one rider, one bike, flat-out speed, loop-ready. SCENE CONTEXT — EXACTLY 1 CHARACTER, 1 BIKE. NO DUPLICATES. No other people or bikes anywhere in the field. ACTIVE REFERENCES [Image 1] is the first frame. It defines the opening composition and <Hyo>'s appearance — a young woman with black hair in two low buns, burgundy windbreaker, olive mountain-bike shorts over grey leggings, orange gloves, seen from behind and already airborne and ALREADY FALLING off the dirt lip. The video starts exactly from this frame. Do not restage it, do not re-rise. GEO SPATIAL LAYOUT (locked): a harvested golden stubble field. A packed dirt track runs STRAIGHT AWAY from camera into the distance. The take-off mound is behind her at frame start; a landing ramp sits immediately ahead; a second smaller dirt lip sits further down the same straight track; the main take-off mound reappears at the far end of the same line. Three round straw bales stand beside the track frame-LEFT; a red barn and hedgerow close the horizon frame-RIGHT. Crisp bright autumn noon, luminous clear blue sky, stubble blazing gold. SPEED (mandatory): she rides FLAT-OUT the whole way, roughly 35 km/h. Ground, stubble, bales and track texture rush past the wheels and out of the bottom of frame fast. Her legs turn a fast continuous cadence; chain and spokes blur. Real-time speed or faster at every moment. [Stage 1] 0.0–1.5s — LANDING Initial state: <Hyo> is already descending, bike level, straw dust trailing behind. Primary event: she presses the bike down and both wheels slam the landing ramp almost together; suspension compresses deep, a burst of dust fires out sideways. End state: both wheels planted, suspension at full compression, her body squashed low over the bars. [Stage 2] 1.5–4.5s — REBOUND AND ACCELERATE Continue from the previous stage: same rider, same bike, camera still behind her. Primary event: the suspension springs back and she stands on the pedals, hammering a fast cadence straight down the dirt track, dust tail streaming behind her. End state: fully upright on the pedals at full speed, track running dead straight ahead of her. [Stage 3] 4.5–8.5s — FLAT-OUT RUN Primary event: she rips past the line of straw bales on her left; the bales, the stubble edge and the track texture streak past and out of frame; her buns and the hem of her windbreaker snap in the wind, settling a beat after her body. End state: the second dirt lip is now filling the lower frame ahead of her. [Stage 4] 8.5–11.5s — QUICK HOP Primary event: she pops the second lip, gets a short sharp half-second of air with the bike tucked, and lands both wheels immediately, a hard crunch and rebound without losing any speed. End state: back on the track at full speed, still accelerating. [Stage 5] 11.5–15.0s — RUN-IN AND LAUNCH Primary event: she drives at the main take-off mound, gloves tight on the bars, body loading as the lip rushes up under her front wheel, then the front wheel leaves the lip and she rises into the air. End state (loop-ready): the exact composition of [Image 1] — seen from behind, low angle, airborne off the lip, bike level, gold field below her wheels. CAMERA — one continuous chase shot. The camera rides roughly 3m behind her rear wheel at about 80cm height, matching her speed so she stays the same size in frame while the ground rushes underneath. Her BACK stays to the lens for all 15 seconds. No cuts, no zoom. The camera never orbits ahead of her, never swings to her side or front, never shows her face, never reverses. PHYSICS — true parabolas, honest suspension compression and rebound, dust and straw lifting and settling at their own weight. AUDIO — ASMR ambient/diegetic only: wind roaring past her ears, tyres crunching and drumming on packed dirt, suspension hissing through its stroke, fast freehub buzz and chain whir, stubble rattling the frame. No narration, no voiceover, no dialogue, no music. NEGATIVE / FAILED TAKE CONDITIONS — No slow motion, no hovering, no floating, no hang time longer than 1.5 seconds; any drifting or slow-motion feel = failed take. No front view, no side view, no face visible, no camera orbit = failed take. A second person or a second bike = failed take. A crash or a foot down = failed take. No summer clothing. No dark, dusk, foggy, sunset or night grading = failed take. No on-screen text, captions, logos or watermarks. No photoreal or 3D CG rendering. STYLE (locked): hand-drawn 2D anime, soft cel shading, lush painterly gouache backgrounds, crisp bright autumn noon, high-key daylight, luminous clear blue sky, warm radiant sunshine, glowing gold stubble, soft lens bloom, soft film grain, nostalgic hand-painted anime film look. Every frame bright, airy, well-exposed.

