Start with the work. Trace it back to the maker and method.

【Style】Live-action + 2D hand-drawn hybrid creative short video (Live-Action × 2D Hand-drawn Animation), vertical 9:16, realistic home-shot texture (Photorealistic Home Vlog) + mirror reflection as flat cel-shaded hand-drawn animation (Flat Cel-Shading, Clean Linework), playful twist, 8K ultra HD 【Duration】12 seconds 【Scene】A bright modern home living room: light wood flooring, cream-white walls, a full-length dressing mirror with a thick black frame standing by the wall, a straw hat hanging beside the mirror, a low cabinet and the corner of a piano in the background, soft indoor natural light 【Character】Protagonist @Image 1 (strictly preserve the appearance, hairstyle, and pink dress with high heels from the reference image); the mirror reflection is a 2D hand-drawn animated version of the same protagonist: same face shape, same hairstyle, same outfit, flat color blocks + clean line art, movements synchronized with the live-action mirror image but with slight cartoon exaggeration (elastic limbs, 10% amplified motion) 【Rules】The live-action person always remains in the real space outside the mirror, and the reflection is always hand-drawn animation; during the two identity reversals, the spaces swap, but the style rules remain unchanged; outfit changes happen instantly on the beat, synchronized inside and outside the mirror [00:00-00:01] Shot 1: Opening hook (Hook Close-up) Close-up: the protagonist @Image 1 gives the camera a sly smile, turns sideways, and points to the dressing mirror behind her; a fast whip pan turns to the front of the mirror. [00:01-00:04] Shot 2: Mirror duet (Mirror Duet) Static medium shot, framing both the live-action side/back view and the mirror: the protagonist dances in front of the mirror wearing the pink dress from the reference image: pointing at the mirror, side kick, turn, hair-touch beat-hit movements. The reflection in the mirror is the 2D hand-drawn version of her, wearing the same pink dress, with mirrored synchronized movements, but each move ends with a slightly bouncy cartoon follow-through. On her feet are white socks with hand-drawn flats. Sound effects: upbeat pop dance music starts, with drum hits matching each beat-hit movement. [00:04-00:05.5] Shot 3: Reversal 1: stepping out of the mirror (Role Swap) On a beat accent: the hand-drawn girl steps one foot out of the mirror frame and stands in the foreground of the real room, keeping the line-art style unchanged and creating a stylistic contrast with the live-action floor; at the same moment, the live-action protagonist appears inside the mirror, holding the mirror frame and peeking out with a surprised expression. Sound effects: accented "boom" + playful "pop" sound as she exits the frame. [00:05.5-00:08] Shot 4: Outfit change 2: gray-toned streetwear (Outfit Swap 2) On another accent, the two instantly return to their original positions and change outfits in sync: the protagonist changes into a gray cropped hoodie + gray miniskirt + sneakers (face and hairstyle unchanged), with a high ponytail. The live-action person and hand-drawn reflection continue dancing in front of the mirror: hip twist, cross-step, knee lift. The cartoon version's movements are more exaggerated, and the skirt hem swings out in elastic arcs. Sound effects: the beat continues, with a "whoosh" sound at the outfit-change moment. [00:08-00:11] Shot 5: Outfit change 3: cream dress (Outfit Swap 3) Third beat-accent outfit change: pale yellow puff-sleeve puffy dress + brown ankle boots, twin ponytails. The two echo each other across the mirror: the live-action person puts her hands on her waist and sways her hips, while the hand-drawn version hops on one foot with an exaggerated smiling face; on the final beat, both freeze in the same pose at the same time. Sound effects: the beat builds to its highest point. [00:11-00:12] Shot 6: Cartoon ending (2D Ending) The hand-drawn girl steps out of the mirror frame again and strides toward the camera, occupying half of the foreground frame. She makes a playful "shh" gesture to the camera and winks; in the background mirror, the live-action protagonist smiles and waves. The image abruptly freezes to end, no fade-out. Sound effects: music stops sharply + one hand-drawn-style "ding".

Create a 15-second hyper-realistic cinematic luxury jewelry commercial in 16:9, featuring an elegant East Asian woman with long, glossy platinum-blonde wavy hair styled in a classic 1950s pin-up look, flawless porcelain skin, soft glamorous makeup, red lipstick, matching red nail polish, wearing a fitted red-and-white gingham halter mini dress with white piping and a heart-shaped bodice, white ankle-strap high heels, and a breathtaking luxury diamond necklace as the hero product. The necklace is the visual centerpiece throughout the commercial, sparkling naturally in warm golden sunlight with realistic diamond dispersion, premium craftsmanship, and elegant reflections. The setting is a spectacular Amalfi Coast-inspired cliffside road overlooking the turquoise Mediterranean Sea, colorful Positano hillside houses, stone walls, flowering bougainvillea, and a vintage black BMW 507 convertible with rich red leather interior and license plate DEMCDESIGN. Shot Breakdown 0–3s Extreme macro close-up of elegant white heels walking slowly across warm sunlit asphalt. The camera tilts upward just enough to reveal the diamond necklace shimmering against her neckline with every graceful step. Golden-hour sunlight creates brilliant sparkle across each gemstone. 3–6s She walks toward the vintage BMW 507 from behind. Smooth cinematic tracking shot. As she reaches for the chrome door handle, the camera briefly pushes in on the necklace as it catches the sunlight. She smiles softly and says: "Some jewels shine... this one tells my story." 6–9s She gracefully sits inside the convertible. Close-up through the side mirror as she gently adjusts her platinum-blonde waves while her necklace remains perfectly framed, glittering naturally. Elegant reflections dance across the polished gemstones. 9–12s Close-up of her hand inserting the key and pressing the classic start button. The engine starts with a refined vintage sound. She lightly touches the necklace with her fingertips and looks toward the sea. She softly says: "Rivelazione... elegance you'll always remember." 12–15s She slowly puts on luxurious white cat-eye sunglasses with subtle gold accents. Close-up beauty shot emphasizing the necklace resting elegantly on her collarbone. Soft wind moves her blonde hair while cinematic sunlight enhances every diamond sparkle. 15–17s Wide aerial tracking shot from behind as the black BMW 507 drives along the winding Amalfi Coast road overlooking the colorful seaside town, cliffs, beach, and turquoise sea. The necklace remains visible as she turns slightly toward the sunlight. Elegant cream-colored cursive typography fades into the landscape: Rivelazione "Reveal Your Brilliance." Premium luxury logo animation. Fade to black.

Create a 3D claymation-style animation of a cute caricature of Erling Haaland wearing Norway's red number 9 football kit, white shorts, red socks, and red boots, with his signature blonde ponytail, walking across a simple muted green background while carrying a giant leek on his shoulder and a bucket of harvested leeks. He stops at a dirt mound, digs a deep hole with a hand trowel, plants the giant leek firmly into the soil, pats it down, then takes out his smartphone, flashes a peace sign with a playful wink, and captures a celebratory selfie. Smooth, expressive character animation with whimsical, humorous, cinematic lighting.

15-second Japanese 2D hand-drawn anime cooking video, 12 scenes, generated from text only (no reference images or storyboard images). Visual style: Clean full-color Japanese 2D hand-drawn cooking animation. Soft pencil-like lines, gentle cel coloring, warm hand-drawn background, a cozy home kitchen with warm light from the stove flame, warm lighting that makes the cooking easy to read, visible shadows beneath tools and ingredients, rich steam animation, glossy highlights on red chili oil and thickened sauce, natural hand-movement timing, steady hands and utensils. Main subject: The cooking process for mapo tofu made in a wok. The color story moves in only one direction: from white tofu to glossy red-brown simmering sauce. Only hands, ingredients, and tools appear. Do not show faces, eating scenes, or character reactions. Scene structure (one main action per scene. The tofu corners remain sharp until the end and do not collapse or restore themselves): 1 (0.00–1.25) Close-up: Silken tofu rests on an open palm while a knife carefully cuts it into even cubes. The blade moves slowly, and the hand stays steady and safe. A quiet, precise process cut. 2 (1.25–2.50) Overhead: The tofu gently slides from the palm onto the cutting board and lines up in clean white rows. 3 (2.50–3.75) Side medium shot: Ground pork sizzles in a heated wok, broken apart with a ladle until crumbly, as the fat turns translucent. 4 (3.75–5.00) Close-up highlight: The moment doubanjiang and douchi touch the ground pork, deep red chili oil spreads across the wok like a flower blooming. A vivid one-direction burst of color. 5 (5.00–6.25) 45-degree angle: Minced garlic, ginger, and chopped scallions are mixed in. Everything glows in the red oil. 6 (6.25–7.50) Side view: Stock is poured from a bowl, the red-brown liquid level rises, and it begins to simmer with small bubbles. 7 (7.50–8.75) Overhead: The white tofu gently slides from the cutting board into the simmering red sauce. The corners remain intact, and the tofu floats softly. 8 (8.75–10.00) Close-up: The back of the ladle slowly and carefully pushes the tofu, coating it with sauce without breaking a single piece. 9 (10.00–11.25) Close-up highlight: As potato starch slurry is poured in a circle, the sauce visibly thickens, becomes glossy, and wraps each piece of tofu. A satisfying moment where the texture changes. 10 (11.25–12.50) Side close-up highlight: On the thickened glossy surface, large, slow bubbles swell and gently burst while steam rises with a wavering motion. An image where you can “hear” the bubbling even without sound. 11 (12.50–13.75) 45-degree angle: For the finish, chili oil is drizzled in a circle and a pinch of ground Sichuan pepper is scattered. The grains settle on the glossy sauce. 12 (13.75–15.00) Overhead: The finished mapo tofu quietly simmers in the wok: sharp-edged white tofu shows through glossy red-brown sauce, steam rises, and the green chopped scallions stand out. A short, beautiful, warm final cut with a natural tempo, without dramatic slow motion or excessive zoom. Camera: Change distance, angle, and height from scene to scene as if a person is moving around the stove: close for tofu cutting, side view for wok work, overhead for finishing. Within each scene, keep the camera calm. Do not show the finished dish until scene 12. Physical continuity: Keep the wok, ladle, cutting board, and tofu size consistent across scenes. Maintain ingredient continuity. The tofu does not collapse, multiply, or return to a previous state even after simmering. The sauce color only deepens in one direction and does not become pale again. Steam always rises upward. Keep gravity and liquid flow realistic. Follow a natural recipe order. No sudden state changes. Prohibitions: Finished dish at the beginning, repeated shots of the finished plated dish, title text, captions, subtitles, logos, watermarks, readable labels, live action, photorealism, 3DCG, clay animation, plastic toy style, game render, ultra-realistic food photography, AI morphing, flicker, distorted hands, extra fingers, floating utensils, floating ingredients, restored collapsed tofu, impossible knife movements, reverse-direction cutting, disappearing wok, shape-shifting wok, incoherent ingredients, raw ingredients appearing after heating, reversed cooking order, sauce color returning to pale, reveal of the finished dish before the final scene, messy background, faces, eating characters, character reactions, person taking a bite, dialogue, narration, BGM.

A highly realistic 12-second vertical UGC-style commercial filmed on a smartphone in a bright modern kitchen. A cheerful young creator holds up a pack of fresh premium meat and says excitedly, "You have to see how fresh this is!" As the package is opened, a mischievous orange cartoon cat with expressive eyes quietly sneaks toward the counter while a tiny clever brown mouse pops out and grabs a small piece of meat, triggering a funny, fast-paced chase. The creator laughs naturally while seasoning and cooking the meat in a sizzling pan. Cinematic macro shots show juicy texture, bubbling juices, golden caramelization, and rising steam. The cat and mouse comically stop, mesmerized by the delicious aroma, while the creator takes a bite, smiles directly at the camera, and says, "Now that's seriously delicious!" End with the product pack in focus and the text: "Fresh Taste. Every Bite." Ultra-realistic food details, natural handheld camera movement, authentic UGC vibe, warm daylight, soft shadows, HDR, 4K, lifelike textures, realistic physics, smooth transitions, energetic pacing, premium commercial quality.

Cinematic vertical 9:16 beauty vlog style, 4k resolution, ultra-realistic textures, clean lighting, and smooth camera stabilization. ​Scene & Timeline Choreography ​00:00 - 00:02 ​Visual: A young woman with short, platinum-blonde hair and a glowing complexion looks directly into the camera with an excited expression inside a bright, modern white-tiled bathroom while holding a small yellow rubber duck under her chin. ​Voice Over: (Playful, surprised intake of breath or light chuckle) ​00:02 - 00:05 ​Visual: She smiles warmly while looking down at the yellow rubber duck in her hand, then looks back up toward the camera with a playful expression. ​Voice Over: "Okay, wait..." ​00:05 - 00:07 ​Visual: She brings a bottle of orange skincare serum up close to the camera, showcasing the label clearly while speaking with an enthusiastic expression. ​Voice Over: "I literally cannot believe how good this is." ​00:07 - 00:08 ​Visual: A close-up shot of her hands dispensing a drop of the translucent, glossy serum onto her fingertip and rubbing it gently against her palm. ​Voice Over: (Soft ambient bathroom sounds / gentle product texture application) ​00:08 - 00:10 ​Visual: Close-up of her face as she gently pats and applies the serum onto her cheek, highlighting her radiant skin and smooth application. ​Voice Over: "Look how it just melts in..." ​00:10 - 00:13 ​Visual: Medium shot showing her full outfit—an off-the-shoulder white long-sleeve top, dark brown leather shorts, and white thigh-high stockings—standing by the bathroom counter with plants and a towel, gently touching her glowing cheek. ​Voice Over: "...my skin already feels insane." ​00:13 - 00:15 ​Visual: She holds up the orange serum bottle again, flashing a wide, radiant smile directly at the camera while speaking excitedly. ​Voice Over: "Okay, I'm obsessed. I'm not going back!"

Poetic xianxia deadpan reversal comedy 【Style】 Poetic xianxia deadpan reversal comedy, realistic live action, authentic cinematic HD texture. Use classical Chinese painting-style composition, restrained wuxia performance, soft morning mist, low-saturation jade green and ivory tones, and elegant, stable camera movement. The first half creates a solemn atmosphere of "profound qinggong and abundant immortal aura"; the second half completes a deadpan reversal through a visual reveal, exposing the immortal image the female lead has carefully maintained. The entire film is set in a purely ancient Chinese world, with no modern objects, modern language, modern architecture, modern sound effects, or modern design elements. The comedy relies on clear spatial relationships, setup, camera reveal, and calm character punchlines. Avoid exaggerated goofy performance. 【Duration】 15 seconds, three-shot structure, 2 people on screen. 【Aspect Ratio】 16:9 horizontal, 24fps. 1. Scene Setting 【Scene】 Beside a secluded mountain gate lotus pond in the early morning. The calm dark-green water reflects an old willow, slowly drifting thin mist, a white stone platform, a distant wooden waterside pavilion, scattered lotus leaves, and weathered stone lanterns. Throughout the entire film, maintain the same lotus pond, the same weeping willow, the same thin mist, the same white stone platform, the same distant waterside pavilion, and the same arrangement of lotus leaves. The spatial relationship must remain stable and clear, making it easy to reveal the true positions of the underwater stone posts at the end. 2. Character Lock 【Character A | Sword Immortal Senior Sister】 East Asian woman, 25-30 years old. Oval face, fair natural skin tone, dark almond eyes, long black hair half-pinned up with a white jade hairpin, tall and slender build. Fixed outfit: white embroidered silk hanfu, translucent layered wide sleeves, pale silver waist sash, jade pendant, white cloth boots. Temperament is cold, confident, restrained, always trying to maintain the bearing of a master. 【Character B | Junior Sister】 East Asian woman, 20-25 years old. Round, lively face, black hair in braids, petite figure. Fixed outfit: teal linen hanfu, dark cloth belt, wooden hairpin, black cloth shoes. Temperament is sincere, natural, and admiring of the senior sister, but the final punchline is calm and direct, creating a deadpan comedic effect. 3. Storyboard Design 【Shot 1 | 0-5s】 【Camera】Low-angle wide shot, lateral tracking 【Main Action】The sword immortal senior sister walks lightly across the water Beside a secluded mountain gate lotus pond in the early morning, thin mist floats over the calm dark-green water. There is a white stone platform by the bank, a wooden waterside pavilion in the distance, scattered lotus leaves, and a gently drooping old willow. The same sword immortal senior sister walks from left to right across the water, fully visible from shoes to head, hands clasped behind her back, chin slightly raised. Every step appears weightless, her posture elegant and steady. The same junior sister stands on the white stone bank, looking up at her with heartfelt admiration. The camera tracks laterally from a low angle, with smooth and restrained movement, emphasizing her seemingly "trace-free water walking" immortal aura. 【Sound】 Solemn guqin, slight morning breeze, tiny ripples on the water, distant birdsong. 【Shot 2 | 5-10s】 【Camera】Medium side tracking shot 【Main Action】The junior sister asks a question, and the senior sister answers solemnly The same junior sister follows along the bank, looks up, and asks: "Senior Sister, is this trace-free water walking?" The same sword immortal senior sister maintains a calm, profound smile and answers: "When the heart is free of dust, the water naturally bears the body." She continues stepping forward, the same pair of white cloth boots landing precisely on the seemingly empty water surface. The background always maintains the same lotus pond, the same weeping willow, the same thin mist, white stone platform, and distant waterside pavilion. The shot rhythm is unhurried, emphasizing the illusion that "she really seems able to walk on water." 【Sound】 Dialogue uses native Mandarin Chinese, with accurate lip sync. The guqin continues, and the ambience keeps a quiet early-morning feel. 【Shot 3 | 10-15s】 【Camera】Low close-up at water level for the reveal, then hard cut to an extreme close-up 【Main Action】Reveal the underwater stone posts and complete the reversal The camera lowers to the height of the lotus pond surface, clearly revealing a row of square stone posts arranged in a straight line beneath the water. The same sword immortal senior sister is actually stepping precisely on these stone posts without missing a step; she is not truly walking without leaving traces on water at all. The same junior sister lifts the last stone post by her feet, which has not yet been placed into the water, and says expressionlessly: "Senior Sister, are we still moving the rest of these stone posts tonight?" The guqin abruptly stops on a clipped note. Then hard cut to an extreme close-up of the sword immortal senior sister. Her eyebrow twitches lightly, the masterful smile she had been trying to maintain freezes instantly, and a small drop of sweat appears beside her temple. A lone frog croak comes from the distance. The image lingers on the moment when she forces herself to stay calm but has clearly lost composure, then ends. 4. Performance Requirements 【Sword Immortal Senior Sister】 For the first 10 seconds, she must always maintain a cold, profound, restrained, confident immortal posture. After the reversal, do not exaggerate by jumping around or shouting. The humor comes from micro-expression failure. Key details: slight eyebrow twitch, frozen smile, sweat appearing, brief stiffness after wounded dignity. 【Junior Sister】 Sincere admiration in the first half. The final punchline should be calm and natural, as if she is seriously asking a practical question. The calmer the tone, the stronger the comedic effect. 5. Technical Execution Requirements 【Continuity Requirements】 The three shots must occur continuously in the same scene Characters' faces, hairstyles, clothing, and body proportions remain stable throughout Senior sister always moves from left to right Junior sister always follows along the bank The positions of the underwater stone posts must strictly correspond to the earlier places where the senior sister stepped Do not add extra characters No shot jumps, character teleportation, background drifting, or disappearing props 【Physical Effects Requirements】 The physical effects of the water surface, thin mist, reflections, lotus leaves, hair, and silk fabric are realistic When the water surface supports the footsteps, there should be subtle natural feedback When revealing the stone posts, the water's transparency, refraction, and the positions of the stone posts must be clear and believable The details of the sweat, hair strands, and fabric should match close-up cinematic quality 【Sound Requirements】 Native Mandarin Chinese dialogue Accurate lip sync Do not generate subtitles Do not use any modern notification sounds or modern music Sound effects should only include guqin, morning breeze, water sounds, birdsong, distant frog croak, and other ancient-style environmental sounds 【Editing Requirements】 Elegant and stable camera movement Clean shot transitions Shot 3 uses a clear hard cut from reveal to close-up The ending pause is clean, preserving the lingering feel of the deadpan reversal 6. Negative Prompt blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, subtitles, captions, logo, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, hairstyle, face morphing, unstable face, background shift, glitching cuts, disappearing props; extra people, duplicated body, duplicated props, broken continuity, floating objects without logic, wrong lip sync; modern objects, modern architecture, modern costume details, modern language, modern sound effects, electronic sounds

A clay pirate captain duck with a tiny hat, wooden sword, eye patch and dramatic pose Sails across a bathtub ocean, battling giant soap waves and riding a sponge ship toward a rubber duck treasure island Bathroom fantasy world with bubbles, towels as cliffs and warm light reflecting on water 3D clay , Pixar-style playful adventure, soft clay textures, rounded props, dynamic camera glide over water, bright cheerful atmosphere, ending with the duck discovering a golden bath plug treasure.

15-second 2D animated video. Camera is completely steady and static the entire time. On the large green chalkboard in a elementary classroom, two simple white chalk stick figures are drawn facing each other (male on the left, female on the right with a ponytail). Sequence: 0–5 seconds: The male stick figure (left) reaches behind his back and pulls out a white chalk-drawn flower. He gently offers the flower to the female stick figure. Small white chalk hearts appear around them. The female stick figure becomes shy and kilig, covering her face slightly with one hand while little hearts float up. All hearts and effects stay strictly inside the green chalkboard. 5–7 seconds: Sudden pause. Both stick figures freeze for a moment. 7–15 seconds: They suddenly drop into intense karate fighting stances. The two stick figures start a very intense chalk-drawn karate fight — fast punches, high kicks, spins, and dramatic poses. White chalk motion lines, impact stars, and dust effects appear with every hit. All motion lines, stars, dust, and graphic effects remain completely inside the green chalkboard and never go outside the board edges. Everything stays as white chalk drawings on the green board. The classroom background, desks, chairs, and posters remain completely still and unchanged. No camera movement. Clean 2D animation style, simple chalk line art, white chalk only, highly detailed motion, 15 seconds. Negative prompt: 3D, realistic people, moving camera, colored chalk, effects going outside the board, changing background, blurry, low quality

Cinematic 10-sec sourdough recipe timelapse. Hands + ingredients only, NO faces. Warm natural kitchen lighting throughout. [0:00-0:02] Overhead: Hands mixing flour and water in silver bowl, flour clouds puffing, shaggy dough forming. [0:02-0:04] Side shot: Hands kneading smooth dough on floured wooden board, rhythmic push-fold motion. [0:04-0:05.5] Overhead timelapse: Dough rising in clear glass bowl on marble counter, doubling in size. [0:05.5-0:07] Close-up: Blade scoring confident slash across round dough boule, surface opening cleanly. [0:07-0:08.5] Oven interior: Loaf baking on rack, warm amber glow, steam rising, crust turning golden. [0:08.5-0:10] Slow push-in: Baked boule on wire rack, steam rising, rustic ear crack, cinematic beauty shot. STYLE: Warm film tones, smooth dissolve cuts, slow push-ins, no shaky cam, wrists/hands only, soft window light from left, 9:16 widescreen.

A peaceful animated-style riverside forest picnic scene, with fresh ingredients gathered directly from nature. Hands scoop silver fish from a clear stream, pick and wash green vegetable leaves, and slice fish fillets and vegetables on a cutting board. Spices are sprinkled into an iron pot over a campfire, then fish, greens, and mushrooms are added and simmered in a clay pot into a rich, hot soup. Rice is served on a wooden table, paired with a glass of fresh coconut juice, while warm dappled sunlight filters down through the tree shadows overhead. Cinematic animated painting style, vivid colors, soft natural light, ultra-detailed, tranquil atmosphere, 4K

Anime visual reference sheet, Studio Ghibli art style, clean cream white background. Bold clean outlines, cel shading, pure 2D anime illustration. FOOD: Raw butter block, cold and pale yellow. Laminated dough with visible layered strata. Rolled out dough sheet, pale gold. Folded dough triangle, uncurled. Shaped croissant crescents on a tray, unbaked and pale. Egg wash brushed golden over dough. Finished croissant, deep golden brown, flaky shattered layers, steam rising, a torn piece showing honeycomb interior. TOOLS: Wooden rolling pin, bench scraper, pastry brush, proofing tray, oven interior glowing warm gold. COLOR PALETTE: Butter yellow #F4D58D, dough pale gold #EFDDB5, baked crust gold-brown #C68E3F, deep golden brown #8B5A2B, egg wash sheen #E8B84B, steam white #FAF8F3, shadow brown #4A2F1B. Bold anime outlines, cel shading, Ghibli bakery illustration style, multiple reference panels clearly labeled. Anime bakery short film, Ghibli pastry aesthetic, warm golden morning light, flour dust drifting in sunbeams, cozy bakery kitchen, 16:9. A series of rapid close-up macro shots: hands placing a cold butter block onto rolled dough, dough being folded over the butter and sealed at the edges, rolling pin pressing and elongating the dough in long even strokes, dough being folded into thirds in one smooth motion, rolling pin flattening the dough again into a long sheet, dough being rolled up tightly into a spiral, dough cut into triangles with a sharp knife, fingers rolling a triangle from base to tip into a crescent shape, shaped croissants being placed on a tray in a neat row, pastry brush sweeping golden egg wash across the surface, tray sliding into a warm glowing oven, close-up of croissants slowly puffing and browning under heat, layers visibly separating and flaking as they bake, croissants pulled from the oven golden and steaming, extreme close-up of a croissant being torn in half revealing airy honeycomb layers, steam curling up from the warm interior. Each shot lasts under one second, cinematic food film pacing, hyper-detailed anime illustration, warm amber and buttery gold tones throughout.

DV 16mm handheld camcorder POV, CHASE filming herself, occasionally propped against a fitting-room mirror. Natural hand shake, imperfect framing, delayed focus, clumsy zooms, tape blur/noise, bloomed vanity lights, flickering auto-exposure, muted contrast, realistic skin. Playful, energetic backstage fitting-room vlog with quick pacing. CHASE: Korean idol in her 20s, long straight black hair, dewy glass skin, coral lips, large eyes, slim. Wears two fully modest stage outfits (1: fitted long-sleeve top + tailored trousers, 2: high-neck dress over long-sleeve base layer), minimal jewelry. Backstage fitting room with mirror, garment rack, stylist off-camera, pins/fabric clips. Sequence: outfit 1 mirror turn ("Okay, first outfit—let's see."), smooths fabric ("I really like this fit."), stylist pins waist (ambient only), playful spin ("Moves pretty well!"), quick change to outfit 2 ("Now let's compare."), compares ("More elegant, but the first had better movement."), close-up thinking ("I genuinely can't decide."), selfie spin ending ("I'll let the team decide—see you on stage!"). Camcorder never visible.

Raw vertical iPhone footage style, real mobile phone recording shot on iPhone 16 Pro, natural bright daylight on a private clifftop, strong sun, endless horizon views, handheld with natural shake and micro movements, authentic phone camera look, no cinematic emulation, no film grain, no photorealism, looks exactly like a real influencer video posted on Instagram, natural vibrant colors. [IMAGE REFERENCES] No reference images provided. Generate a fully consistent female influencer: mid 20s, attractive, energetic Dragon Ball fan vibe, tanned skin, long dark hair in a high ponytail, wearing a stylish casual-luxury outfit with subtle yellow and green accents, very expressive and excited when showing details. [TIMELINE SECOND BY SECOND] 0-3s: [Handheld phone shot, natural shake] The influencer walks toward a modern luxury villa built on a private clifftop with 360º views. The villa has a distinctive rounded yellow and white design. Parked outside is a small, quirky luxury car in bright yellow. She points at it smiling: "Look at this. They actually made the car real." 3-6s: [Quick cut to main living area] She enters the bright open-plan living space. The entire back wall is glass with insane views of the sea and horizon. She gestures at the minimalist but warm interior and says: "Everything is designed so you feel like you're floating above the world." 6-9s: [Quick cut to garden terrace] She walks out onto a large circular terrace with perfectly cut grass and a small garden area. There’s a big round stone table in the center. She runs her hand over it and says: "This is where you sit and watch the clouds go by for hours." 9-12s: [Quick cut inside special room] She enters a round meditation-style room with floor-to-ceiling curved windows. The light fills the entire space. She turns slowly and says with a smile: "This room… you can literally see the whole world from here. No exaggeration." 12-15s: [Quick cut to edge of terrace] She stands at the very edge of the terrace, wind in her hair, with nothing but open sky and sea behind her. She looks at the camera and says: "Private clifftop villa. Feels like your own little planet. Would you live here?" [STYLE & QUALITY BOOSTERS] Real iPhone 16 Pro footage look, natural bright daylight, authentic mobile camera movement and slight shake, natural vibrant colors, coherent physics, stable character, real phone video quality, no film look, no artifacts, looks like genuine Instagram Reel footage shot on location.

Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D look, a moving oil painting, NOT clay, NOT puppets, NOT 3D. True 12fps, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding — even at full gallop the action steps pose to pose with the strobing cadence of hand-drawn animation. Constant painterly BOIL. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from <<<image_1>>>, the wolves from <<<image_2>>>, RIDER 1 from <<<image_3>>> riding HIS horse from <<<image_4>>> — the same lead rider and the same horse as one consistent pair throughout, never another horse, never another man. The dusk snowfield from <<<image_5>>>. Blizzard haze and blowing snow drift SMOOTHLY; figures, horses, wolves and drawn snow-spray effects step on twos with secondary action. DIRECTOR'S NOTES: 1/ THE SCENE — full-gallop chase in the dusk blizzard, brutal and fast. RIDER 1, the lead rider, chases a sprinting wolf, leans low off the saddle in the manner of a kok-boru player reaching for the ulak, seizes the wolf by the scruff — and the wolf twists and savages his arm. A second wolf hits him from his blind side. He is torn from the saddle at full speed and the pack swarms him. Savage, dynamic, with REAL PHYSICS and a visible causal chain — every wound has its on-screen cause. 2/ REAL PHYSICS AND CAUSALITY — the horse (<<<image_4>>>) gallops with true four-beat weight; RIDER 1 hangs low off the side of the saddle, one hand braced, reaching down; the wolf is a heavy animal — when seized it twists its WHOLE body mid-stride, and that twisting weight plus the clamping bite WRENCHES the rider off balance; the bite is shown on screen: jaws clamp and crush onto his forearm, tearing sleeve and flesh, dark blood — cause before effect, always; the second wolf launches from his blind side and slams full-body into his chest like a missile; torn from the saddle at gallop speed he hits the snow HARD and TUMBLES with momentum, rolling over and over, loose powder snow bursting around each impact (drawn snow-spray effects on twos), the riderless horse galloping on; the pack converges as a fast dark stream and swarms over him, a savage thrashing dark mass. 3/ BRUTALITY STAGED, NOT LINGERED — the violence is fast, hard and physical: the crunching bite, the dark blood across the snow, the swarming pack. Show the savagery through motion, dark mass and sound, not slow anatomical detail. 4/ AGGRESSIVE HANDHELD CHASE CAMERA — racing alongside at gallop, violently jolting with the speed, whipped by wind, jerky corrections, the horizon tilting and never level; on the fall a hard DUTCH TILT as the world goes over with him. Never gimbal-smooth, never tripod-locked. 5/ SECONDARY ACTION on twos — RIDER 1's chapan skirts and fur hat whipping with follow-through, the horse's mane and tail streaming, the wolves' fur rippling along their backs, harness swinging, breath-vapor of horse and man tearing off in the wind, snow bursting from hooves as drawn powder on twos. 6/ LIGHT — deep dusk in a blizzard, dim cold blue-grey storm light, soft, no rays, no beams, no god rays, the figures dark masses against the pale snow. Correct neutral white balance, NOT a blue filter, muted desaturated; the blood a dark muted red, stark on the snow but never glossy, never bright. SHOT 1 — FULL-GALLOP TRACKING, ~35mm, aggressive handheld racing alongside. COMPOSITION: RIDER 1 on his horse a large dark mass driving in from the RIGHT third, the sprinting wolf low ahead of him on the LEFT third, both tearing diagonally through the frame left-and-deeper — the diagonal of the chase as the line of dynamics; the pale storm-lit snowfield from <<<image_5>>> streaking past as negative space. RIDER 1 drops LOW off the side of the saddle in a kok-boru lean, one hand braced on the saddle, the other arm stretching down for the wolf's scruff, his chapan and the horse's mane whipping on twos, hooves throwing bursts of powder. He bares his teeth, hoarse over the wind, lips on twos: "Ustadym!.." His fist closes on the wolf's scruff — HARD CUT to SHOT 2 — CLOSE DYNAMIC, ~50mm, aggressive handheld slammed in tight: the wolf, seized, TWISTS its whole heavy body mid-stride in one violent stepped motion — and its jaws clamp CRUSHING onto RIDER 1's forearm, on screen, tearing through sleeve and flesh, dark blood whipping across the snow and the wolf's muzzle. His raw scream tears over the wind. The wolf's twisting weight and the bite WRENCH him sideways off his balance, his body dragged half out of the saddle, his fur hat ripping away with follow-through. Cause and effect brutal and readable, all stepping on twos. HARD CUT to SHOT 3 — MEDIUM WIDE with a hard DUTCH TILT, ~35mm, aggressive handheld: from his blind side a SECOND wolf launches — a dark missile — and slams full-body into his chest. Torn from the saddle at gallop speed RIDER 1 hits the snow HARD and TUMBLES, rolling over and over with real momentum, powder snow bursting at each impact as drawn effects on twos, the horizon tilted and reeling, his riderless horse (<<<image_4>>>) galloping on into the storm. And then the pack pours in — a fast dark stream of wolves from <<<image_2>>> out of the storm, varied coats, converging from all sides and SWARMING over him, a savage thrashing dark mass on the pale snow, dark blood spreading, snow scattering, his cries swallowed by the blizzard and the snarling. The dark mass of the pack traps and frames him. Hold one brutal beat in the howling wind. End. Audio: NO MUSIC — the roar of the blizzard, pounding gallop, the wolf's snarl and the wet crunch of the bite, the rider's raw scream, the heavy tumbling impacts, the converging snarls of the pack, the wind swallowing everything. No subtitles. Natural diegetic sound only, absolutely no music. Constraints: stop-motion stepped cadence on twos at 12fps with painterly boil even at full gallop, every action stepping pose to pose never gliding, NO smooth interpolation NO motion blur NO morphing, blizzard haze smooth while all figures animals and drawn snow-spray effects step on twos, hand-painted oil look from <<<image_1>>> not photoreal not 3D not glossy, three shots with hard cuts — full-gallop tracking with the kok-boru lean and the grab "Ustadym!..", close dynamic of the twisting wolf and the crushing on-screen bite with dark blood and the scream, dutch-tilted wide of the second wolf's full-body slam the hard tumbling fall at speed and the pack swarming him as a savage dark mass — RIDER 1 from <<<image_3>>> and his horse from <<<image_4>>> the SAME consistent pair in every shot never swapped, REAL PHYSICS AND VISIBLE CAUSALITY every wound caused on screen the wolf's twisting weight wrenching the rider the bite before the blood the slam before the fall the momentum carrying the tumble, AGGRESSIVE HANDHELD racing jolting wind-whipped horizon never level hard dutch tilt on the fall never gimbal-smooth, SECONDARY ACTION on twos chapan hat mane tail wolf fur harness breath-vapor all whipping with follow-through, wolves from <<<image_2>>> varied in coat tone size and stride never mirrored never cloned, deep dusk blizzard dim cold storm light soft no rays no beams, correct neutral white balance not a blue filter muted desaturated dark muted blood never bright never glossy, brutality fast hard and physical staged through motion dark mass and sound not lingering gore, spoken Kazakh in Latin transliteration pronounced as written, NO MUSIC only storm hooves snarls and screams.

Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, makeup, skin tone, body proportions, pearl choker, bracelets, rings, and facial consistency throughout every shot. Replace the jeans with a stylish white pleated mini skirt while keeping the fitted white sleeveless crop top. Maintain realistic hand anatomy and natural expressions. Create a premium 20-second mango juice commercial with a bright tropical summer aesthetic. The hero product is a realistic branded mango juice bottle with a vibrant orange label featuring fresh mango illustrations, green leaf accents, and a modern fruit juice logo. The bottle design remains identical in every shot. The video opens with the girl already on screen, smiling warmly while holding a fresh ripe mango beside her face. She playfully tosses the mango upward, catches it, and it seamlessly transforms into the branded mango juice bottle. She smiles confidently and says, "Taste summer in every sip." Cinematic macro shots highlight the premium bottle covered in sparkling condensation. Fresh mango cubes, juice splashes, and golden droplets burst around the bottle as sunlight reflects beautifully across the label. She takes a refreshing sip before walking through a vibrant tropical fruit market wearing her white crop top and pleated mini skirt. Smooth tracking shots capture her browsing colorful fruit stalls, smiling at vendors, and naturally carrying the branded juice bottle. The scene transitions to a lush mango orchard where she picks ripe mangoes straight from the trees while holding a basket of fresh fruit. She sits beneath the trees with friends enjoying a picnic, laughing together as everyone drinks from the same branded mango juice bottles. The final golden-hour scene shows her standing in the orchard with the sunset behind her. She extends the chilled mango juice bottle toward the camera with a bright smile and says, "Pure mango. Pure happiness." The camera slowly pulls back, revealing glowing mango trees, warm sunset light, and friends celebrating together. Style: Premium beverage advertising, luxury commercial cinematography, ultra-realistic fruit textures, realistic liquid physics, cinematic handheld and gimbal movements, shallow depth of field, vibrant tropical colors, glossy product photography, photorealistic 4K HDR, premium brand campaign quality, 16:9 widescreen. Negative Prompt: No text overlays, no subtitles, no watermarks, no distorted hands, no duplicate people, no deformed bottle, no AI artifacts, no blurry label, no low resolution, no cartoon style, no flickering, no oversaturated colors.