Cinematic anime clip, 20 seconds. Dark South American compound at night — concrete buildings, jungle surrounding, fire and explosions in background. One location. BARNEY: Use uploaded character sheet. Pistol. CHRISTMAS: Use uploaded character sheet.

えっちゃんがエキサイトなダンスをする、ダイナミックな15秒のモーショングラフィックスビデオを作成してください。 履歴書用のショーリールのような感じで、全力でやって。

Hand-painted anime film look, golden-hour light. A young woman in a sage-green knit cardigan stands in a sunlit bookshop aisle reading an open book, then slowly lifts her gaze toward the window with a dreamy smile. Very slow push-in.

A cute 3D anime fantasy elf warrior girl, white braided hair, animal ears, blue eyes, freckles, cheek war paint, fur trim leather armor, feather cape, sword, Pixar/DreamWorks style, 8k cinematic lighting. Video Prompts: 1. Wake Up: 3D animation close-up, cute elf girl under fur blanket, magic glowing particles, opening big blue eyes, warm cozy cottage light. 2. War Paint & Prep: Fantasy girl splashing water from wooden bowl, putting black war paint on cheeks, braiding white hair, cinematic close-up, golden light. 3. Armor Sequence: Close-ups of tightening leather boots, strapping dragon shoulder armor, wearing feather cape, dynamic camera angles. 4. Planning & Eating: 3D anime elf girl eating bread at wooden table, looking at fantasy map, thoughtful expression, warm dusty morning light. 5. Sword & Departure: Elf girl pulling sword from scabbard, grabbing bag, opening wooden door, bright golden backlight, cinematic entrance. 6. Final Hero Shot: Medium close-up of white-haired elf warrior at doorway, sunset backlight, feather cape swaying, determined look turning into a smile.

Create a cinematic anime battle sequence, 16:9, with premium hand-drawn cel animation and ultra-fluid sakuga-style movement. At a ruined ancient Japanese torii gate during a blazing crimson sunset, a white-haired swordsman in a torn white haori stands facing a towering shadow-black demonic warrior with glowing red eyes and smoky tendrils. 0–2s: Wide dramatic shot. Both warriors face each other beneath the giant torii gate, dust and debris floating through the air, huge orange sun directly behind them. 2–4s: Fast cinematic push-in to the white-haired swordsman’s face. His eyes glow intense red as he tightly grips his black katana. Wind moves his hair and clothing. 4–7s: He suddenly launches forward at extreme speed and clashes swords with the demon. Explosive white-blue lightning, sparks, shockwaves and a brilliant curved energy slash tear across the frame. Dynamic anime camera movement and strong motion lines. 7–8s: The swordsman completes one clean finishing slash. The demon breaks apart into swirling black smoke, glowing red embers and particles. 8–10s: Final wide rear shot: the swordsman stands completely still with his katana lowered, facing the enormous setting sun beneath the torii gate while the remaining dark particles disappear into the sky. Visual lock: dramatic red-orange sunset palette, deep black shadows, sharp anime linework, cinematic contrast, fluid 2D animation, consistent character design throughout, realistic cloth and hair motion, powerful impact frames, no extra characters, no character duplication, no text, no subtitles, no watermark.