Create an ultra-realistic premium smartwatch commercial featuring the same young Korean woman throughout the entire sequence. Maintain identical facial features, shoulder-length soft ash-brown wavy hair, glowing glass skin, natural makeup, and body proportions in every shot. She wears a fitted white athletic crop top, high-waisted beige tennis skirt, white sneakers, delicate gold hoop earrings, and a premium silver smartwatch on her wrist. Bright summer morning, luxury lifestyle aesthetic, premium commercial cinematography, ultra-realistic storytelling. The video opens with the young Korean woman already in frame, smiling naturally toward the camera while walking through a beautiful tree-lined city street. As she approaches the camera, she gracefully raises her wrist toward the lens, revealing the premium smartwatch catching the warm morning sunlight. She gently taps the display, and the screen instantly lights up with an elegant animation. She smiles confidently and says, "Let's make today count." A cinematic macro hero shot showcases the smartwatch from every angle. Close-ups reveal the premium metal frame, crystal-clear display, rotating crown, textured strap, elegant reflections, and beautifully animated watch face as sunlight glides across the polished surface. She continues her morning jog through peaceful parks while the smartwatch tracks her pace, heart rate, calories, and distance. Smooth tracking shots capture her checking workout progress, receiving encouraging fitness notifications, and smiling naturally as she enjoys the run. The scene transitions to a stylish café where she effortlessly pays for her coffee using the smartwatch. Cinematic close-ups highlight the contactless payment animation, subtle wrist gestures, and premium design. Later she walks through vibrant city streets, using the smartwatch for navigation, controlling her music, reading messages, checking the weather, and setting reminders. Natural lifestyle moments show her confidently interacting with the watch without ever reaching for her phone. Golden hour arrives as she relaxes on a rooftop overlooking the city skyline. She raises her wrist toward the sunset, and the smartwatch display transitions into a beautiful golden watch face. Macro shots emphasize the premium craftsmanship, slim profile, sapphire glass reflections, and luxury finish. The final cinematic hero shot shows her smiling warmly toward the camera while gently holding her wrist forward, making the smartwatch the focal point. The camera slowly circles around her before pulling back to reveal the glowing city skyline bathed in golden evening light. Natural ambient audio only: birds chirping, footsteps, gentle breeze, smartwatch tap sounds, subtle notification chimes, café ambience, coffee machine sounds, city ambience, leaves rustling. No background music, no subtitles, no logos, no watermarks,

8K ultra HD, extremely detailed photography; the scene is set on an open-air observation terrace with glass railings on a high-rise, during blue hour at dusk. In the distance is a modern skyscraper city skyline just beginning to light up. A black civilian helicopter hovers in midair in the background, its lights on. Soft dusk ambient light, with the atmosphere of a luxurious tycoon-style gathering. Deep depth-of-field effect, with the distant city view softly blurred as atmospheric background support. Spielberg-level refined cinematic lens aesthetics, balanced and grand composition, no background music, no subtitles. Shot 1 | 00:00-00:02 Medium opening frame · arcing move left Medium opening frame. After a smooth opening, the camera slowly makes an arcing lateral move to the left. The second woman [@Image 1], a woman with supermodel poise, wears a champagne-beige long sparkling evening gown with a full floor-length skirt. The shoulders of the gown are embellished with fluffy white feathers. She stands at an angle, one hand lightly supporting her chin as she lowers her head in thought, then raises her eyes to look at the camera, her gaze filled with detachment. Reserve an out-of-focus hidden foreground area. The focus remains steadily locked on the second woman, with the foreground naturally blurred and clear depth layers. Shot 2 | 00:02-00:06 Rack-focus cut · extreme close-up of the first woman [@Image 2]. The camera continues its arcing lateral move left while simultaneously executing an ultra-fast foreground rack focus. The first woman is also wearing a champagne-beige long sparkling evening gown with a full floor-length skirt, with fluffy white feathers embellishing the shoulders. In the area of the foreground that was originally completely out of focus, the first woman turns her head and forms an extreme face-filling close-up from a low angle looking upward, crashing into the foreground and filling the frame. Her gaze is languid and lively, with naturally soft pink lips. In the background, the second woman lowers her head and closes her eyes, completely blurred and thrown to the far distance. The foreground and background create an extremely strong spatial pull and tension. Focus is precisely locked on the first woman’s face, with the background fully blurred. Shot 3 | 00:06-00:12 Diagonal pullback and rise · the camera continuously performs a large-scale diagonal pullback + rising crane movement, expanding the scene space step by step. The field of view enlarges exponentially with the camera movement. The first woman turns from the side to face the camera while crossing both arms in front of her chest, standing at the center of the frame with commanding, all-controlling dominance. The third woman [@Image 3] leans against the terrace railing at the far left of the frame. The fourth woman [@Image 4] stands second from the left with one hand on her hip. The second woman stands to the right of the first woman, turned sideways and looking back. The third and fourth women also wear champagne-beige long sparkling evening gowns. As the camera pulls back and gradually widens, a black civilian helicopter hovers in midair with its lights on. Shot 4 | 00:12-00:15 Grand wide ending frame, power freeze-frame Grand wide ending frame. After the camera has completely pulled back Video duration: 15 seconds

POV MiniDV camcorder vlog filmed entirely by the main character herself. The camcorder is never visible. Authentic early-2000s DV tape aesthetic with soft analog blur, subtle tape grain, faint tape hiss, slight colour bleed, blooming highlights, autofocus hunting, exposure breathing, muted contrast, imperfect white balance, realistic skin texture, natural motion blur, handheld shake, crooked framing, delayed focus, accidental head crops, awkward zooms, and genuine human camera movement. Documentary style, not cinematic perfection. Main Character: The same recurring fictional Japanese woman for every episode. Early 20s, very fair porcelain skin, naturally beautiful, long dark brown-black hair in a loose ponytail with soft face-framing strands, expressive brown eyes, natural makeup, slim petite build, oversized cream hoodie, black leggings, white sneakers, warm smile, playful and slightly clumsy personality. Location: Quiet Japanese neighbourhood during golden hour, tree-lined sidewalks, small local café, soft evening sunlight, peaceful atmosphere. Scene 1 (0–2s) Handheld selfie while leaving home. "Okay... today's mission is simple. One iced coffee... then straight home." Scene 2 (2–5s) Walking down the street. She notices a fluffy dog, crouches to pet it, laughs. "...No, stay focused... coffee first." Scene 3 (5–8s) Camera propped on the café counter. She reaches for her pocket to pay and suddenly freezes. "...Wait... where's my wallet?" Scene 4 (8–11s) Quick panic. She checks another hoodie pocket, finds it instantly, bursts into genuine laughter. "Never mind... false alarm!" Scene 5 (11–15s) Walking outside with the iced coffee during golden hour. Takes the first sip, smiles at the camera. "Mission accomplished... see you in tomorrow's chaos." Audio: No background music. Only authentic ambient sounds: birds, footsteps, distant traffic, café ambience, doors opening, soft wind, clothing movement, breathing, laughter, and natural voice. Overall feeling: Cozy, wholesome, funny, spontaneous, highly realistic, authentic camcorder diary, social-media-friendly pacing, emotionally warm, subtly humorous, and designed to feel like viewers are spending 15 seconds with a real person rather than watching a scripted video.

Create a premium UGC-style beverage commercial featuring a beautiful young woman with long silky dark hair, radiant skin, and a fresh natural look. Bright modern apartment, soft morning sunlight, clean minimalist interior, cinematic handheld camera, ultra-realistic lifestyle photography. The video opens with the woman smiling directly into the camera while holding an ice-cold sparkling fruit drink beside her face. She rotates the chilled can playfully in her hand as condensation glistens under the sunlight, then looks into the lens with an excited expression. She walks into the kitchen, pops the can open with a satisfying fizz, and immediately takes a refreshing sip. Cinematic macro shots capture sparkling bubbles, tiny water droplets, and cold vapor escaping from the can. Fresh lemons, strawberries, mint leaves, and ice cubes splash through the air in beautiful slow motion as the camera circles around the floating drink. Crystal-clear sparkling liquid pours elegantly into a glass filled with ice, creating refreshing splashes and rising bubbles. The woman enjoys another sip while relaxing beside a large window. She smiles naturally, closes her eyes for a moment, and enjoys the refreshing taste as sunlight highlights the cold drink and glowing skin. She heads outside for a sunny afternoon walk carrying the drink through a modern park filled with greenery. She laughs, enjoys the weather, and refreshes herself with another sip while walking. Cinematic tracking shots follow her naturally. The product becomes the focus with premium rotating hero shots surrounded by floating citrus slices, fresh berries, mint leaves, sparkling water droplets, and shimmering light reflections against a bright clean background. The final sequence shows the woman raising the chilled can toward the camera with a bright smile before taking one last refreshing sip. The camera slowly pulls back as she walks away through warm golden sunlight holding the drink. Style: premium UGC commercial, realistic lifestyle cinematography, luxury beverage advertising, macro product photography, cinematic handheld and gimbal shots, vibrant fruit colors, sparkling liquid effects, realistic condensation, shallow depth of field, photorealistic, 4K HDR, 16:9 widescreen. Negative Prompt: No text, no captions, no subtitles, no logos, no labels, no product branding, no watermarks, no duplicate people, no cartoon style, no distorted anatomy, no UI elements, no packaging text visible.

Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, makeup, skin tone, body proportions, white sleeveless fitted top, pearl choker, bracelets, rings, and outfit consistency throughout every shot. Replace the jeans with a stylish pleated grey mini skirt while keeping the same top and accessories. Maintain perfect facial consistency and realistic hand anatomy. Create an 8-second premium UGC lipstick commercial with elegant beauty cinematography. Warm blush-pink studio background, soft diffused lighting, luxury skincare aesthetic, shallow depth of field, cinematic commercial color grading, photorealistic 4K HDR. Shot 1: Medium beauty shot. She looks directly into the camera while holding a luxury lipstick beside her face with a confident smile. Shot 2: Cinematic macro close-up of the lipstick rotating slowly in her hand. Metallic reflections shimmer across the premium packaging. Shot 3: Close-up as she naturally applies the lipstick to her lower lip while looking into a mirror just outside the frame. Shot 4: Extreme macro of glossy lips. She gently taps her lower lip with her fingertip to blend the product, revealing smooth hydrated texture and natural shine. Shot 5: Side-profile beauty shot. She smiles softly while holding the lipstick near her chin as her hair moves gently from a soft breeze. Shot 6: Full-body shot. Wearing the white fitted sleeveless top and grey pleated mini skirt, she confidently walks toward the camera through a minimalist luxury studio while holding the lipstick naturally. Shot 7: Beauty close-up. She slightly tilts her head, raises the lipstick beside her cheek, and smiles confidently as soft golden highlights illuminate her face. Shot 8: Hero ending. Elegant close-up of her face beside the lipstick. She lowers the lipstick slightly, maintains eye contact with the camera, gives a subtle confident smile, and the camera slowly pushes in before fading out. Style: Premium UGC beauty commercial, luxury K-beauty aesthetic, realistic skin texture, glossy lips, elegant natural expressions, cinematic handheld and gimbal movements, macro beauty shots, soft bokeh, commercial-grade lighting, photorealistic, ultra-detailed, 4K HDR, 24fps. Negative Prompt: No text, no subtitles, no logos, no watermarks, no kissing, no duplicate people, no distorted hands, no deformed lips, no low resolution, no AI artifacts, no cartoon style, no exaggerated makeup, no extra fingers, no flickering, no oversaturated colors.

Main Subject: Young Korean woman, 22, natural appearance, shoulder-length dark brown hair tied in a loose ponytail with wispy bangs. Wearing a light blue oversized hoodie, black cycling shorts, white sneakers, and a small grey crossbody bag. Minimal makeup, realistic skin texture, warm personality. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Quiet bicycle path beside the Han River during a sunny spring afternoon. Cherry trees, green grass, wooden benches, cyclists, joggers, gentle river breeze, distant city skyline, peaceful atmosphere. Visual Style: Ultra-realistic documentary realism. Genuine candid behavior, natural body language, authentic everyday life. Camera Style: Early-2000s Sony MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting, exposure pumping, faded colours, soft contrast, slight motion blur, DV compression artifacts, no stabilization. 00:00–00:03 She unlocks a silver city bicycle beside a wooden bench, smiling as wind moves loose strands of hair. Camera briefly focuses on the handlebars before correcting. 00:03–00:06 She rides slowly along the riverside path. The camera jogs behind, shaking naturally while struggling to keep her centred. 00:06–00:09 She stops beside the river, parking the bike. Resting both hands on the handlebars, she quietly watches the water while cherry blossom petals drift past. 00:09–00:12 She drinks from a small bottled water, brushes hair behind her ear, and laughs softly after noticing the camera. 00:12–00:15 She gets back on the bicycle, waves casually toward the camcorder, and rides away as the operator lowers the camera. Recording cuts abruptly to black. Audio: Natural ambience only—birds, bicycle wheels, wind, distant conversations, footsteps, leaves rustling, flowing river, occasional bicycle bell. No music or narration. Goal: A forgotten MiniDV home video from 2004 capturing a peaceful afternoon bicycle ride along the Han River, warm, imperfect, nostalgic, and completely believable.

Style: Brutal martial arts duel, no weapons, realistic combat, elite warrior level, lightning-fast choreography, readable action, no comedy, no floating, no anime physics, every hit carries weight and momentum. Cinematic Style: ARRI Alexa Mini LF, anamorphic lens, professional action cinematography, dynamic camera language, layered composition, deep composition, high-speed action film pacing, cinematic motion blur, dramatic volumetric lighting, dust, debris, realistic body mechanics. Shot 1 (0s-2s) Extreme wide shot, ruined stone temple interior, foreground broken pillars framing both fighters on opposite sides of the frame using rule-of-thirds composition. Low-angle push-in. Wind blows through the temple. Both warriors instantly explode into motion and sprint toward each other at full speed. Shot 2 (2s-4s) Tracking side shot. @image1 launches a flying spinning kick. @image2 ducks underneath at the last second. Camera whip-pans with the movement. Dust erupts from the floor. Fast but readable action. Shot 3 (4s-6s) Dynamic orbit shot. @image2 grabs @image1's leg mid-air, pivots his hips, and throws him across the temple floor. @image1 lands on one hand, uses the momentum to perform a full backflip recovery without stopping. Camera follows continuously. Shot 4 (6s-8s) Split lens composition. @image1 sharp in foreground charging forward while @image2 remains equally sharp in the distant background preparing a counterattack. Both collide in a rapid exchange of punches, elbows, knees, and spinning strikes. Camera aggressively pushes through the action. Shot 5 (8s-10s) Low-angle tracking shot. @image2 attempts a devastating spinning heel kick. @image1 slides underneath the kick, grabs the supporting leg, lifts, rotates, and slams @image2 into a stone pillar. Debris explodes across the foreground creating strong depth layers. Shot 6 (10s-12s) Handheld-style combat intensity without excessive shake. Both fighters unleash a relentless combination of punches, elbows, knees, shoulder strikes, sweeps, and acrobatic counters. Backflip evasion, spinning recovery, rapid footwork. Every strike narrowly misses or lands with visible impact. Shot 7 (12s-14s) Heroic orbit shot around both fighters. They sprint toward each other simultaneously. One launches a jumping knee strike while the other performs a rotating aerial kick. Both attacks collide in mid-air. Shockwave bursts outward through dust and debris. Shot 8 (14s-15s) Extreme low-angle hero shot. Both land several meters apart. Silence. Dust falls from the air. Camera slowly pushes in. Neither fighter breaks eye contact. End before revealing the winner.

Immersive first-person spaceship cockpit perspective, no visible pilot, no HUD, no interface, only the view through the canopy. The spacecraft launches into deep space with overwhelming acceleration, immediately performing violent high-G maneuvers. The camera dives through a dense asteroid field at impossible speed, snap-rolling between spinning boulders, knife-edging through razor-thin gaps, then slingshotting around a colossal ringed planet only meters above its atmosphere. It instantly transitions into a corkscrew climb through the wreckage of an ancient megastructure orbiting a dying star, weaving through gigantic rotating space stations, shattered capital ships, and kilometer-wide debris fields. Every movement is unpredictable,rapid S-turns, barrel rolls, split-S reversals, vertical dives toward black holes before pulling away at the last instant, power loops around luminous neutron stars, wall-hugging passes along enormous alien megastructures, and gravity-assisted slingshots around planets. The spacecraft flies through glowing wormholes, crystalline nebulae, collapsing stars, and colossal cosmic rings stretching for thousands of kilometers. Giant planets fill the entire sky, binary suns ignite the horizon, lightning storms rage inside colorful nebula clouds, and impossible alien architecture floats silently through space. The final acceleration becomes relentless as the ship races through an immense rotating Dyson sphere, threads the center of gigantic energy rings, narrowly avoids collapsing fragments of planets, and enters a tunnel of distorted spacetime where galaxies stretch into brilliant rivers of light before exploding into an infinite cosmic panorama filled with countless stars and celestial giants. Continuous first-person flight, no cuts, relentless acceleration, extreme high-speed FPV, aggressive banking, rapid direction changes, barrel rolls, corkscrews, split-S maneuvers, knife-edge turns, gravity slingshots, realistic inertia, cinematic motion blur, volumetric cosmic dust, dynamic lighting, hyper-detailed space environments, breathtaking sci-fi spectacle, blockbuster VFX, IMAX quality.

[CONDITION DEFINITION] 1:1 square, 15 seconds, no reference image. A cinematic luxury miniature diorama formation montage in which a harbor town rapidly assembles across an entire vast island. The direction should feel not like a cheap toy, but like a premium handmade diorama, high-end collector toy, or precision model for film shooting. Keep the cuteness, organized beauty, and model-specific sense of fun, while creating a grand sense of scale as the whole island spreads out widely. Show bright, clear daylight, blue sea, white waves, red, blue, and white roofs, wooden piers, stone quays, lighthouse, bridges, canals, hillside townscape, and multiple harbor districts. The main subject is not people, but the giant harbor island diorama itself. No text, logo, watermark, or subtitles needed. [SHOT/FLOW] 0.0-3.0 seconds: Start from a wide-angle high overhead shot. Show the entire large island surrounded by blue sea, not a small tabletop garden. On the empty island terrain, the coastline, bay, breakwaters, cliffs, hills, harbor entrance, canals, multiple quays, bridges, main roads, and outlines of stepped city blocks appear at high speed, first completing the large skeleton of the island and harbor all at once. From the start, show the breadth of the open sea, bay, hills, and harbor, avoiding a cramped impression. 3.0-6.5 seconds: While keeping the wide angle, the camera gently descends and moves forward toward the harbor side. Wooden piers, stone paving, stairs, railings, warehouses, fishing-gear huts, canal-side buildings, rows of houses with red, blue, and white roofs, and narrow roads leading up the hill assemble rhythmically as if clicking into place. Do not move in too close; always keep a composition where the depth of the harbor, hills, and open sea is visible. 6.5-10.0 seconds: Add a natural scene transition and move to a medium-distance shot of the harbor. Details such as multiple piers, small boats, sailboats, mooring ropes, wooden boxes, small cranes, streetlights, flags, bridges, canals, stone joints in the quays, and pier planks are completed in succession. This is the scene that most strongly shows the satisfaction of formation, but do not focus only on close-ups of small props; show the entire broad harbor district rapidly gaining density. 10.0-12.5 seconds: Show the lighthouse, hillside townscape, multiple harbor districts, and bay leading out to the open sea. The lighthouse is completed, and roofs, windows, bridges, streetlights, boats, and flags are arranged as the final touches, bringing the vast harbor island diorama close to its finished form. Here, strongly show the island’s sense of scale once again. 12.5-15.0 seconds: The completed harbor island comes to life. The water surface sparkles, small boats sway slightly, flags and ropes flutter in the wind, the lighthouse beam slowly rotates, and windows and streetlights softly turn on. End with a grand wide-angle full view pulled far back. Include the harbor, hills, lighthouse, multiple piers, and open sea, closing on the lingering feeling of a large premium diorama island cutely beginning to breathe. [CAMERA/EDITING] Emphasize wide-angle camera work and always convey the breadth of the whole island. Begin with a high overhead view, then descend forward, pass close along the harbor, lightly orbit around the lighthouse, and finally pull back to a large full view. Include 2-3 natural scene transitions within 15 seconds. Close-up cuts are allowed, but do not get so close that it looks only like a small toy. Layer foreground, middle ground, and background to create compositions where the harbor, hills, lighthouse, and open sea can be seen at the same time. Keep the tempo fast and emphasize the satisfaction of formation. Avoid monotonous straight-line movement and long static shots. [SOUND] Include BGM and sound effects. The BGM is bright, refreshing cinematic music with a slight sense of adventure. It supports the excitement of the premium diorama coming together, but is not too flashy. Sound effects include small assembly sounds, wood and stone fitting into place, light clicks, water sounds, wave ripples, rope and flag sounds, boat creaks, distant seagulls, and small mechanical sounds from the lighthouse. No dialogue, no narration. [NEGATIVE] Avoid an island that is too small, a cramped tabletop garden, cheap toy feel, cheap plastic feel, rough craft feel, narrow harbor, a town with only a few houses, compositions with no sense of scale, dark overcast sky, muddy sea, real-size giant humans, making people the main subject, text, logo, watermark, subtitles, monotonous straight-line camera, or an ending that simply stays completely still after completion.

Create a 15-second seamless architectural space renovation animation. The camera remains completely fixed in the exact same position, angle, focal length, perspective, and composition throughout the entire video. No camera push-in, pull-out, panning, rotation, zoom, handheld shake, or reframing. Room dimensions, walls, windows, doors, ceiling height, and structural layout remain completely unchanged throughout the transformation. 0–3 seconds: The scene begins as a rough, unfinished interior with exposed cement walls, raw concrete flooring, exposed ceiling, visible construction materials, and an empty space. Dust settles naturally while the environment remains static. The floor installation begins, gradually spreading from left to right until the entire concrete floor transforms into premium microcement or elegant large-format light grey tiles. 3–6 seconds: Walls and ceiling begin transforming simultaneously. Rough cement walls smoothly become perfectly finished creamy-white walls. Wood veneer panels, decorative wall mouldings, built-in storage cabinets, TV feature walls, suspended ceiling structures, recessed lighting channels, and hidden LED strip lighting appear naturally in their correct architectural positions as though installed by invisible craftsmen. 6–9 seconds: Electrical fixtures, doors, window frames, skirting boards, switches, sockets, and architectural details complete themselves with realistic construction logic. Ambient lighting gradually powers on, filling the room with soft, warm illumination while maintaining a natural daylight balance. 9–12 seconds: Furniture and soft furnishings assemble sequentially. Luxury sofas, coffee tables, dining furniture, rugs, curtains, indoor plants, decorative artwork, lighting fixtures, books, cushions, and decorative accessories naturally move into place piece by piece, resembling a real construction and interior installation time-lapse. 12–15 seconds: The renovation reaches its final premium interior design. Every object settles perfectly into position while the lighting subtly adjusts to create a luxurious atmosphere. The completed room remains perfectly still for the final second, allowing viewers to appreciate the finished transformation. Overall style: Ultra-realistic architectural visualization, photorealistic materials, premium luxury interior design portfolio quality, realistic construction time-lapse, physically accurate lighting, smooth seamless transitions, natural installation logic, cinematic realism, highly detailed textures, clean modern luxury aesthetic, 8K quality.

Use the uploaded storyboard image as a visual reference only. Create a single 10-second cinematic 3D animation by recreating every storyboard panel in sequence. Do NOT animate the storyboard page itself. Rebuild every scene as a real animated environment while keeping the exact same girl, outfit, hairstyle, facial features, kitchen, colors, lighting, props, and overall style from the storyboard. 0.00–1.25s: The girl happily waves at the camera and points toward the cupcake ingredients on the table. 1.25–2.50s: She pours flour into a clear glass bowl. Soft flour particles float naturally. 2.50–3.75s: She gently whisks the cupcake batter while smiling. 3.75–5.00s: Extreme close-up of creamy batter being poured into colorful cupcake liners. 5.00–6.25s: She sprinkles rainbow sprinkles over the cupcake batter. 6.25–7.50s: Top-down shot of the cupcake tray as she carefully places it into the oven. 7.50–8.75s: Inside the oven, the cupcakes rise into fluffy golden cupcakes with warm glowing light. 8.75–10.00s: She removes the cupcakes, proudly presents them to the camera, smiles brightly, and gives a cute thumbs-up. Style: Pixar-quality 3D animation, ultra-cute, cozy bakery kitchen, warm golden lighting, soft pastel colors, cinematic depth of field, smooth camera movements, realistic hand movements, natural facial expressions, seamless transitions, high detail, 4K look. Camera: Follow the storyboard camera angles exactly (wide shot, medium shot, close-up, extreme close-up, top-down, close-up, wide shot). Important: Treat the uploaded storyboard only as a reference. Never animate the storyboard page itself. Recreate every scene from scratch in full 3D animation. Do not show storyboard borders or text.

Live-action footage + 2D anime sticker composite comedy short video 【Style】 Live-action footage + Flat 2D Sticker Composite comedy short video. First-person cooking perspective, with a strong contrast between the realistic kitchen texture and the flat cartoon sticker style. The overall effect is a Live-Action + Flat 2D Cartoon Sticker hybrid. The image is a real live-action kitchen, while the character remains a purely 2D flat sticker-style chibi cartoon character throughout. 8K ultra HD, vertical video, slight handheld shake, brisk short-video pacing, direct comedic beats. 【Duration】 10 seconds 【Aspect Ratio】 9:16 vertical 1. Scene Setting 【Scene】 A real home kitchen from a first-person perspective. A black iron wok sits on the stovetop, with beef and vegetables being stir-fried inside, oil sizzling and steam rising. The background includes: A white tile wall Wall outlets Soy sauce bottles and oil bottles lined up against the wall A stainless-steel sink on the right Natural light coming in through a side window The overall environment must feel real and lived-in, with a believable kitchen texture, and must not turn into a cartoon kitchen. The camera is first-person POV, with slight handheld shake, but not so shaky that it becomes chaotic. 2. Character Setting 【Character】Chibi anime sticker character: Capybara Lulu Requirements: A round, cute anthropomorphic cartoon capybara Standing front-facing in the lower center of the frame About half the height of the iron wok Flat 2D sticker texture Clear cartoon outline Strong paper-cutout feel Must not become a three-dimensional realistic animal Must not be reshaped by the real environment lighting into realistic 3D light and shadow Locked appearance: Light yellow body Wearing orange shorts A small yellow apron tied around the neck A small tangerine on top of the head Four short little paws, rounded like beans Head and face take up a very large proportion Overall like a soft, cute paper sticker character Character temperament: Usually chill and lazy But extremely skilled whenever causing trouble A smug, mischievous expression with a strong prankster feel 【Live-action Portion】 The real person’s hand is realistic and enters the frame from the right side. Skin details must be realistic, with visible pores, creating a clear contrast with the 2D character. 3. Shot Design 【Shot 1 | 00:00–00:03】 Salt Avalanche Opening 【Camera Position】 First-person overhead POV 【Visual Action】 The real person’s hand is using a spatula to stir-fry the beef and vegetables in the wok. Capybara Lulu sits on a small wooden stool beside the stovetop, squinting its bead-like eyes, with deeper blush and an upturned mouth showing a smug, wicked grin. It raises a glass seasoning jar bigger than its own head high with both short little paws and, while the person is stir-frying, pours the entire jar of white salt into the wok. The salt should cascade down like a real waterfall, clearly falling into the wok and forming an exaggerated but visible “little white salt mountain” on top of the food. 【Character Expression】 Slightly narrowed bead-like eyes Wicked grin Mischievous satisfaction 【Sound Effects】 Food sizzling Dense rustling sound of salt being poured into the wok 【Only Main Action in This Shot】 Capybara Lulu pours the entire jar of salt into the wok. 【Shot 2 | 00:03–00:05】 Spatula Bonk 【Camera Position】 Continue in first-person close-up POV 【Visual Action】 One of the real person’s hands quickly snatches the glass salt jar from its arms. The other hand raises the spatula, with the flat side facing downward, and gently taps the top of Capybara Lulu’s head. Note that this is a cartoon-style light tap, not realistic violence. After the tap, an obvious red cartoon bump immediately pops up on the top of its head. Its entire round 2D sticker body jolts sharply up and down, both little paws instantly hold its head, and its bead-like eyes suddenly widen. 【Character Expression】 Shocked Wronged Dazed for a moment 【Sound Effects】 A “Duang” sound from the spatula A light metallic tap Cartoon spring sound effect 【Only Main Action in This Shot】 The real person lightly taps the top of its head with the spatula. 【Shot 3 | 00:05–00:08】 Cry & Feed 【Camera Position】 First-person close-up POV, focused on the character’s face and the edge of the wok 【Visual Action】 Capybara Lulu holds the red bump on its head, and its bead-like eyes instantly turn into spinning spiral eyes. It opens its mouth wide and cries “waa waa,” with blue cartoon tears exaggeratedly spraying like fountains from both sides. The small tangerine on its head also trembles with the crying. At the same time, the real person’s hand immediately uses the spatula to scoop up a full spatula of “white salt and salty vegetable mixture” from the salt mountain in the wok, and while it is crying with its mouth open, accurately feeds the spatula into its mouth. Its mouth is instantly stuffed until bulging, and its left and right cheeks swell up exaggeratedly like two hemispheres. 【Character Expression】 Spiral eyes Loud crying Shocked blankness after its mouth is stuffed full 【Sound Effects】 Exaggerated cartoon bawling Rustling sound of scooping salt A “pop” sound as it is stuffed into the mouth 【Only Main Action in This Shot】 The real person stuffs a spatula of salty vegetables into its mouth while it is crying with its mouth open. 【Shot 4 | 00:08–00:10】 Salt K.O. Ending 【Camera Position】 First-person fixed close-up, freeze-frame ending 【Visual Action】 Capybara Lulu’s cheeks are swollen red on both sides, and it is forced to swallow the salt in its mouth. Its pupils suddenly shrink into two tiny dots, its light yellow body instantly turns one shade paler, and the whole character stiffly trembles for half a beat. Immediately after, its bead-like eyes turn into two “X” marks, and its body falls backward stiffly from the small wooden stool, landing flat on its back on the stovetop with all four paws facing up. One little paw weakly swipes through the air, then drops. A ring of small spinning stars slowly circles beside the red bump on its head. A wisp of soul-like white smoke drifts lazily from in front of its square little nose. The image freezes at the instant it is “so salty it ascends.” 【Sound Effects】 A stiff “clunk” sound A “thud” as it falls backward A slight cartoon ascension sound effect to end 【Only Main Action in This Shot】 Capybara Lulu falls backward after being overwhelmed by saltiness. 4. Execution Requirements 【Visual Requirements】 The kitchen environment must be realistic and live-action Capybara Lulu must always maintain a pure 2D sticker feel The 2D character must strongly contrast with the real kitchen and real human hand Do not make Capybara Lulu into a three-dimensional realistic furry animal Do not let the character receive complex realistic lighting The character outline must remain clear, like a cartoon sticker pasted onto live-action footage 【Action Requirements】 Keep only one main action per shot The action rhythm should be short, direct, and fast The character’s expressions should be exaggerated, but the action logic must be clear The salt, spatula, steam, and fall must have clear physical feedback 【Performance Requirements】 Capybara Lulu’s troublemaking feel must be strong The real person’s full body does not appear, only the hands The real person’s reaction should be crisp, like someone experienced at handling a troublemaker The overall piece is a dialogue-free comedy, with no need for anyone to speak 【Camera Requirements】 Keep first-person POV throughout the film Slight handheld shake Do not switch to third person Do not add unrelated people The ending freeze-frame should be crisp 5. Negative Words blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, subtitles, text, logo, error; deformed, mutated, bad anatomy, extra limbs, broken hands, disfigured, bad composition, out of frame; realistic animal fur, 3D realistic capybara, over-rendered lighting on sticker character, inconsistent character, changing clothes, changing body color, changing head accessory; background shift, disappearing props, broken kitchen continuity, floating objects, incorrect POV, extra people, extra hands, glitching cuts

DV 16mm handheld tape camcorder POV by CHASE, who occasionally props the camera on a treadmill console or nearby bench. Natural hand shake, crooked framing, delayed autofocus, clumsy zooms, imperfect framing; camcorder never visible. Soft vintage tape quality with subtle noise, slight blur, muted colors, realistic skin tones, gentle bloom around gym lights, authentic early-2000s camcorder aesthetic. Tone: energetic but exhausted cardio challenge vlog with authentic reactions and playful humor. CHASE: Korean idol in her 20s with a long black ponytail, light post-workout sweat, expressive eyes, slim athletic build, wearing a modest long-sleeve athletic top, loose joggers, white sneakers, towel around her neck. Setting: modern indoor gym with treadmills, rowing machines, mirrors, and soft evening lighting. Shots: (1) Selfie before stepping onto the treadmill: “Let's see if I can survive twenty minutes.” (2) Camera on the treadmill console while she jogs naturally. (3) Handheld close-up breathing heavily: “Why does it feel faster every minute?” (4) Macro shot of her finger pressing the stop button. (5) Walking slowly off the treadmill, laughing while wiping sweat from her forehead. (6) Drinks water and takes a deep breath. (7) Gives the camera a tired thumbs-up: “Cardio officially defeated me today.” (8) Picks up her gym bag, smiles warmly, waves goodbye, and says, “See you next time!”

ASMR anime scene of hands creating a pressed-flower bookmark on a warm wooden desk delicate petals are arranged, laminated, trimmed, and finished with a gold ribbon the translucent bookmark glows in sunlight beside a vintage book ghibli-inspired, dreamy, nostalgic, detailed hand-drawn style

Ultra-realistic live-action cinematic travel vlog, absolutely NO CGI, NO animation, NO game graphics, NO artificial visual effects. A young East Asian woman with long layered maroon hair, wearing the EXACT SAME professional paragliding outfit throughout both videos: matte white certified paragliding helmet, navy blue lightweight windproof paragliding jacket with subtle reflective details, black moisture-wicking performance base layer, black certified tandem paragliding harness with properly secured leg straps and chest buckle, black stretch outdoor pants, gray high-ankle hiking boots with strong ankle support, lightweight black paragliding gloves, sport sunglasses tucked into the jacket collar. Location: a real tropical coastal mountain paragliding launch site with lush green cliffs overlooking turquoise ocean, white sandy beaches, and distant mountain ranges under bright morning sunlight. Montage sequence: • Walking confidently toward the launch area while smiling naturally at the vlog camera. • Close-up tightening the helmet strap and checking the harness buckles. • Instructor performing a final safety check as she laughs and gives a thumbs-up. • Holding the brake toggles correctly while facing the wind. • Running naturally down the grassy launch slope. • The wing inflates smoothly overhead and both feet lift naturally from the ground. • Ending with a breathtaking wide shot as she glides away above the coastline. Natural handheld vlog camera mixed with cinematic tracking shots, realistic wind interaction, authentic paragliding procedures, practical lighting, ARRI Alexa 35, ARRI Signature Prime lenses, subtle film grain, warm cinematic color grading, documentary realism, realistic physics.

After a rhythmic approach like stop-motion, a glitch video that aggressively moves back and forth between completely different dimensions (2D⇔3D), such as 3D CG, live action, 2000s anime, and pixel art, without minding if the facial structure changes. It ends with a browser-crasher-like screen collapse. Video concept: Completely eliminate smooth camera movement. The camera approaches the face in stages (jump cuts) to the rhythm of “Pa! Pa! Pa!” After the approach, the girl's face does not need to preserve its “original features.” The entire screen is pulled in and keeps being violently swapped (moving back and forth) through hard cuts into “completely different art styles and dimensions (2D⇔3D),” such as dimensional 3D CG, raw live action, a 2000s-style anime beautiful girl, and flat retro pixel art. Camera and editing policy: [Extremely important: Smooth changes and zoom-ins are absolutely not allowed. The sequence must be composed of stop-motion-like jump-cut approaches and “complete switching” into art styles from different dimensions.] 0.0–3.0 seconds: [Stop-motion approach] Start from the first shot. Instead of the camera moving smoothly closer, it approaches the face in stages with jump cuts at a steady rhythm every 0.5 seconds: “Pa! Pa! Pa! Pa!” At the moment each cut switches, strong chromatic aberration (RGB shift) noise runs across the image. 3.0–8.0 seconds: [Dimensional collapse; complete art-style replacement] Reach an extreme close-up of the face. From here, the rendering style of the video itself keeps crackling and switching (moving back and forth) every 0.5 to 1 second, without concern for changes in the facial structure. It is forcibly swapped with flashes into completely different art styles that cross between 3D and 2D dimensions, such as “dimensional polygonal 3D CG” → “ultra-high-definition live-action human” → “2000s-style cel anime beautiful girl character (2D)” → “completely flat retro pixel art (2D).” 8.0–10.0 seconds: [Browser-crasher-like collapse ending] The violent back-and-forth between art styles exceeds the processing limit, and the video completely collapses. Using the face footage as an underlay, “massive error windows,” “video panels with different visual expressions,” and “vividly colored block noise” keep popping up chaotically in multilayered layers like a browser crasher. The entire screen is completely filled with a buggy video collage, becoming a chaotic collapse screen that retains none of the original video's form. Constraints: During the midsection art-style changes, “smooth changes that try to preserve the original face silhouette” are absolutely unnecessary. The structure may change, so violently repeat “complete hard cuts (swaps)” many times into rendering styles from different dimensions: “dimensional (3D)” and “flat (2D),” as well as “live action” and “2000s anime.”

Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D . True 12 frames per second, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding. Constant painterly BOIL — brushstrokes and outlines subtly alive frame to frame. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from <<<image_1>>>, the yurt camp from <<<image_2>>>, the wolves from <<<image_3>>> — lean steppe wolves, coal-black with cold sheen, pale eyes. THE HERDSMAN from <<<image_4>>> (on foot). RIDER 1 from <<<image_5>>> riding HIS horse from <<<image_6>>> — keep this man and this horse together as one consistent pair. RIDER 2 from <<<image_7>>> riding HIS horse from <<<image_8>>> — a second consistent pair. Never mix the riders onto each other's horses. Atmospheric motion (blowing snow, blizzard haze) moves SMOOTHLY; figures, horses and wolves step on twos with secondary action. DIRECTOR'S NOTES: 1. THE SCENE — dusk, a blizzard rising over the Kazakh yurt camp. Wolves have come down on the herds. Panic erupts: THE HERDSMAN screams the alarm, men run, RIDER 1 is the first into the saddle and the first to tear out into the storm, RIDER 2 right behind him shouting orders. 2. RISING ENERGY — the sequence builds from dread to chaos: the dark wolf shapes at the herd, then the scream, then the explosive mounting and gallop. Each shot more energy than the last. 3. RIDER 1 IS THE LEAD — give RIDER 1 a clearly readable beat: he is the first to vault into the saddle of his horse (<<<image_6>>>) and the first to spur out of the camp, leading the charge, grim and silent, his face readable for a moment so the audience will know him again. RIDER 2 mounts shouting and follows. 4. AGGRESSIVE HANDHELD — the camera is in human hands in a panic: constant restless motion, jerky corrections, vertical bounce from running steps, buffeted by wind gusts, the horizon never level, never gimbal-smooth, never tripod-locked. Raw documentary chaos. 5. REAL PHYSICS — horses wheel and rear with weight, men vault into saddles with effort, snow is kicked up by hooves and boots as bursts of loose powder (drawn snow-spray effects on twos), cloth and manes whip in the wind with follow-through. 6. SECONDARY ACTION on twos on everything: chapan skirts and fur hats whipping, horse manes and tails streaming, breath-vapor of men and horses torn off by wind, harness straps swinging. 7. LIGHT — failing dusk in a blizzard, dim cold blue-grey storm light, soft and diffuse, no rays, no beams, no god rays; one or two struggling torch flames as small warm accents whipping in the wind. Correct neutral white balance, NOT a blue filter, muted desaturated, the wolves near-black masses. SHOT 1 — WIDE, ~35mm, aggressive handheld, the yurt camp at dusk in driving snow. COMPOSITION: the pale domed yurts low across the LOWER-RIGHT third, the churning panicked herd a dark restless mass on the LEFT third — and along the far edge of the herd, low dark wolf shapes from <<<image_3>>> flowing fast between the snow-veils, barely readable, a dark current, varied in tone and stride, never mirrored, never cloned. Blizzard haze drifts smoothly, figures and animals on twos. The herd wheels and screams. Energy rising. HARD CUT to SHOT 2 — MEDIUM, ~35mm, aggressive handheld running with him: THE HERDSMAN (<<<image_4>>>) bursts between the yurts toward camera, stumbling in the snow, waving an arm, his chapan and fur hat whipping with follow-through, breath-vapor tearing away, screaming raw over the wind, lips on twos: "Böri-i-iler!! BÖRILER!!!" Figures scramble behind him, a torch flame struggling and whipping. Snow bursts from his boots as drawn powder on twos. HARD CUT to SHOT 3 — MEDIUM, ~50mm, aggressive handheld in the chaos, on RIDER 1: he reaches his horse (<<<image_6>>>) at a run, the horse wheeling with real weight, and VAULTS into the saddle in two hard stepped poses, grim and silent, his weathered face readable for one beat in the torch-glow — then he wrenches the horse around and spurs it, the first one driving out into the storm, snow bursting from the hooves, his chapan and the mane streaming with follow-through. Behind him RIDER 2 (<<<image_7>>>) swings up onto his own horse (<<<image_8>>>), shouting hoarse over the wind, lips on twos: "Attardy qutqar!!" HARD CUT to SHOT 4 — WIDE, ~35mm, aggressive handheld, the edge of the camp: RIDER 1 already a dark mass at full gallop tearing toward the UPPER-LEFT into the blizzard, leading; RIDER 2 and one or two further silhouetted riders breaking after him from the LOWER-RIGHT, hooves drumming, powder bursting, manes tails and chapans streaming on twos, the pale yurts falling behind in the snow-haze, the dark storm ahead as the negative space they ride into. Camera buffeted, horizon tilting. The hoofbeats swallowed by the wind. End. Audio: NO MUSIC — the roar of the blizzard wind, panicked horses screaming and stamping, the herdsman's raw cries, men shouting, drumming hooves fading into the storm, distant wolf snarls under the wind. No subtitles. Natural diegetic sound only, absolutely no music. Constraints: stop-motion stepped cadence on twos at 12fps with painterly boil, figures horses and wolves stepping pose to pose never gliding, NO smooth interpolation NO motion blur NO morphing, blizzard haze and blowing snow smooth while all living things and drawn snow-spray effects step on twos, hand-painted oil look from <<<image_2>>> not photoreal not 3D, four shots with hard cuts rising in energy — wide wolves-at-the-herd, medium the screaming alarm "Böriler!!" from THE HERDSMAN <<<image_4>>>, medium RIDER 1 <<<image_5>>> vaulting onto his horse <<<image_6>>> grim and silent his face readable one beat and spurring out FIRST while RIDER 2 <<<image_7>>> mounts his horse <<<image_8>>> shouting "Attardy qutqar!!", wide the riders tearing out into the storm RIDER 1 leading — each rider stays on his own horse the pairs never mixed, AGGRESSIVE HANDHELD constant restless jerky motion vertical bounce wind-buffeted horizon never level never gimbal-smooth, REAL PHYSICS horses wheeling and rearing with weight men vaulting with effort snow kicked as loose powder bursts, SECONDARY ACTION on twos chapans fur hats manes tails harness breath-vapor all whipping with follow-through, dusk blizzard dim cold storm light soft no rays no beams torch flames as small warm whipping accents, correct neutral white balance not a blue filter muted desaturated, wolves from <<<image_3>>> varied never mirrored never cloned, spoken Kazakh in Latin transliteration pronounced as written not Russian-accented, NO MUSIC only storm and voices.