Create a 30-second fast-paced cinematic Japanese anime cooking video showing the preparation of authentic katsudon, entirely from the text description below. IMPORTANT: Do not display, recreate, trace, reference, or imitate any storyboard, sketch, reference image, panel, annotation, or source material. Generate only original anime-style animation. STYLE High-quality Japanese anime film style, cinematic summer lighting, ultra-detailed food textures, realistic cooking physics, visible steam and moisture, shallow depth of field, macro close-ups, smooth camera movement, warm Japanese kitchen atmosphere. Fast rhythmic editing with natural match cuts based on movement, shape, texture, and composition. TIMELINE 0–2.5s — Prepare Pork Close-up of hands pounding a thick pork loin with a wooden mallet on a cutting board. The meat gradually flattens and its fibers loosen. Sprinkle salt and pepper evenly. Crisp rhythmic impacts. 2.5–5s — Bread the Pork Quick match cuts: press the pork into flour, dip into beaten egg, then firmly coat with coarse panko breadcrumbs. Show realistic egg dripping and breadcrumbs adhering to the surface. 5–7.5s — Fry Lower the breaded pork into hot golden oil. Intense bubbling surrounds the cutlet as the crust turns golden brown and crispy. Warm cinematic lighting and detailed oil movement. 7.5–9.5s — Slice Place the fried tonkatsu on a wooden board. A sharp knife cuts it into even strips. The crispy crust cracks naturally, revealing juicy white pork with gentle steam escaping. 9.5–12s — Simmer Dashi & Onion Thinly sliced onions gently simmer in amber dashi inside a shallow pan. Small bubbles rise while the onions become translucent. Chopsticks gently move them through the broth. 12–14s — Add Tonkatsu Place the sliced tonkatsu carefully over the simmering onions using chopsticks. The broth begins soaking into the crispy edges while steam rises. 14–16.5s — Pour Egg Slowly pour beaten golden egg over the tonkatsu and onions. The egg spreads naturally through the gaps and begins setting around the hot edges. 16.5–19s — Set the Egg Close-up of the egg gently coagulating over low heat. Edges become soft and golden while the center remains glossy, slightly runny, and trembling. No stirring. 19–21s — Prepare Rice A white ceramic donburi bowl receives a generous mound of steaming Japanese short-grain rice. The rice looks fluffy and slightly glossy. 21–24s — Assemble Carefully slide the egg-and-tonkatsu mixture from the pan onto the rice. The egg settles naturally in a soft wave while dashi lightly absorbs into the rice. 24–26s — Final Close-Up The finished katsudon rests on the counter. Glossy egg slowly settles over the tonkatsu and rice, gently trembling. Slow cinematic push-in. 26–30s — Hero Reveal Present the finished katsudon in a traditional blue-and-white ceramic bowl on a wooden surface. Golden egg cover

Create a music video where every frame is pure JavaScript. Tap the film to restyle live in browser. Trace manga into vectors and print as SVG. Every word on screen is live type.

この画像の女の子がエキサイトなダンスをする、ダイナミックな15秒のモーショングラフィックスビデオを作成してください。履歴書用のショーリールのような感じで、全力でやって。

暗いタクティカルギアを身にまとった、擬人化されたアニメ調のダルメシアンが、緑色に輝く植物のツタが交錯する近未来的な金属製の通路で、素早く正確なパルクールを披露していますダルメシアンはツタの下をスライディングでくぐり抜け、その先のツタを飛び越え、更にその先の縦状の駆け上がり、見事な制御の効いたバックフリップを決めて安全に着地します。ダイナミックなローアングルの追跡カメラ、サイドビューのアクションショット、光を反射する金属の床、緑色のネオンの輝き、漂うミスト、映画のような照明、滑らかで自然な動き、エネルギッシュなSFコメディ、AAA級ゲームのシネマティック映像、4Kワイドスクリーン。

“Cinematic cel-shaded 3D anime, semi-realistic CGI, 30-second Korean action sequence. Set inside a modern Korean university campus at night during a student festival. Neon Korean signs, lecture halls, lockers, staircases, convenience store, gymnasium and underground parking connected as one continuous campus environment. JUN-HO: 22-year-old Korean college student, messy black hair, oversized dark varsity jacket, white T-shirt, loose black trousers and sneakers. Bruised cheek, determined expression. Fast, athletic Korean action-movie fighting style. Always moving, sliding, vaulting, dodging and using the environment. SO-YEON: 21-year-old Korean college student, long dark hair, cream university jacket, jeans and sneakers. She has been kidnapped by four masked men and is desperately trying to escape. KIDNAPPERS: Four Korean men wearing dark streetwear and black masks. No firearms. Aggressive hand-to-hand fighting, grappling and coordinated attacks. Jun-ho notices So-yeon being dragged through a crowded campus corridor and immediately runs after the kidnappers. One attacker attacks him, but Jun-ho ducks the punch, grabs his jacket and drives him into a row of lockers. Another attacker rushes from the side, and Jun-ho spins around, blocks the attack and launches a powerful kick, sending him through an open classroom doorway. So-yeon breaks free and runs toward the stairwell, but another kidnapper catches her arm. Jun-ho grabs the stair railing, swings around it and knocks the attacker away. Inside the stairwell, two kidnappers surround him. He slides underneath one attack, rises behind them and uses the narrow staircase to throw one attacker into the wall. The chase continues into an underground parking garage. Jun-ho dodges several attacks between parked cars, grabs one kidnapper and slams him onto a car hood. So-yeon grabs a fire extinguisher and blocks the final attacker long enough for Jun-ho to recover. He rushes forward and knocks the attacker down with a fast hand-to-hand combination. Jun-ho and So-yeon sprint through the campus convenience store toward the exit, knocking over cardboard boxes and shaking shelves as students scatter out of their path. Jun-ho turns back for one final confrontation, defeats the last attacker and reunites with So-yeon outside the university entrance as security lights flash and campus security approaches. AUDIO: Intense Korean action-thriller orchestral score, heavy footsteps, shouting, lockers crashing, glass breaking, clothing movement, realistic impacts and distant campus ambience. STYLE: Cinematic cel-shaded 3D anime, semi-realistic CGI, Unreal Engine-quality rendering, Korean action-anime aesthetic, detailed facial expressions, realistic cloth and hair physics, dramatic rim lighting, bold cel-shaded shadows, cinematic depth of field, dynamic camera movement, motion blur, detailed Korean university environmen