Premium stylized 2D animated pirate action sequence, bold black ink-outline comic-animation style, flat cel-shaded coloring with dramatic high-contrast lighting, matching a high-end animated game-cinematic look. 15 seconds, fast-cut action-trailer pacing across 12 rapid scenes. Reference: THE CREW (@img1) — CAPTAIN, THE QUARTERMASTER, THE OLD NAVIGATOR — matching each character's exact face, outfit, and design throughout. Location: their own weathered galleon deck, at stormy dusk under bright overcast grey-white daylight (NOT pitch-black night — the storm clouds and rain are dramatic but the scene stays clearly lit throughout), in a torrential storm, under boarding attack from a rival pirate ship. (0:00–0:01.2) A rival pirate ship looms alongside through fog and rain, a cannon flash bursting bright against the pale overcast storm sky. Wide static low-angle shot. (0:01.2–0:02.2) THE OLD NAVIGATOR wrenches the ship's wheel hard, rain streaming down his weathered face, the deck tilting as a cannonball splashes close off the bow. Close handheld shot with subtle shake. (0:02.2–0:03.2) Grappling hooks fly through the rain-streaked air and bite into the deck railing with sharp metallic impacts. Fast tracking shot following a hook mid-flight. (0:03.2–0:04.2) Rival boarders swing across on ropes between the ships, clearly lit against the bright grey storm sky with a lightning flash adding a brief highlight. Wide low-angle composition, figures fully visible rather than in silhouette. (0:04.2–0:05.4) THE QUARTERMASTER draws his knife in one fluid, practiced motion, his scarred face clearly lit by the bright overcast daylight, feathers in his bandana whipping in the wind. Fast whip-pan into a tight close-up. (0:05.4–0:06.6) A sharp, fast knife-fight exchange between the Quartermaster and a boarding pirate — blades flash, coat fabric tears, rain sprays off with the impact of each parry. Tight handheld mid-shot with quick internal cuts. (0:06.6–0:07.6) THE CAPTAIN strides forward through the surrounding chaos, drawing his cutlass with calm, deliberate confidence, utterly unshaken by the fighting around him. Slow-motion push-in, a deliberate contrast to the frantic energy around him. (0:07.6–0:08.8) The rival ship's captain steps forward to meet him. The surrounding fight blurs into soft-focus background as a clean, symmetric one-on-one composition forms between the two captains. Wide symmetric two-shot. (0:08.8–0:10.2) Their blades clash — sparks burst off crossed steel, lit starkly by a cannon-fire flash from the background. Close dynamic shot with a slight dutch-angle tilt, fast cutting energy. (0:10.2–0:11.4) THE OLD NAVIGATOR, still gripping the wheel, ducks a swinging boom overhead and steadies the ship through a crashing wave, entirely unshaken. Side tracking shot. (0:11.4–0:13) THE CAPTAIN lands a decisive final strike, disarming the rival captain — his blade spins away and clatters to the deck.

Cinematic Korean action sequence in a narrow sunlit urban alleyway lined with brick buildings, air conditioning units, wooden pallets, and a prominent GS25 convenience store. A young athletic woman with long blonde hair tied in a high ponytail wears a form-fitting pink long-sleeve athletic crop top with a deep square neckline and matching fitted pink athletic leggings paired with clean pink athletic sneakers. Her face, neck, and upper chest have a light sheen of sweat, emphasizing that she has just finished training, while her expression remains calm, focused, and determined. She faces a group of aggressive young men wearing black tracksuits and hoodies. Without hesitation, she charges forward using precise, powerful martial arts techniques with lightning-fast punches, spinning kicks, elbow strikes, knee attacks, sweeps, and perfectly executed throws, taking down each attacker one by one with fluid, realistic choreography. The handheld camera follows closely through the narrow alley with dynamic movement, subtle camera shake, realistic motion blur, and rapid perspective shifts that heighten the intensity of every impact. Bodies crash onto the pavement as the fight escalates with cinematic momentum. In the background, three Korean schoolgirls in neat school uniforms stand near the GS25 entrance, watching the confrontation in stunned silence. Bright natural daylight casts crisp shadows across the brick walls and stacked wooden pallets, highlighting dust, debris, and realistic environmental details. The sequence concludes as the final attacker collapses beside the stacked pallets. The woman pauses, calmly adjusts her fighting stance, straightens her pink athletic crop top, and confidently walks away down the sunlit alley. Hyper-realistic live-action style, Korean action film aesthetic, high-energy choreography, sharp facial detail, physically accurate movement, cinematic handheld camera work, natural lighting, realistic textures, and feature-film quality.

CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from bathroom vanity lighting. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic. STYLE: Cozy skincare vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments. Focus on satisfying sounds: bottle caps popping, cotton pad taps, water splashing, jar lids twisting, soft patting sounds. SUBJECT: Young woman in her early 20s, hair wrapped in a soft headband, oversized robe, no makeup, relaxed expression. Calm, unwinding energy before bed. SETTING: Small bathroom vanity area at night. Warm vanity lights, neatly arranged skincare bottles, mirror, soft quiet atmosphere. STORYBOARD: → (2s, propped medium shot) Places camera on the vanity shelf, sits down. "Time for my nighttime routine." → (2s, overhead shot) Pours cleanser onto palms, lathers gently. → (2s, close-up) Splashes face with water, pats dry with a towel. → (2s, handheld shot) Holds up a toner bottle, pours onto a cotton pad. "This one's been my favorite lately." → (2s, detail shot) Applies serum with gentle patting motions. No dialogue. → (2s, medium shot) Twists open a moisturizer jar, scoops a small amount. "Almost done." → (2s, macro shot) Applies lip balm, sets it back on the shelf. → (2s, propped shot) Brushes hair gently in front of the mirror. → (2s, warm ending shot) Looks at reflection, relaxed smile. "Ready for bed now." → (1.5s, final shot) Turns toward camera, reaches for the lens. "Goodnight." Hand covers lens as recording ends. AUDIO NOTES: Natural bathroom ambience bottle caps, water splashing, patting sounds should be clearly audible. Dialogue quiet and casual, almost a whisper. REALISM NOTES: Authentic body language, natural blinking, genuine soft smiles, occasional pauses, imperfect framing, focus breathing, warm dim lighting. Should resemble a genuine personal skincare vlog on a consumer camcorder, not a commercial production.

CAMERA: Modern full-frame digital cinema camera with handheld POV by RENA, occasionally propped on the vanity. Natural handheld movement, subtle camera shake, imperfect framing, occasional delayed autofocus, gentle zoom adjustments, face occasionally cropped. Camera never visible. LOOK: Clean, high-end digital image with soft flattering vanity lighting. Subtle bloom from vanity bulbs, realistic skin texture, shallow depth of field, cinematic dynamic range, natural colors, premium mirrorless camera quality. STYLE: Casual beauty vlog. Relaxed, chatty, slow pacing with quiet mirror moments. CHARACTER: RENA, Korean female idol in her early 20s, long straight jet-black hair with a natural center part, fair dewy skin, soft brown eyes, natural makeup with glossy coral lips. She is wearing a glamorous black K-pop stage outfit embellished with crystals and metallic details, completely covered by a professional black makeup cape draped over her shoulders, with only subtle glimpses of the sparkling stage costume visible around the neckline, sleeves, and lower body. Unseen stylist's hands occasionally enter frame to brush, section, curl, and style her hair. SETTING: A professional K-pop idol dressing room backstage before a performance, featuring a large bulb-lit vanity mirror, styling chair, hair dryers, curling irons, brushes, styling sprays, makeup products, garment racks filled with stage outfits, mirrors, and an authentic backstage atmosphere. STORYBOARD: 1. Camera is propped on the vanity. RENA smiles warmly and waves at the camera. Korean: "안녕하세요 여러분! 오늘 헤어랑 메이크업 받으러 왔어요." 2. Handheld close-up as the stylist gently separates and pulls sections of RENA's hair while preparing the hairstyle. Korean: "준비하는 데 항상 시간이 오래 걸려요." 3. Insert close-up of the stylist clipping and arranging her hair with professional tools. Ambient backstage salon sounds only. 4. Camera is propped on the vanity again. RENA smiles naturally while looking into the mirror. Korean: "이제 거의 다 됐어요." 5. Handheld close-up of RENA quietly watching the stylist through the mirror, smiling softly as the finishing touches are applied. Ambient sounds only. 6. Handheld shot as RENA uses a handheld mirror to check the back of her hairstyle from multiple angles. Korean: "뒤도 한번 볼게요." 7. Tight close-up as RENA's expression brightens after seeing the completed hairstyle. Korean: "너무 마음에 들어요!" 8. Selfie shot. RENA gives a thumbs-up, waves enthusiastically at the camera, and smiles brightly. Korean: "완성! 다음에 또 만나요. 안녕!"

Create a 15-second vertical (9:16) UGC-style fashion advertisement that feels authentic, premium, and social-media ready. The model is wearing the EXACT dress shown in the attached reference image. Do not redesign, modify, recolor, simplify, or reinterpret the dress in any way. Maintain identical embroidery, fabric, silhouette, neckline, sleeves, dupatta, borders, patterns, proportions, textures, embellishments, and overall craftsmanship throughout the entire video. A confident young woman stands in a bright, modern home with soft natural morning light. She gently showcases the dress while smiling warmly as if recommending it to a friend. Her hair is long, healthy, shiny, and naturally bouncy. She speaks directly to the camera: "I've finally found a dress that feels as beautiful as it looks. The craftsmanship is stunning, the fabric feels luxurious, and every detail looks incredibly premium. It's elegant, comfortable, and honestly makes me feel confident every time I wear it. If you're looking for a timeless outfit, you have to try this!" Storyboard: Scene 1: Close-up of the dress in her hand as she introduces it by gently showcasing the embroidery, fabric texture, and premium craftsmanship. Scene 2: She gently spreads the dupatta and lightly runs her hand across the embroidery, showing the intricate detailing and luxurious fabric movement. Scene 3: Beauty shots of her wearing the dress while walking naturally, adjusting the dupatta, lightly twirling, and showcasing realistic fabric flow, elegant movement, and premium embroidery from different angles. Scene 4: After styling herself, she confidently flips her silky, glossy hair while smiling at the camera, allowing the dress to flow naturally as she turns. Scene 5: Final hero shot holding the dupatta beside her while showcasing the complete outfit against a clean, premium interior background. She smiles and says, "Highly recommend!" The video should have realistic smartphone camera quality, natural handheld movement, genuine facial expressions, smooth transitions, accurate lip sync, premium visibility of the dress throughout, and a polished yet authentic UGC aesthetic. The dress remains perfectly identical to the attached reference image, with every embroidery detail, color, fabric texture, silhouette, and design element consistently visible in every shot.

High-quality anime footage. Dense 3D toon / cel look. Feature-film-level key animation, refined compositing, translucent lighting, and richly detailed background art. The setting is a magnificent magical city wet with rain. Depict it as a cinematic high-fantasy action RPG. The character from the reference image fires continuous beams from a main gate opened in front of them and from multiple converging gates opened around them, then finally defeats a gigantic black dragon in slightly overkill fashion with a simultaneous full volley from all gates. [Reference Character Lock] Use the character in the source reference image as reference and maintain them as the same person. Use the reference image only for the character’s face, eye shape, iris color, hairstyle, hair color, outfit, ornaments, physique, silhouette, atmosphere, and character colors. Do not reproduce the background, room, furniture, pose, camera angle, or framing of the reference image itself. Only the expression, gaze, mouth, pose, breathing, and natural movement of hair and clothing may change. Mixing features, averaging the face, changing the outfit, turning them into a different person, cloning them, or adding extra people is prohibited. Keep the equipment and accessories shown in the reference image, and do not arbitrarily multiply them or add different gear. The attack must always come from gate groups in front of the character’s palms, not from waist equipment or small items. [Character Adaptation Rules] Keep the fixed scene content and battle progression, but adjust the background decorations, props, magical motifs, color tones, glow colors, and atmosphere to match the reference character. While keeping the city’s basic structure fixed as a magnificent stone-built magical city, bring the balustrade designs, magic lamps, waterways, crystal pillars, patterns, mist, and reflection colors closer to the reference character’s world and colors. Rebuild the beams, gates, explosions, particles, and floor reflections around the reference character’s signature colors. Prioritize colors that enhance the character’s appeal, and keep the background one step darker so the protagonist does not get buried. [Fixed 3D Style] Maintain a delicate cel look throughout. Use thin lines, clear two- to three-step cel shading on the face, hair, and outfit, plus translucent midtones. Add multilayer highlights to the eyes and hair. Distinguish fabric, leather, metal, gems, wet stone floor, glass, and puddles with different reflections and roughness. Only the magic should use high-luminance graphic anime VFX, volumetric light, additive glow, refractive waves, and directional motion blur. Do not use thick black outlines, flat single-layer cel shadows, generic 3D faces, low-density backgrounds, semi-realism, or mixed art styles. [Fixed Protagonist and Enemy] The protagonist is on the left side of the screen, and the enemy is on the right. The protagonist spreads both legs, bends the knees, keeps their center of gravity over the rear leg, and opens one palm toward the dragon’s chest. The other hand may support that arm or wrist. Make the connections between palm, wrist, elbow, and shoulder readable, and do not hide the entire arm too much with the gate. Recoil travels continuously through the wrist, shoulder, waist, and supporting leg, while the hair, clothing, and ornaments stream backward with a slight delay. The enemy is only one gigantic black four-legged winged dragon on the right side. It is about four times the protagonist’s height. It has one head, two horns, two eyes, four legs, one pair of left and right wings, and one tail. The impact point is fixed at the center of the chest. Do not create extra heads, legs, wings, or tails. [Setting and Camera] The setting is a broad stone magical boulevard jutting into the air within a gigantic magical city after rain. Place wet stone slabs, shallow puddles, old cracks, magical metal balustrades, surrounding magic towers, spires, arch bridges, aerial corridors, floating small towers, giant crystal pillars, magic lamps, glowing waterways, and low mist. Adjust these motifs and glow colors to match the reference character. Keep the protagonist on the left and the black dragon on the right, and make the main gate center, each sub-gate, the beam axes, and the black dragon’s chest converge onto the same attack line. The camera starts with a gentle close-range arc movement where the face is readable, then shifts to a low rear three-quarter wide shot through an occlusion wipe where the gate’s arc covers the lens. During the lateral move along the beams, make the balustrades, raindrops, floor patterns, puddle reflections, and floating lights flow at different speeds, briefly push the camera back with the impact pressure, and move in quietly only when the smoke opens. Do not use purposeless circling or random camera shake. [Attack Progression] At the start, the main gate forms in front of the protagonist’s palm. It is made of two to four layers of incomplete concentric-circle gates, with each ring separated forward and backward and counter-rotating at different speeds. Short tick marks, radial lines, and electric light gather toward the firing axis; the light in the palm pulses three times, and on the third pulse the rings compress. At the same time, multiple sub-gates also appear one after another around the protagonist. Place them above the right shoulder, behind to the upper left, overhead in front, in front of the side, overhead behind, and so on, surrounding the protagonist with depth differences. They are numerous but organized, divided into foreground, midground, and background. Always keep the face and both eyes readable, and do not completely hide them with rings. For the first attack, fire a thick high-output beam from the main gate. Build the core, outer shell, mid-layer, and edge colors from the reference character’s signature colors, and do not make it a thin rod. Immediately afterward, the surrounding sub-gates fire in sequence with time offsets, continuously striking the center of the black dragon’s chest. Each beam is thick enough to push rain, mist, and water droplets outward. The black dragon’s chest scales are driven inward, its front claws scrape the wet stone floor, and the impact transfers with delay to the wing membranes, neck, and tail. Thick reflection bands matching the protagonist’s signature colors run across the floor. [Overkill and Defeat] After the continuous barrage, all gates recompress to maximum output. The protagonist remains braced at the lower left with the palm fixed, and all surrounding sub-gates also aim at the same impact point. All gates, including the main gate, fire simultaneously in the same frame, and multiple extra-thick beams concentrate on the center of the black dragon’s chest. Each beam maintains its thickness, luminance, and axis, with compressed waves running inside. In the same frame where the final compression wave reaches the chest, completely erase all beams from the firing ports to the impact point. Leave no thin afterglow. At that instant, a white-hot core appears at the center of the chest, and a local hemispherical shock dome swells once and tears open. From there, a giant flame-like magical explosion based on the reference character’s signature colors erupts three-dimensionally upward and to both sides. Develop sharp flame tips, thick volumetric light, transparent refractive waves, thin electric light, and outward speed lines with depth differences. Glowing cracks run through the wet floor, and water, steam, black scales, and stone fragments blast outward. Immediately afterward, gray smoke and black scales overlap the foreground, completely hiding the black dragon’s entire body. When the center of the smoke splits open, the black dragon is kneeling with the chest impact point facing the viewer. Magical cracks corresponding to the protagonist’s signature colors spread from the center of the chest through the whole body; black scales unravel into ash from the wingtips and tail tip, turning into fine glowing particles. The wing membranes, wing bones, tail, four limbs, torso, neck, and head collapse in sequence, and finally the magical core in the chest, the horns, and the light in both eyes shatter into particles; the body, shadow, and even the floor reflection disappear completely. Do not leave a corpse. The ending is a single battle-result image. Leave the protagonist in the foreground left, and in the background right only the empty wet road surface where the black dragon had been, plus fading ash and glowing particles. The protagonist keeps their guard up while slightly lowering the palm, and the hair and clothing settle with their breathing. Cut the moment the final particles rise and the black dragon’s shadow and reflection have completely disappeared. [Critical Breakdown Prevention] No text, subtitles, logos, watermarks, or UI. Do not let the beams become thin lines, be too brief, fade midway, explode too early, beam

She was just admiring the glowing jellyfish... 🪼 Suddenly, a massive Kronosaurus ambushed her from the deep! 🐊 Now she’s trapped underwater, hiding from the ultimate marine predator.

80s/90s retro home-videotape-style fitness vlog. DV / VHS / old DVD texture, low definition, 4:3 aspect ratio, as if the footage were recorded on a home video camera from the late 80s to the 90s. The overall image presents a clear retro tape aesthetic: slight noise, scan lines, tape grain, a slight dropped-frame feeling, warm and slightly faded colors, slight blur, low resolution, softened edges, occasional auto-exposure drift, delayed focus, unstable white balance, and soft blooming around lighting highlights, preserving the real rough flavor of old video footage. The image looks like an old DVD / home videotape that has been copied several times, with a bit of period feel and everyday life atmosphere. Shooting style: POV first-person perspective, filmed by CHASE herself. She sometimes shoots handheld, and sometimes casually props the camera on the treadmill console or a nearby small stool. The image naturally shakes, the framing is unstable, the composition is awkward, and the lens occasionally zooms in and out in an unskilled way. The camera itself must never appear in the frame. Character setting: An Asian woman in her 20s, with a Korean idol vibe. Long black ponytail, delicate features, lively eyes, slight post-workout sweat, a slim, balanced, athletic-leaning figure. She wears a plain, understated long-sleeve workout top, loose joggers, white sneakers, and a towel around her neck. Her overall state is authentic. Do not over-retouch, and do not make it feel like a fashion blockbuster. It should feel like a personal fitness diary casually recorded in that era. Scene: A modern indoor gym, but presented with old video-camera image quality to create a retro feeling. The environment includes treadmills, rowing machines, mirrors, and soft evening indoor lighting. The background is realistic and natural, not overly clean or commercialized, with a little lived-in clutter and signs of use. Overall tone: Relaxed, playful, real, with a slightly tired aerobic-challenge vlog feel. It is not an advertisement, not a movie, and not a high-quality blockbuster, but an old-style personal video with everyday life atmosphere and humor. The character’s reactions are natural, with real breathing, panting, pauses, and small expressions. Shot content: Selfie opening. She stands in front of the treadmill and says to the camera: “Let’s see if I can survive twenty minutes.” The camera is propped on the treadmill console, and she starts jogging naturally. Handheld close-up. While panting, she says helplessly: “Why does every minute feel faster?” A close-up of her finger pressing the treadmill stop button. She slowly steps off the treadmill, smiling as she wipes sweat from her forehead. She picks up a water bottle and drinks, taking a deep breath. Tired but amused, she gives the camera a thumbs-up and says: “Cardio officially defeated me today.” Finally, she picks up her gym bag, smiles warmly, waves goodbye to the camera, and says: “See you next time!” Additional requirements: Maintain an old home-video camera / VHS / old DVD look No modern HD feel, no over-sharpening, no excessive beauty retouching Preserve real sweat, breathing, tired expressions, and natural small mistakes The overall result should look like an 80s/90s home fitness diary recording

A massive human fortress built into the cliffs of a frozen planet faces a final assault from an endless ocean of armored insectoid aliens advancing across the ice beneath a violent magnetic storm, defensive cannons rotating into position as thousands of infantry soldiers line the walls and prepare to fire; the battle begins with synchronized railgun blasts ripping through the front ranks, missiles streaking overhead and enormous creatures using smaller bodies as bridges across defensive trenches, while flying aliens dive through lightning and crash into watchtowers; a gigantic siege beast covered in crystalline armor charges through the main gate, scattering tanks and soldiers, then climbs the fortress wall as defenders fire point-blank into its glowing joints; the fortress commander runs along a collapsing battlement, jumps onto a rotating cannon platform and manually redirects the weapon toward a deep fracture beneath the enemy swarm, but the siege beast tears the cannon loose just as it fires; start with a majestic ultra-wide panorama showing the impossible scale of the invasion, push rapidly through the storm toward the fortress, combine sweeping crane movements with visceral ground-level combat and dramatic low-angle shots of the siege beast, use a brief slow-motion moment as lightning strikes the cannon, icy blue ambient lighting contrasted with red emergency lights and orange explosions, dense snowfall, vapor clouds, electrical arcs and shattered ice, desperate mythic last-stand atmosphere, ending with the cannon blast splitting the frozen battlefield from horizon to horizon, swallowing the entire swarm into a glowing abyss while the ruined fortress remains standing above the collapsing ice.