Create a 15-second cinematic 2D anime sequence in a warm, nostalgic late-90s/early-2000s anime aesthetic. A loving family of three sits together in a cozy living room at night: a muscular bearded father with messy dark hair in a loose black shirt, a gentle mother with shoulder-length dark hair wearing a cream sweater, and their adorable young daughter with brown hair in two pigtails tied with pink ribbons, wearing a pink heart-print pajama top. Shot 1 — 0–4s: Wide establishing shot of the family relaxing together on a brown sofa in a warmly lit living room. The father sits comfortably with the little girl beside him while the mother sits close on the other side. Soft orange lamp light, natural shadows, cozy home interior. The child looks around curiously while the parents exchange subtle affectionate expressions. Shot 2 — 4–7s: Medium close-up of the father and daughter. The little girl shifts closer against her father while looking up at him with a playful, slightly stubborn expression. The father gently adjusts his arm around her. Subtle facial animation, natural blinking, small head movements and believable anime body motion. Shot 3 — 7–10s: Cut to the mother and daughter. The mother looks toward the child and speaks gently, raising one hand in a casual conversational gesture. The daughter looks up at her mother, listening attentively. Warm interior lighting gradually transitions toward cooler nighttime tones. Shot 4 — 10–12s: Transition to the bedroom at night. The same family is now lying together comfortably in a large bed under a blue-gray blanket. The father is on one side, mother on the other, and the little girl sleeps peacefully between them. Moonlight enters through the window, creating soft blue illumination. Shot 5 — 12–15s: Slow intimate close-up of the sleeping child, peacefully nestled against her father. Then gently shift focus toward the mother lying awake beside them. She gazes upward thoughtfully with a quiet emotional expression as the curtains move slightly from a soft nighttime breeze. Visual style: high-quality hand-drawn Japanese anime, expressive eyes, detailed hair strands, clean linework, subtle cel shading, cinematic composition, natural character animation, soft film grain, beautiful warm-to-cool lighting transition, atmospheric nighttime ambience, emotionally intimate family scene, consistent character designs throughout, smooth camera movements, shallow depth-of-field where appropriate. Negative prompt: photorealistic, 3D CGI, live action, plastic skin, distorted anatomy, extra fingers, extra limbs, inconsistent faces, changing hairstyles, changing clothing, character duplication, flickering, jittery animation, warped backgrounds, text, subtitles, watermark, oversaturated colors, excessive motion blur.

Created a dramatic top-down shot of a pink-haired anime-style girl falling through a futuristic glass skyscraper at night, surrounded by reflections, lights, and intense motion blur. The camera rapidly rotates and follows her descent, then cut to a dark close-up where she looks calm and mysterious. Show detailed shots of her pink outfit, clenched hand, and flowing hair. Build tension with cinematic lighting and deep shadows, then transition into a powerful final shot where she flies forward toward the camera with glowing golden eyes, wind blowing through her hair, bright warm light and wings-like energy behind her. Ultra-detailed 3D anime cinematic style, realistic motion, smooth camera movement, dramatic depth of field, high-quality lighting, dynamic action, consistent character design, epic cinematic atmosphere.