Character Consistency: The subject is the young male influencer from the reference image @Image 1. In every time period and from every angle, the face shape, facial features, and skin tone must match @Image 1 exactly. Do not alter or distort the face. Outfit: In every scene, wear stylish and luxurious black casual, streetwear, or suit outfits. Do not wear the outfit from the character reference sheet. Completely change the outfit and hairstyle for each segment. Format: 9:16 vertical. Camera / Style: Fast editing rhythm with cuts every 0.5 to 1 second. iPhone handheld vertical shooting texture. Mix digital zoom in, zoom out, and tilt up, with natural camera shake. Include autofocus hunting, indoor and outdoor lighting exposure changes, and image quality degradation during zoom adjustments. Preserve real skin texture including pores, beard shadow, flyaway hairs, and natural skin oil. Do not use beauty filters, excessive skin retouching, CGI textures, or cinematic color grading. Do not merge cuts or omit scenes. Do not insert on screen text. Sound: Trendy hip hop or R&B background music mixed with natural environmental sounds such as street noise, footsteps, and everyday ambient sounds. --- M-01. Hongdae Busking Street & Tattoo Shop Tour 0 to 2 seconds: [Hongdae Walking Street] A low angle shot holding a selfie stick high above while quickly spinning to capture both yourself and the crowd in the middle of a busy busking street. 2 to 4 seconds: [Tattoo Shop Waiting Room] A tight shot pointing at the tattoo designs hanging on the wall with your finger, followed by a quick transition to your face looking at the camera while lightly biting your lip with a slightly nervous expression. 4 to 6 seconds: [Tattoo Workstation] A forearm shot rolling up the sleeve of an oversized black T shirt, rapidly cross edited with a shot of your face smiling while enduring the pain. 6 to 8 seconds: [In Front of the Shop Mirror] A tight shot checking the linework of the newly completed tattoo in the mirror, followed by your face making eye contact with the camera through the mirror and nodding with satisfaction. 8 to 10 seconds: [Hongdae Alley] A close up taking one bite of a street waffle, then blowing on it because it is hot while smiling at the camera. 10 to 12 seconds: [Select Shop Hallway] A handheld tracking shot from behind as you walk slowly with a shopping bag over one shoulder. The screen naturally shakes in sync with your footsteps. 12 to 15 seconds: [Hongdae Station Entrance] In front of the station exit, playfully extend your fiste toward the camera in a fist bump pose. End with a front facing full body shot frozen on the final frame.

BROADCAST TYPE: Live business news report covering a sudden stock market crash during trading hours. ON-AIR REPORTER: Female journalist, early 30s. Sharp blazer, earpiece, handheld mic with financial network logo. Composed but visibly tense. LIVE BROADCAST TIME: 11:20 AM. Bright daylight, glass-walled trading floor visible behind glass partition. REPORT LOCATION: Outside a stock exchange building. Digital ticker boards flashing red numbers. Traders visible through windows, gesturing anxiously. Passersby stopping to check phones. BROADCAST CAMERA: Steady tripod-mounted main shot with a secondary handheld cutaway camera. Occasional quick zoom to ticker board numbers dropping. Reflections of red digital numbers on glass. LIVE SEGMENTS: Opening: Reporter explains the sudden index drop and market panic. Update: Camera cuts to trading floor screens showing plunging graphs. Eyewitness Moment: A trader stepping outside briefly comments on the chaos. Situation Change: Ticker shows a fresh plunge, reporter reacts live to the number. Closing: Reporter signs off, noting market will be watched closely into afternoon. LIVE AUDIO: Muffled trading floor shouting, city traffic, notification pings from nearby phones, reporter's controlled voice, no music. BROADCAST REALISM: Genuine tension, traders ignoring camera, real-time number changes driving reactions, natural interruptions from passersby glancing at screens.

High-quality anime footage. A high-speed sword fight from a cinematic action RPG in dense 3D toon/cel look. Feature-film-level key animation, high-quality compositing, clear translucent lighting, and dense background art. In a short 8-second clip, densely connect an onslaught of floating swords, defense, evasion, counterforce, encirclement, and maximum-impact collision. 【Reference Images and Fixed Characters】 @1 is the first person, the reference image for Character A. @2 is the second person, the reference image for Character B. Refer to the characters in the source reference images and maintain each as the same person. Use the reference images only for the characters’ faces, eye shapes, iris colors, hairstyles, hair colors, outfits, accessories, physiques, silhouettes, atmosphere, character colors, and weapon designs. Do not reproduce the background, room, furniture, poses, camera angle, framing, text, or split layout of the reference images themselves. Both characters remain the same person and same character identity throughout. Only their expressions, gaze, mouth shape, posture, breathing, and natural hair and clothing movement may change. Do not create feature mixing, averaged faces, swapped hair colors, swapped outfits, swapped weapons, physique changes, different-person transformation, cloning, duplicates, or additional people. 【Automatic Adjustment of Worldview and Setting】 Keep the battle content, positional relationships, movements, power dynamics, number of swords, and camera structure fixed. Redesign only the background, props, architectural style, floor material, weather, lighting, color tone, particles, and environmental effects to match the character designs of @1 and @2. Create a new unified cinematic battle stage where both characters can naturally exist, based on their outfits, accessories, weapons, materials, patterns, signature colors, and motifs. Choose the most suitable setting from options such as an academy city, palace, temple, garden, fantasy city, industrial facility, or near-future space. However, do not directly copy the backgrounds from the reference images. Place contact expressions appropriate to the worldview on the floor, such as reflections, water droplets, dust, snow, petals, sparks, or magic particles. Use only props suited to the stage, such as railings, pillars, glass, trees, mechanical structures, magic devices, or glowing lines. Make the background one level darker than the characters, keeping faces, silhouettes, and sword trajectories clear. Use Character A’s signature color for the attacker’s key light, floating-sword aura, and slash afterglow. Use Character B’s signature color for defensive light, counterattack afterglow, and fill light. Keep the two colors separate and clearly distinguishable. 【Fixed Visual Style】 Thin, delicate colored outlines. Clear two- to three-step cel shading and translucent midtones on faces, hair, outfits, and weapons. Eyes have multi-layered highlights; hair has delicate strand definition; outfits are drawn in high density with details present in the reference images, such as embroidery, lace, armor, chains, jewels, and metal fittings. Render cloth, leather, metal, jewels, glass, and flooring with different reflectivity and roughness. Do not use thick black outlines, flat single-layer cel shading, simplified TV anime, generic 3D pretty-girl faces, plastic CG, low-density backgrounds, semi-realism, live action, dull colors, or mixed art styles. Do not copy the art style of the reference images; unify everything into a dense 3D toon/cel look. 【Fixed Weapons】 Character A uses one handheld katana and four floating katanas hovering around the body. The floating katanas are positioned to surround A above, below, left, and right. Character B uses one handheld katana. The total number of katanas in the entire video is fixed at six. Even if the weapons in the reference images are not katanas, redesign them as katanas that inherit the colors, materials, designs, ornaments, and motifs of those weapons. Each floating katana is a complete single katana with blade, guard, and hilt connected. Only during attacks do they move along clear flight paths, and after contact or evasion they return to A’s surroundings. Do not multiply, disappear, fuse, transform, or add extra katanas. Do not make only the tip or blade rotate independently. Handheld katanas are held only by the hilt; do not grip the blade with the hand. 【Floating Sword Effects】 The four floating katanas carry a thin flame-like, mist-like, particle-like, or lightning-like aura centered on Character A’s signature color. The expression type should match A’s worldview, but it must always cling closely to the blade. They leave short trails in the direction of movement and must not become huge independent lasers or separate beams of light. Slash afterglows appear as curved afterglows attached closely to the sweep plane of the katana. 【Power Dynamics】 Character A is the higher-ranked fighter, calmly controlling the initiative. A controls the four floating katanas with staggered timing while also advancing with the handheld katana. Character B deflects, dodges, parries, and attempts to counter the onslaught with high sword skill, but is gradually pushed back as the directions of attack change continuously. Maintain asymmetrical movement where only A advances and only B retreats. 【Camera】 Do not use a fixed side view. Use a diagonal low angle through the floating katanas, over B’s shoulder, close range at the contact point, a roughly 60-degree orbit around the contact point, and a diagonal low-altitude camera closing in on the final collision. Use floating katanas passing in front of the lens, environmental particles, splashes bouncing from the floor, and sword light as short occluding wipes. The camera and background rotate; do not rotate the characters meaninglessly. 【8-Second Action Structure】 Cut 1: Start with the four floating katanas stationary above, below, left, and right of A. The camera passes between two floating katanas from a diagonal low angle, showing A’s face, upper body, ornaments, and handheld katana. A advances quietly, locking onto B with only the gaze. Immediately after, the upper-right floating katana accelerates and flies diagonally toward B’s left shoulder opening. Cut 2: Over B’s shoulder. B uses a two-handed katana to deflect the first floating katana outward at a single contact point between the centers of the blades. Metal sparks, magic sparks in both characters’ signature colors, environmental particles, and counterforce appear. The deflected katana arcs back toward A’s surroundings. Next, the second katana from the lower left skims just above the floor, and B drops low to evade it by a hair. The third katana from the upper left descends diagonally from above, and B turns the katana back to parry it. Cut 3: From behind an occlusion of environmental particles, show A from a diagonal front angle. A steps in without stopping and slashes upward from lower right to upper left with the handheld katana. B blocks while retreating. At the instant the two handheld katanas contact at a single point, the lower-right floating katana enters from B’s side. B pulls the shoulder back to dodge, but the posture drifts sideways. A slides off the contact and releases it, then steps deeper inside B’s range. Cut 4: The camera orbits roughly 60 degrees around the contact point. B uses the counterforce to launch a return slash, but one of A’s floating katanas contacts from the side and diverts B’s katana upward. A swings the handheld katana downward from upper left to lower right. B blocks in a hurry, but the footing slips and B is pushed backward. The remaining three floating katanas spread to B’s left, right, and above, forming an encirclement composition that narrows the escape routes. Cut 5: Diagonal low-altitude camera. A advances in the left foreground, while B is driven back in the right background. B steps in for a final counterattack. A also keeps advancing and launches a rising slash from lower left to upper right. The two handheld katanas form a clear X shape at a single central contact point. One floating katana adds extra pressure from the side onto B’s blade, while the remaining three take their next slashing stances around them. A’s attack color and B’s defense color rise separately, forming a huge two-color X-shaped color plane outside a narrow white-hot core at the center. Radial shockwaves, environmental particles, steam, and sparks spread outward. B’s rear foot slips, the knee sinks, and both arms and shoulders

Style: STOP-MOTION ANIMATION — stepped, frame-by-frame motion brought to a HAND-PAINTED 2D look, a moving oil painting, NOT clay, NOT puppets, NOT 3D. True 12 frames per second, ANIMATED ON TWOS: 12 distinct hand-painted drawings per second, each pose held two frames then snapping to the next, never gliding. Constant painterly BOIL — brushstrokes and outlines subtly alive frame to frame. NO smooth interpolation, NO motion blur, NO morphing, real frame-by-frame animation not AI slop. Style from @[Image 1](image_1), ANA from @[Image 2](image_2), UMAI from @[Image 3](image_3), THE WOLVES from @[Image 4](image_4) — lean steppe wolves, coal-black with cold sheen, pale eyes, the snowy cliff from @[Image 5](image_5). THE INFANT is not a separate reference — render from description: a tightly swaddled baby wrapped in a thick DARK BLUE wool blanket, PRESSED AGAINST ANA'S CHEST in one arm as she clings to the cliff, only a small dark-blue bundle, face barely visible, stirring faintly; NOT a second active child. Heavy weather: drifting FOG, falling and blowing SNOW, gusting WIND. Atmospheric motion (fog, falling and blowing snow, wind-haze, breath-vapor) moves SMOOTHLY; figures, falling rock, wolves and drawn snow-spray step on twos. DIRECTOR'S NOTES: 1. THE SCENE — the catastrophe, the heart of the whole story, and it MUST READ through a precise CHAIN OF CAUSE AND EFFECT, with composition and camera telling the cruel story. As ANA climbs one-armed with her infant, her foot dislodges a rock slab; the slab falls toward little UMAI below; and a WOLF leaps and SHOVES UMAI clear WITH ITS BODY an instant before the slab hits — the wolf SAVES her. Then the pack streams in and carries UMAI away. The wolves do not attack — the first saves her, the pack takes her. This reversal is everything. 2. THE CAUSAL CHAIN — stage each link on screen, cause before effect, on twos: (a) ANA's foot comes down on a ledge high on the cliff, the ledge CRACKS and BREAKS under her weight; (b) a heavy SLAB breaks loose and FALLS straight down toward UMAI — the falling rock the through-line; (c) UMAI stands directly below, looking up; (d) from the side a WOLF LAUNCHES and SLAMS its shoulder and body into UMAI — NOT its jaws, NOT a bite — knocking her sideways clear; (e) the slab CRASHES into the snow exactly where she stood, a burst of powder snow on twos; (f) UMAI tumbles unhurt among the wolves. Every cause visible. 3. THE WOLF SAVES WITH ITS BODY — CRITICAL: the first wolf strikes UMAI with its shoulder/flank, a SHOVE, mouth NOT on her, no bite, no seize — a rescue read as a body-slam. For one instant it LOOKS like an attack — then the rock smashes the empty snow and we understand. Play the shock-reversal. 4. THE PACK TAKES HER — the pack pours in as a fast dark stream from @[Image 4](image_4), varied coats, and SWEEPS UMAI up among them, NOT tearing her, carrying her in the current as they stream away into fog and blizzard. She is small in the dark flowing mass, swept away into the white. The beginning of her life among them. 5. ANA ABOVE SEES AND SCREAMS — high on the cliff, helpless, clinging one-armed with her baby, she SEES and reaches out and SCREAMS her daughter's name. FACIAL ACTING: her held composure SHATTERS — her face breaks open, eyes blown wide in horror, mouth tearing open, all the controlled tenderness from before exploding into raw terror, on twos as snapping held poses of a face coming apart. 6. CAMERA LAW (angle and height tell the cruelty) — SHOT 1 high WITH ANA then a hard VERTIGO TILT DOWN following the falling rock — the height is the cruel mechanism, she is the unwitting cause from above. SHOT 2 LOW at UMAI's level or below — we share the child's helplessness, the rock and the wolf bearing down on us. SHOT 4 the BIG-VERSUS-SMALL angle — ANA tiny and powerless high on the vast cliff, the storm dwarfing her, never powerful, only helpless. Aggressive dynamic handheld throughout, the horizon reeling on the scream, never gimbal-smooth, never tripod-locked. 7. COMPOSITION LAW (the frame tells the story — RUPTURE, the opposite of the vow's affinity) — LINE: the cruel CROSS of forces in the save — the VERTICAL line of doom (the falling rock from above) intersected by the HORIZONTAL line of salvation (the wolf from the side); their crossing on the tiny child IS the story. The pack's flow a DIAGONAL line of dynamics sweeping her off. The vertical gap between mother above and child below now PERMANENT and vast. SHAPE: the angular rock and angular lunging wolf (both read as threat) converging on the small rounded child. TONE: dark masses (rock, wolf, pack) on pale snow and fog, the child the focal point. MOVEMENT: contrast and high intensity — fast violent vertical fall, horizontal slam, diagonal sweep, against the slow helpless reach. CONTRAST & AFFINITY: maximum CONTRAST and PEAK visual intensity — the rupture the vow's affinity has been saving for. SPACE: deep vertical, the cruel distance. 8. FRAMED INK STAGING (read as masses) — FRAME-TRAP the small child between the falling rock above and the lunging wolf from the side, two dark angular masses closing on her. CONCEAL: fog half-swallows the catastrophe, and swallows UMAI as the pack carries her into the white. CAMERA HEIGHT: low and helpless at the child; tiny and powerless at the mother. LARGE VS SMALL: the small child and small distant mother against the vast cliff, the storm, the dark flowing pack. 9. WEATHER — FOG, SNOW, WIND, all smooth: low drifting fog across ground and cliff base, thick snow blown sideways in gusts, gusting wind dragging fog and snow and tearing breath-vapor, the catastrophe half-veiled and swallowed by the storm. 10. SECONDARY ACTION on twos — ANA's and UMAI's clothes hair and breath-vapor whipping, the wolves' fur rippling, the dark-blue swaddled bundle shifting, snow bursting from the rock's impact and the wolves' running as drawn powder on twos; fog and blowing snow smooth. 11. LIGHT — cold grey stormlight in fog and snow, flat soft directionless, no sun, no rays, no beams, no god rays, faces readable. Correct neutral white balance, NOT a blue filter, muted desaturated, snow soft storm-grey white, fog pale grey; nearly BLOODLESS — a rescue not a mauling, any blood dark muted and minimal. SHOT 1 — ON THE CLIFF, ~50mm, aggressive handheld, high on the rock face in fog and blowing snow. COMPOSITION: ANA climbing one-armed in the UPPER frame, the dark-blue swaddled infant pressed to her chest, her boot reaching for a ledge — framed HIGH WITH HER so we feel the drop below. Her foot comes down — the ledge CRACKS and BREAKS away on twos, a SLAB breaking loose. Hard VERTIGO TILT DOWN following the slab as it FALLS down the cliff through the fog toward the tiny figure far below — the vertical line of doom, the height the cruel mechanism. Cut on the falling rock. HARD CUT to SHOT 2 — BELOW THE CLIFF, ~35mm, aggressive handheld, framed LOW at UMAI's level. COMPOSITION (the cross of forces): little UMAI small in frame looking up, fog and snow blowing past — the SLAB falling INTO frame from the TOP straight down at her (vertical line of doom) — and from the SIDE a WOLF LAUNCHES and SLAMS its shoulder and body into her (horizontal line of salvation), the two lines crossing on the tiny child, knocking her sideways clear (jaws NOT on her, a shove not a bite) — and the slab CRASHES into the snow exactly where she stood, a burst of powder on twos. For one beat the two dark angular masses closing on her read as ATTACK — then the empty crater shows the wolf saved her. UMAI tumbles unhurt among arriving wolves. Real weight and impact, all on twos. HARD CUT to SHOT 3 — BELOW, WIDE, ~35mm, aggressive handheld. COMPOSITION (the diagonal sweep): the pack pours

A young creator walks into a bright living room holding a pair of sleek wireless earbuds still inside their charging case. Looking directly into the camera, they smile and say, 'These have honestly become my everyday essential.' They open the case, put the earbuds in, and instantly transition into a quick montage of working on a laptop, making coffee, and taking a short walk outside while music plays. Close-up shots highlight the earbuds' premium design and secure fit. The creator finishes by holding the charging case toward the camera and says, 'Great sound, all-day comfort, and I barely need to recharge them.' End with a clean product hero shot on a table and on-screen text: 'Upgrade your everyday audio.' Natural facial expressions, smooth handheld camera movement, cinematic depth of field, authentic UGC feel, high-quality audio, realistic lighting, premium commercial quality.

Use both attached images as strict reference material. The floor plan defines the exact room layout, dimensions, window placement, door locations, garage position, bathrooms, kitchen, living room, and bedroom. The exterior reference defines the exact architectural style, brick facade, roof shape, front entrance, and garage door. Throughout the transformation, the interior layout must remain perfectly consistent with the blueprint. No rooms may change position, size, or orientation. The video begins with a perfectly flat, top-down 2D architectural blueprint floating on a clean white background. Thin blueprint lines glow softly. The camera slowly descends toward the plan. As the camera gently tilts from overhead into an isometric perspective, the blueprint begins transforming into reality through an elegant architectural timelapse. Walls rise vertically from the floor lines exactly where they exist in the blueprint. Interior partitions emerge first, followed by exterior brick walls. Window openings and doors appear in their precise blueprint locations. The foundation becomes textured concrete. Wooden flooring spreads naturally through the living room, bedroom, and kitchen exactly matching the plan. Bathroom tiles gradually replace the blueprint markings. Kitchen counters, cabinets, island, sink, appliances, and fixtures assemble piece by piece exactly according to the blueprint. Bathroom fixtures, bathtub, toilet, vanity, and shower appear in their designated locations. The bedroom forms with the bed centered exactly where shown. The living room sofa, coffee table, rug, and television materialize exactly matching the furniture arrangement from the blueprint. The garage forms around the parked car in the correct position. The roof structure grows over the house while maintaining the exterior silhouette from the reference image. Red brick textures spread across the exterior walls. Windows become reflective glass. The front entrance, garage door, landscaping, pathway, and surrounding lawn emerge organically. Sunlight gradually fills every room as if the home is coming alive. The transformation is smooth, continuous, and realistic, like watching months of construction compressed into seconds. Dust particles, tiny construction details, framing, roofing, drywall, painting, flooring, furnishing, and landscaping all appear in rapid but elegant timelapse. The final shot reveals the completed fully rendered house from a three-quarter aerial angle. The camera slowly circles a few degrees while sunlight reflects off the windows. Warm interior lighting glows naturally through the windows, emphasizing that every room perfectly matches the original floor plan. Camera: Smooth cinematic movement beginning as a top-down blueprint, gradually tilting into an isometric angle and finishing with a slow cinematic orbit aro

Main subject: Young Korean man, early 20s, natural everyday appearance, oversized cream knit sweater with sleeves slightly covering his hands, relaxed dark olive cargo pants, white worn sneakers, simple silver bracelet on left wrist, medium-length black hair with soft natural waves. Realistic skin texture, minimal styling, calm and thoughtful personality. Maintain identical face, hairstyle, clothing, body proportions, and appearance throughout the entire video.\n\nLocation: Quiet Korean riverside walking path after a light rain. Wet stone pavement reflecting soft daylight, wooden benches, willow trees, bicycle lane, shallow puddles, small bridge in the distance, green riverbank, gentle breeze moving leaves. Peaceful environment with no crowds, shops, advertisements, or tourist activity.\n\nVisual Style: Hyper-realistic documentary footage. Ordinary daily life with spontaneous human behavior. Natural movement, subtle facial expressions, believable environmental interaction. Nothing staged or cinematic.\n\nCamera Style: Mid-2000s MiniDV handheld camcorder. Friend casually filming. Constant handheld shake, imperfect framing, slow autofocus hunting, exposure fluctuations from cloudy skies, occasional rolling shutter, soft image quality, mild digital compression, slight color fading, visible sensor grain, subtle motion blur. No stabilization, no cinematic tracking, no modern grading.\n\n00:00–00:02\nThe recording starts unexpectedly while he stands beside a puddle looking at the reflections. He lightly nudges the water with his sneaker, creating ripples. Camera briefly loses focus.\n\n00:02–00:04\nHe walks along the riverside path carrying a transparent umbrella even though the rain has stopped. The camera trails behind while struggling to keep him centered.\n\n00:04–00:06\nHe pauses beside a wooden railing, watching ducks glide across the river. Wind moves his hair naturally while autofocus shifts between the railing and his face.\n\n00:06–00:08\nHe notices a small fallen maple leaf stuck on his sweater, laughs quietly, removes it, and lets it drift away. The camera zooms slightly by accident before correcting.\n\n00:08–00:10\nPassing beneath willow branches, he reaches up and brushes the hanging leaves with his fingertips while continuing to walk. Sunlight briefly breaks through clouds, causing exposure pumping.\n\n00:10–00:12\nHe sits on a damp wooden bench sipping from a small convenience-store coffee cup. He glances toward the camera with a relaxed smile before looking back at the river.\n\n00:12–00:15\nAs he walks away toward the bridge, he casually turns over his shoulder, gives a small wave, and quietly says, “Gaja.” The operator lowers the camcorder too early, cutting off the top of the frame before the recording abruptly ends.\n\nAudio: Natural ambience only. Light wind, distant flowing river, birds, bicycle passing occasionally, soft footsteps on wet pavement, leaves rustling, ducks spl

Create an 8 second square 1:1 experimental art film featuring a small stack of handmade playing cards placed in the exact center of a deep crimson red textured surface. Use a perfectly locked top down overhead camera with a clean, symmetrical composition. The frame should feel balanced and minimal, with the deck centered and enough negative space around it. No camera movement, no hands, and no surrounding objects. The cards are warm off white with slightly uneven handmade edges, softly bent corners, subtle paper fibers, realistic thickness, delicate contact shadows, and a faint shadow beneath the deck. The background is a rich dark red textured surface, resembling paper, fabric, or velvet, with soft studio lighting, a gentle vignette, and darker edges. Animate the top card using rapid rhythmic stop-motion jump cuts. Replace the card approximately every three frames, creating around eight sharp transformations per second. Each new card should remain briefly frozen before instantly changing into another design. Add extremely subtle deck wobble, tiny positional shifts, slight changes in rotation, natural paper vibration, and occasional one frame motion smears during transitions. Each card contains a different bold editorial illustration created only with black, white, and vivid scarlet-red ink. Cycle through surreal minimalist artwork such as: horse riders, galloping horses, elegant female silhouettes, dancers, abstract human faces, expressive eyes, red lips, flowers, fashion portraits, masked figures, brush painted bodies, geometric facial fragments, mysterious black shadows, and poetic botanical symbols. Use rough ink strokes, screen printed textures, imperfect paint edges, dry brush marks, vintage European graphic design, contemporary fashion branding, handmade collage aesthetics, and refined artistic playing card composition. Include small abstract playing card rank and suit markings in opposite corners, but no readable sentences, logos, captions, or watermarks. Keep the white deck consistently centered while only the illustration, card markings, slight card shape, and tiny rotation change. Synchronize every transformation to a fast sequence of crisp mechanical clicks, card tapping sounds, and minimalist percussion. Build a hypnotic rhythm that becomes slightly more intense toward the end. Finish on a clean card featuring a graceful black human silhouette with one strong red accent. Hold the final image sharply for a brief moment before ending with a direct cut. Visual quality: premium studio photography, realistic paper texture, sharp graphic details, deep red and black contrast, soft cinematic shadows, polished art direction, subtle film grain, high end editorial branding film, smooth 24 fps output while preserving the deliberate 8 fps stop motion transformation rhythm. Avoid: moving camera, zooming, human hands, floating cards, cards flying awa

premium UGC-style bitbyte ad showing a young professional taking a relaxing break from work in a warm golden-hour home office, naturally enjoying a bitbyte with realistic chocolate and wafer details, ending with the message: “Have a Break. Grab Your bitbyte.”

meta: task_type: video_generation style: camera: cinematic_dynamic render: AAA_animation_unreal_engine_quality reference_lock: character_appearance: strict style_and_art_direction: strict priority: cinematic_impact cinematography: shot_type: multi_shot_dynamic_sequence framing: - full_body_visible_during_key_actions camera_height: variable lens_look: 24mm_to_35mm camera_motion: - low_tracking_shot_following_behind - side_tracking_shot - drone_orbit - fpv_drone_chase - handheld_chase - crane_pull_back - speed_ramp - slow_motion_on_key_flip subjects: athlete: type: parkour_runner level: elite attributes: - athletic_build - consistent_outfit_and_appearance_locked - hair_and_cloth_physics_reactive environment: location: modern_realistic_city floor: - paved_street - rooftop_concrete - metal_beams_and_pipes background: - glass_skyscrapers - busy_traffic - pedestrians - street_signs - bridges - construction_zones lighting: - warm_sunset_transitioning_to_blue_hour - volumetric_lighting - realistic_reflections process: - phase: sprint_launch timing: 0s-3s description: - explosive_believable_acceleration - dodge_pedestrians - jump_over_obstacles - slide_beneath_barriers - phase: vault_and_wall_run timing: 3s-6s description: - vault_over_railings - wall_run_across_building - leap_to_next_rooftop - believable_momentum_and_impact_recovery - phase: advanced_parkour_techniques timing: 6s-9s description: - kong_vault - precision_jump - tic_tac_wall_jump - front_flip - perfect_balance_no_floating - phase: rooftop_traversal timing: 9s-12s description: - swing_from_metal_beam - run_along_narrow_rooftop_edge - slide_under_pipes - long_rooftop_gap_jump - phase: final_leap timing: 12s-15s description: - reach_tallest_rooftop - confident_smile - final_cinematic_leap_toward_skyline - freeze_frame_ending motion_rules: pacing: - natural_timing_with_dramatic_speed_ramps - uninterrupted_flow_between_phases physics: - grounded_gravity_present - accurate_center_of_gravity - natural_inertia_and_weight_shift - realistic_foot_placement - proper_landing_compression - cloth_simulation - hair_simulation - no_unearned_floating visual_rules: style: - anime_photorealistic_hybrid - HDR_ray_tracing_reflections - global_illumination - soft_bloom - shallow_depth_of_field - filmic_color_grading - shinkai_inspired_lighting clarity: - body_mechanics_readable_outside_slow_motion_beats

Stop-Motion Chip Stacking — Chips stack themselves into the logo shape or brand initials, then explode apart — playful, highly shareable.

Ultra cinematic dystopian cyberpunk combat sequence, 7 seconds. A platinum silver-haired young man wearing a long black futuristic coat with a white skeletal spine design fights inside a ruined industrial city at night. He wields a glowing black-and-red cyber blade. Faceless armored enemies surround him in smoke and flickering red emergency light. 0.0–1.0s Low-angle close-up. He quickly draws the cyber blade from behind his coat. The blade activates with sharp red energy running along its edge. Wind moves his silver hair and long coat. 1.0–2.3s He dashes forward with explosive speed and performs one clean horizontal slash through the first masked enemy. The enemy instantly dissolves into black digital particles, red sparks, and glitch fragments. No blood. 2.3–3.7s Without stopping, he spins, ducks under an attack, and cuts diagonally through two approaching enemies. Both bodies break apart into ash-like pixels and luminous fragments before touching the ground. 3.7–5.1s Tracking side shot. He runs along a broken concrete wall, pushes off, and performs an aerial rotating slash through another enemy. The enemy vanishes in a circular burst of digital dust. 5.1–6.2s He lands in a low crouch. The long coat sweeps across the wet ground. Remaining particles drift behind him while the cyber blade leaves a fading red light trail. 6.2–7.0s Hero close-up. He slowly rises and turns his face toward the camera, calm and emotionless. The cyber blade powers down as the final enemy disintegrates in the background. Red light flickers, then cut to black. Visual style: ultra realistic, dark sci-fi action film, post-apocalyptic cyberpunk, luxury fashion editorial, ruined concrete architecture, wet reflective ground, heavy smoke, floating ash, red emergency lights, black and cold gray palette, sharp red accents, 35mm anamorphic lens, dynamic tracking camera, controlled handheld motion, realistic cloth physics, fast precise combat, cinematic motion blur, volumetric lighting, film grain, high detail. Combat style: fluid sword choreography, efficient tactical movement, parkour-inspired footwork, precise controlled strikes, continuous momentum, no exaggerated superhero poses. Enemy destruction effect: enemies dissolve immediately into black particles, red sparks, digital glitch fragments, holographic dust, and fading geometric pixels, no corpses remaining.

Cinematic anime short film clip, 15 seconds. Underground street tunnel at night, long dark corridor, walls completely covered in colorful graffiti tags, wet glistening asphalt reflecting dim tunnel lights, raw illegal underground energy, nobody around.

Full magical transformation sequence: a molten phoenix knight floating in a dark volcanic void as glowing embers rise from below and thick smoke coils around them in slow ceremonial waves ,sparks attach to the body, igniting gold-red hair, forging radiant winged armor, tracing molten feather markings across the skin, and forming a burning longsword from compressed flame as phoenix wings unfold behind them. A circular lava-forged ritual seal opens beneath their feet with orange cracks spreading outward, the camera pushes through smoke layers in a slow heroic spiral, each ember burst synced to a rising drum hit, ending in a wings-spread blade-raised signature pose held inside a firestorm starburst. Stock-footage grandeur, played sincere Made in @LumaLabsAI #LumaCPP

A rope bridge stretches across a bottomless canyon. The camera crosses but the bridge dissolves behind each step, forcing the traveler forward

Use the reference image as the only visual basis to generate a 5-second, 9:16, silent image-to-video. Animation requirements: maintain the paper cutout / scrapbook / stop-motion collage style. All elements (people, maps, title cards, copper coins, tracks, arrows, etc.) move as independent cutout pieces. The motion should include: dropped-frame feel, slight paper jitter, segmented displacement, sticker bounce.

[Video Specifications] 10 seconds, 16:9, horizontal full screen. A theatrical dark fantasy anime with a total production budget on the scale of 1 billion yen. No music, sound effects only. No subtitles, no text, no logos. High-quality Japanese dark fantasy anime. Based on 2D cel animation, using high-density digital compositing only for magic effects, glow, particles, and ethereal expressions. A limited color palette based on a dark space, centered on blue, azure, cyan, bluish white, ultramarine, purple, and black. Strong glow, hard shadows, blue and purple rim lights, fine magical particles drifting through the air, thin mist, and atmospheric perspective. [Character] Faithfully reproduce the female character in the reference image attached at generation time. Keep her face, hairstyle, hair color, outfit, physique, and perceived age consistent across all cuts. The woman has a calm, emotionally restrained expression, but her eyes show a clear will and tension as she faces the enemy. She is always looking at the enemy ahead. Even while controlling the magic, she does not keep looking only at the magic circles, but directs her gaze toward the enemy beyond them. In all cuts, both left and right hands have normal five-fingered hands. Do not distort the fingers, arms, face, or human anatomy. [How to Show the Enemy] The powerful enemy they are confronting exists in the back right of the screen or ahead in the direction of movement. Do not clearly show the enemy's full body or true form. Express the presence of a giant enemy through her gaze, strong wind blowing from the enemy's side, subtle ground vibrations, distortion in the air, mist and particles being pushed back, low shockwaves, and ominous backlight shining from the depths of the darkness. The woman and the two phantom beasts all look toward the same enemy. After the summoning, do not have them wait in place. Clearly depict the flow of the woman and the two phantom beasts facing the enemy together. [Important Magic Circle Instructions] The only magic expression used is circular magic circles. There must be exactly two magic circles. Do not increase them to three or more. In every cut, both magic circles must be placed in front of the woman. Do not make them appear overhead, directly behind her, or in positions surrounding her. Place a blue magic circle on the front-left side of the woman and a purple magic circle on the front-right side. Each activates as an independent summoning formula. The magic circles are semi-transparent circular rings or thin disks. They are composed of ancient letters, geometric patterns, multiple concentric circles, crests, and rotating rings. Make them feel mystical and solemn, like an ancient summoning ritual, not a mechanical UI. The blue magic circle emits blue, cyan, and bluish-white light. The purple magic circle emits purple, blue-purple, and pale purple light. [Important Summoning Direction] Do not make the phantom beasts suddenly appear as fully completed whole bodies from the beginning. From the two magic circles, first make only parts of the phantom beasts' bodies, such as hands, forelegs, feet, and claws, appear in an ethereal state. The ethereal parts are translucent, with blue or purple light flowing inside. They do not burst out of the magic circles. Make them quietly, heavily, eerily, and slowly emerge forward, as if a gigantic presence were surfacing from beneath water. Even in short cuts, make it look like a captured instant of slow movement, not a fast charge. The motion of the ethereal parts appearing continues into the next materialization cut, connecting smoothly across cuts into the full-body materialization. Summon one blue-toned phantom beast from the blue magic circle. Summon one purple-toned phantom beast from the purple magic circle. There must be exactly two phantom beasts. The two are summoned to the front left and front right of the woman. Immediately after the summoning, the two phantom beasts stand in front of the woman. After that, the woman walks forward with dignity from between the two phantom beasts and takes the lead in front of the three. Do not depict the woman as hiding behind them under their protection; depict her as a commander who confronts the enemy herself. [Phantom Beast Design] There are exactly two phantom beasts. They have clearly different silhouettes from each other. The first is a giant blue-toned phantom beast summoned from the blue magic circle. It is a heavyweight phantom beast that looks like a fusion of a lion and a dragon, with a base color of blue-black, ultramarine, and cyan. It has sharp fangs, thick horns, a long mane, huge forelegs, and blue glowing eyes. A heavy quadruped type. Dust rises each time it plants its feet on the ground. The second is a giant purple-toned phantom beast summoned from the purple magic circle. It is a phantom beast that looks like a fusion of bird-beast and reptile, with a base color of black-purple, blue-purple, and pale purple. It has a long neck, sharp jaws or a beak, wings or large protrusions on its back, and purple glowing eyes. Give it a slimmer and sharper silhouette than the blue phantom beast, visually distinguishing the two. Both are overwhelmingly larger than the woman. Do not make them remain still like ornaments. Subtly move their breathing, mane, wingtips, tail, ears, claws, and glowing eyes. Both are under the woman's control and take a combat-ready stance toward the common enemy.

anime style, 10 seconds, one-take, no cuts. Keep the same person strictly consistent, with a young girl as the protagonist. Long pale-blonde twin tails, red ribbons, slightly dark eyes, a white and navy sailor uniform, a red ribbon at the chest, and black headphones around her neck. The location is inside a club at the DJ booth. Huge woofers and vertically stacked speakers tower behind her, with silhouettes of the audience in the back. Red, blue, purple, and yellow-green spotlights cut through the smoke, creating the bright energy of a party. Depict the entire piece in a consistent style with perfect visual unity. Use matte flat coloring with no gloss as the base, while the line art has slight flicker and wavering; shadows use shifting hatching, and the whole piece is unified with a semi-sketch style that conveys the dryness of art materials and the texture of traditional media. The camera uses a fisheye lens, handheld, looking slightly down from a diagonal upper angle. 0.0s-2.5s: while swaying widely left and right, it bounces forward and backward rhythmically and dollies in with the feeling of surrendering to the beat. The girl scratches the turntable with her right hand and taps the fader and knobs with her left. She keeps rhythm with her shoulders, hips, and knees, making her upper body move with supple, sinuous motion. 2.5s-5.5s: the camera flows slightly to the right from in front of her, making a smooth semicircular motion as if orbiting forward and backward. Her twin tails and ribbons spring as if wind is blowing through, and she raises her hand, controlling the music through nonverbal hand dancing. 5.5s-7.5s: show the flow of her fingertips tracing her neck, shoulders, and arms; the camera follows that hand in close-up, emphasizing the path of her fingers with strong fisheye perspective. 7.5s-10.0s: as the heavy bass builds, the camera moves up and down while pulling backward, then pushes forward again. The girl briefly makes a short gesture with her hand toward the viewer, then immediately looks up at the camera. Finish with a decisive scratch, ending on an exhilarated feeling close to a smile as she bounces her body. Audio has no singing. Only EDM-leaning tech house, a heavy kick, deep bass, scratching sounds, and cheers from the floor. Overall, it is dynamic and unstable, but the motion remains smooth, graceful, and refined in its flow.

Create a music video; the images are exclusive appearance references and @[blackout video] is the editorial clock. Keep four distinct members, continuous choreography, and an open rightward exit. Use @[image1] only for Vocal 1's final identity and wardrobe.

Create a 3D claymation style animation of a cute caricature of Odysseus, wearing weathered bronze armor, a deep red cape, leather sandals, and windswept hair, sailing alone across a miniature stormy sea in a tiny wooden ship. A gigantic Cyclops suddenly rises from the water and reaches toward him. Odysseus calmly pulls out an enormous olive, launches it into the Cyclops’s mouth with a tiny catapult, and watches as the confused giant begins chewing happily. The storm instantly clears, the Cyclops gives him a thumbs up, and Odysseus takes a triumphant selfie with the giant in the background. Smooth expressive clay animation, epic orchestral music mixed with playful sound effects, handcrafted textures, cinematic lighting, mythological scale, absurd humor, viral energy.

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

Using the attached character reference, create a 15-second ultra-realistic cinematic GRWM (Get Ready With Me) video featuring the exact same young Korean East Asian woman with consistent facial features, hairstyle, glowing skin, body proportions, and identity throughout the sequence. She wears a white fitted athletic crop top, high-waisted red leggings, white running sneakers, a lightweight smartwatch, and a high ponytail throughout the outdoor workout. The video opens with her peacefully waking up in a bright modern bedroom as soft sunrise light streams through the curtains. She smiles, stretches naturally, washes her face, brushes her teeth, completes a quick skincare routine, and changes into her white crop top and red leggings. She ties her hair into a neat high ponytail, fastens her smartwatch, laces her sneakers, picks up a yoga mat, reusable water bottle, and wireless earbuds, then heads outside. She steps onto a lush green lawn surrounded by blooming flowers and tall trees glowing in the golden morning light. She begins with gentle stretching, yoga poses, squats, lunges, planks, push-ups, jumping jacks, and light jogging across the grass. Cinematic tracking shots capture realistic hair movement, natural breathing, and dew sparkling beneath her shoes. Macro shots highlight her smartwatch tracking heart rate, shoes brushing fresh grass, hands reaching toward the sky, and sunlight illuminating her face. After finishing her workout, she drinks water, sits cross-legged on the yoga mat for mindful breathing, smiles peacefully, then returns home. She prepares a fresh strawberry smoothie in a modern kitchen, pours it into a glass, walks to a sunlit window, notices the camera, smiles warmly, raises the smoothie toward the viewer in a friendly toast, and enjoys the peaceful morning as the camera slowly pulls back. Use smooth cinematic transitions, seamless match cuts, gentle handheld and gimbal camera movement, shallow depth of field, premium lifestyle cinematography, realistic skin texture, natural hair physics, physically accurate sunrise lighting, warm golden-hour atmosphere, glossy commercial-quality color grading, 4K HDR, 16:9, with natural ambient audio only (birds chirping, gentle breeze, rustling leaves, footsteps on grass, breathing, water bottle opening, smoothie blending), no background music, subtitles, logos, watermarks, or on-screen text.

# FOOD ANIME COOKING VIDEO Use the provided 12-panel anime cooking storyboard @Image1 as direct sequential visual keyframe reference for the entire 15s animation. Follow the exact panel progression and cooking flow while smoothly interpolating all motion between poses. ## CONSISTENCY Maintain the SAME kitchen environment, cookware, dishware, and hand appearance throughout every scene — full visual continuity across the sequence. Exactly five pork-wrapped asparagus rolls appear through the cooking scenes; after cutting, the same 5 cm bite-sized pieces stay identical in shape and glaze through the bento scenes. ## STYLE beautiful food anime realism, lush painterly food rendering, warm kitchen lighting, realistic cooking physics, accurate culinary movement, stylized but natural steam, soft cinematic depth of field, subtle film grain, smooth editorial transitions. ## REALISM RULES no flying vegetables, no explosive effects, no dramatic splashes, no floating ingredients, no exaggerated anime action, no faces, no full bodies — hands and food only, all motion follows real physics, the knife is always gripped by a hand, blade vertical when cutting, never floating. ## FOCUS food texture realism, elegant hand movement, appetizing sizzle moments, physically correct steam and liquid behavior, satisfying cooking progression. ## SCENE SEQUENCE Scene 1 (0s–1.25s): Slender green asparagus spears, a tray of thin pork belly slices, and small glass bowls of soy sauce, mirin, and sugar rest on a wooden cutting board. Camera: slow push-in. Motion: gentle steam of ambient kitchen air, a hand enters and lightly touches the asparagus bundle. Scene 2 (1.25s–2.5s): Hands trim the woody bottom ends off the asparagus spears with a knife on the cutting board. Camera: fixed. Motion: the knife presses down cleanly through the stem ends, cut pieces settle naturally on the board. Scene 3 (2.5s–3.75s): Hands wrap one thin pork belly slice in a tight spiral around a single slender asparagus spear from bottom to top. Camera: slow push-in. Motion: fingers rotate the spear steadily as the pork ribbon coils around it. Scene 4 (3.75s–5s): A row of five finished rolls on a metal tray is dusted lightly with flour from a small sieve. Camera: fixed. Motion: fine flour drifts down softly and settles on the rolls, the sieve taps gently. Scene 5 (5s–6.25s): The five pale rolls are placed seam-side down into a hot oiled frying pan. Camera: slow push-in. Motion: a gentle sizzle begins, tiny oil bubbles form along the edges of each roll. Scene 6 (6.25s–7.5s): Chopsticks slowly turn the five rolls in the pan, the pork surface an even golden brown. Camera: fixed. Motion: each roll rotates naturally under the chopsticks, faint steam rising. Scene 7 (7.5s–8.5s): A small glass bowl pours the mixed soy-mirin-sugar sauce into the pan around the five browned rolls. Camera: fixed. Motion: the dark sauce streams down, spreads across the hot pan and starts to bubble. Scene 8 (8.5s–10.5s): ★ HIGHLIGHT — the sweet soy glaze bubbles and thickens, coating each of the five rolls in a glossy caramelized sheen: glistening tare sauce, rich amber reflections, fine bubbles clinging to the pork, soft steam curling upward. Camera: slow push-in. Motion: the pan tilts slightly and the rolls roll gently through the reducing glaze, light glinting across the glossy surface. Scene 9 (10.5s–11.75s): On the cutting board, one hand grips a kitchen knife with the blade held straight and vertical, edge down, while the other hand steadies a glazed roll; the knife slices crosswise into 5 cm bite-sized pieces, cut faces showing the bright-green asparagus core. Camera: fixed. Motion: a clean, natural downward knife stroke; the cut piece tips softly onto the board. Scene 10 (11.75s–13s): Hands pack the 5 cm pieces upright with chopsticks into one compartment of an open wooden bento box, beside white rice with a pickled plum, rolled egg omelet, and a cherry tomato — green cross-sections facing up. Camera: slow push-in. Motion: each piece is placed one by one, settling snugly into the compartment. Scene 11 (13s–14s): A spoon lightly drizzles the remaining thick glaze over the pieces in the bento box, followed by a sprinkle of white sesame seeds. Camera: fixed. Motion: the glaze flows slowly off the spoon, sesame seeds fall and scatter naturally over the glossy surface. Scene 12 (14s–15s): The finished bento box, the glossy pork-wrapped asparagus pieces packed neatly beside white rice, gentle steam rising in warm light. Camera: slow pull-out. Motion: soft steam drifts upward, warm light catches the shiny glaze. ## AUDIO Warm homemade-bento mood BGM: cozy lo-fi jazz, 85–90 BPM, brushed drums, mellow electric piano, soft upright bass — gentle and comforting, like a weekday morning kitchen. ASMR cooking sounds synced to action: knife trimming taps on the wooden board, the soft wrap of pork slices, fine flour sifting, oil sizzling as rolls hit the pan, chopsticks turning rolls, sauce pouring and bubbling as the glaze reduces, clean knife cuts through the glazed rolls, pieces nestling into the bento box, thick glaze drizzling, sesame seeds lightly scattering. ## NEGATIVE NO SUBTITLES. NO TEXT ON SCREEN. NO CAPTIONS. NO OPENING TITLES. NO END TITLES. NO WATERMARKS. NO UI ELEMENTS. NO SPEECH BUBBLES.

Create a 15-second Ultra HD 4K anime cooking show POV video inspired exactly by the provided cute omelet recipe image. STYLE: Premium Japanese kawaii anime cooking commercial. Pastel pink/cream chibi kitchen, warm soft lighting, cozy magical breakfast mood, highly detailed food animation. POV: First-person chef perspective. Only show cute female hands and arms (no face, head, or body). Delicate hands with pastel pink nails and frilly chef sleeves. Pink checkered countertop, cinematic camera movement, macro food shots, shallow depth of field. RECIPE: Follow the reference omelet recipe: Crack 3 eggs, add 2 tbsp milk, salt and pepper, whisk fluffy. Melt butter in pan, pour eggs, add cheese, mushrooms, red tomatoes, and green herbs. Fold into a golden fluffy omelet and garnish with herbs. FOOD: Make it extremely delicious: soft airy egg texture, melted cheese stretch, glossy mushrooms, juicy tomatoes, fresh herbs, gentle steam, satisfying cooking sounds. BUNNY HELPER: Add a tiny fluffy white anime bunny chef wearing a mini chef hat and apron. Cute, clumsy, playful helper: tries carrying ingredients, drops a mushroom then fixes it, struggles with a spoon, helps sprinkle herbs, gives a tiny thumbs-up, happily hops beside the finished omelet. Cute mascot style, not realistic. SEQUENCE: 0-5s: Female hands start cooking, crack eggs, bunny joins excitedly. 5-10s: Whisk eggs, butter melts, omelet cooks with fillings and close-up sizzling shots. 10-15s: Hands fold omelet, bunny celebrates, final hero shot of beautiful fluffy omelet with cozy sparkles. QUALITY: 4K UHD 3840x2160, 24fps cinematic animation, smooth hand movement, premium anime rendering, crisp textures, beautiful lighting, cinematic depth of field. MOOD: Fluffy • Savory • Cute • Playful • Heartwarming • Cozy. NEGATIVE: No face, no full body, no realistic human, no scary bunny, no dark mood, no burnt food, no wrong ingredients, no extra fingers, no deformed hands, no distorted bunny, no text, no watermark, no blur.

SCENE CONTEXT RIMEBORN. In a frozen valley of an original ice-fantasy world, a mountain-sized titan of layered ice and stone tears itself free from a millennia-old glacier as an army of armored wardens scrambles across the frozen field below, a war-horn

generate an interesting music video using this image as first frame,be professional and use dynamic visuals

Cinematic anime short film clip, 15 seconds. Outdoor Chinese martial arts training ground, ancient stone platform, traditional Chinese temple with curved red rooftops in background, sparse bamboo on sides, stone lanterns, clear bright blue sky, crisp

CAMERA / LOOK: Propped Mini DV camera on a wooden deck ledge, surrounded by rising steam. Extremely smooth pan, ultra-relaxed pacing, natural soft warm sunlight through mist, calm consumer vlog framing. STYLE: Ultra-chill ASMR

The Adventures of Tom Sawyer — Whitewashing the Fence Characters: * Tom Sawyer — cheerful twelve-year-old boy with messy brown hair, straw hat, rolled-up sleeves. * Ben Rogers — energetic boy wearing suspenders and carrying an apple. Scene: Sunny morning outside a wooden house in a small Missouri town. Tom slowly paints a long white fence with exaggerated concentration while Ben walks up eating an apple. Ben laughs at Tom’s punishment, but Tom calmly insists that painting such an important fence is a rare privilege. Curious, Ben eventually offers his apple just for the chance to paint a few strokes himself. Tom casually hands him the brush and relaxes in the shade, smiling as Ben eagerly does the work. No music. Pay attention to maintain spatial consistency and respect 180 degree rule in cinematography.

STYLE: Handheld selfie vlog — arm's-length front camera, eyes locked to lens, natural micro-shake, bright airy festive tone. One continuous handheld take (no hard cuts); keep the young woman's face perfectly consistent across all shots, same happi robe/hair/smile/makeup. ~8s total. Aspect 9:16 vertical UGC. Color: warm golden sunset glow from festival lighting, lifted shadows, soft skin bloom from paper lanterns, energetic red-orange festival mood. Camera energy stays casual, intimate, and celebratory throughout. === (1) SHOT-BY-SHOT EFFECTS TIMELINE === SHOT 1 (00:00-00:02) — ARM'S-LENGTH FESTIVAL HELLO • EFFECT: handheld motion blur (subtle) + speed ramp (decel into eye-contact) • VISUAL: Young woman's face fills frame at arm's length in the bustling summer festival setting, wearing a bright red-white happi robe and festival headpiece, catching the lens with an energetic open-mouthed laugh; warm golden paper lantern glow and blurred festival crowd bokeh in the soft-focus background. • CAMERA: high-ish front-facing selfie angle (~10-15° down), handheld with organic micro-shake mimicking the movement of the mikoshi (portable shrine) swaying beneath, ~24mm wide phone-style lens, subtle push-in as the arm draws the phone closer. • SPEED: opens ~110% then decelerates to 100% as eyes settle on lens. • TRANSITION: natural handheld drift as the phone tilts down into Shot 2 (no cut). SHOT 2 (00:02-00:04) — JAPANESE CHANT BEAT (SIGNATURE) • EFFECT: SIGNATURE VISUAL EFFECT — intimate handheld eye-contact talk with live lip-sync to Japanese chanting, stacked with breathing rack focus (festival crowd softens into bokeh) + gentle golden ambient bloom from surrounding lanterns. • VISUAL: Woman's face speaks in Japanese: "わっしょい！わっしょい！" ("Wassoi! Wassoi!") with accurate lip-sync to the traditional festival cry, beaming smile, authentic celebratory energy; natural hand gestures (raising fist in festival rhythm) enter frame edge. • CAMERA: chest-up selfie framing in the heart of the festival, ~26mm, constant micro-jitter matching the rhythmic sway of the mikoshi; soft reframe to recenter the face; rack focus pulls the festival crowd and lanterns into creamy bokeh, keeping the face crisp. • SPEED: 100% real-time for honest lip-sync. • TRANSITION: quick handheld whip as the phone swings down to reveal the mikoshi action (motion-blur smear, no cut). SHOT 3 (00:04-00:06) — SHOW-AND-TELL (MIKOSHI & FESTIVAL) • EFFECT: digital zoom (scale-in ~115%) + motion blur + warm light leak from festival lanterns streaking the frame • VISUAL: Phone swings down to show the ornate wooden mikoshi (portable shrine) on the woman's shoulders, intricately carved gold details and crimson drapes catching lamplight; thick festival crowd in happi robes surround her, chanting and dancing; festival stalls with yatai (food carts) and red paper lanterns (chochin) strung overhead glow in the background; waves of heat shimmer rise from the throng; energetic, hot summer-festival atmosphere peaks here. • CAMERA: arm extends to capture the full scene, brief pull-back then digital push-in onto the mikoshi's decorative details and the swaying crowd, ~24mm, lively handheld sway; strong rhythmic shake on the downward swing matching the "wassoi" cadence. • SPEED: micro speed ramp — accel on the swing, settle to 100% on the reveal of the mikoshi. • TRANSITION: phone arcs back up to face on a quick handheld pan (motion blur), no cut. SHOT 4 (00:06-00:08) — CELEBRATION SIGN-OFF • EFFECT: speed ramp (decel) + soft golden bloom + slow-motion accent (~25%) on a final laugh and wave • VISUAL: Back to the woman's face front-on, flushed from exertion and joy, genuine beaming smile, casual celebratory wave toward lens; golden festival glow enveloping the frame, soft bloom on highlights from the sea of lanterns and crowd energy; warm, joyful, unmistakably festival UGC mood resolved. • CAMERA: chest-up selfie, ~26mm, micro-shake easing down as the chanting swells, the tiniest pull-back to give air around the face. • SPEED: ramps down into a ~25% slow-motion held beat on the final wave and radiant smile. • TRANSITION: settle and gentle golden bokeh hold to end (no cut). === (2) MASTER EFFECTS INVENTORY === 1. Handheld micro-shake / motion blur — used 4x (Shots 1,2,3,4) — the constant casual UGC texture, enhanced by mikoshi rhythmic sway. 2. Speed ramp (accel/decel) — used 3x (Shots 1,3,4) — energizes the festival opening, peaks on the mikoshi reveal, and eases the celebratory sign-off. 3. Rack focus / breathing bokeh — used 1x (Shot 2) — SIGNATURE; isolates the woman's joyful face during the intimate Japanese chant beat, softening the crowd. 4. Live lip-sync talk beat (Japanese) — used 1x (Shot 2) — anchors authenticity ("わっしょい！わっしょい！" with accurate sync to traditional festival rhythm). 5. Digital zoom (scale-in/push-in & pull-back) — used 3x (Shots 1,3,4) — draws viewer toward face, then to mikoshi details and crowd, back to face. 6. Warm light leak / festival lantern flare — used 1x (Shot 3) — golden-orange paper-lantern sparkle from chochin and ambient glow on the high-energy show-and-tell swing. 7. Whip pan (handheld smear) — used 2x (Shots 2→3, 3→4) — cutless bridges between face chant and mikoshi reveal, maintaining handheld continuity. 8. Soft bloom / golden highlight glow — used 4x (all shots) — warm festival lantern-lit evening signature tone throughout. 9. Slow-motion accent (~25%) — used 1x (Shot 4) — savors the final celebratory wave and triumphant smile. === (3) EFFECTS DENSITY MAP === • 00:00-00:02 (Shot 1) — MEDIUM DENSITY: handheld blur + decel ramp + push-in + warm golden bloom establish the festive selfie feel without overload; festival chants audible in the background. • 00:02-00:04 (Shot 2) — LOW DENSITY: deliberately intimate for the SIGNATURE Japanese chant beat — only rack focus + golden bloom over the lip-sync, letting the traditional "wassoi" cry and genuine joy carry. • 00:04-00:06 (Shot 3) — HIGH DENSITY: digital zoom + motion blur + warm light leak + whip-pan swing + crowd energy stacked for the peak festive show-and-tell reveal of the intricately carved wooden mikoshi with crimson drapes and glowing chochin lanterns surrounding the celebrating throng. • 00:06-00:08 (Shot 4) — MEDIUM-to-LOW DENSITY: decel ramp resolves into a ~25% slow-mo golden-bloom-soaked celebratory sign-off, winding the peak energy into a warm held smile. === (4) ENERGY ARC === • ACT 1 — HOOK (00:00-00:02): immediate arm's-length eye-contact with the joyful woman's face in the bustling festival setting; warm push-in and a celebratory decel grab attention in the first second. • ACT 2 — DEVELOPMENT / SIGNATURE (00:02-00:06): intimate Japanese chant beat ("わっしょい！わっしょい！") with signature breathing rack focus and golden bokeh (low-density trust moment celebrating tradition), then a high-density whip-and-zoom reveal of the ornate wooden mikoshi on her shoulders draped in crimson, surrounded by cheering happi-robed festival-goers, glowing red chochin paper lanterns overhead, and yatai stalls — the contrast spike that captures the full festive heat and energy. • ACT 3 — RESOLVE (00:06-00:08): camera returns to the woman's beaming face, energy decelerates into a ~25% slow-motion golden-bloom-lit celebratory wave and held smile — warm, joyful, conclusive, and unmistakably authentic festival UGC; the arc fully resolves on a radiant, triumph-filled final frame bathed in festival lantern light.

STYLE Ultra-realistic cinematic adventure, live-action quality, blockbuster filmmaking, photorealistic, seamless visual transitions, grounded physics, natural daylight, HDR, immersive storytelling. CHARACTER A handsome young adult male with short dark hair, athletic build, wearing a black jacket over a gray T-shirt, dark jeans, and sneakers. Natural facial expressions and believable reactions. CAMERA Shot on an ARRI Alexa 65 with anamorphic lenses. Smooth cinematic tracking, aerial camera movements, realistic motion blur, shallow depth of field, seamless transitions. LIGHTING Bright natural daylight with physically accurate sunlight, realistic shadows and atmospheric haze. TIMELINE 0.0–4.0s | Scene 1 Real life like realistic style, natural lighting, The man standing on the rooftop of a tall building overlooking a busy modern city. A massive glowing dimensional portal suddenly opens high in the sky beyond the rooftop in front of him. The camera smoothly circles behind him into an over-the-shoulder view. Curious, he begins running toward the mysterious phenomenon. As he reaches it, gravity suddenly shifts, lifting him off the rooftop and pulling him into the portal. He immediately enters a continuous high-speed freefall through an endless sky. His expression changes from curiosity to complete shock. 4.0–8.0s | Scene 2, Still falling with realistic body movement and accurate wind interaction, a glowing portal appears below him. He passes smoothly through it without interruption. Instantly, the entire environment transforms into a vibrant animated city. Buildings, streets, vehicles, people, and even the character become high-quality animation while preserving his hairstyle, facial features, and clothing design. He looks at his animated hands and outfit in amazement while continuing to fall naturally. Another glowing portal appears below. 8.0–12.0s | Scene 3 He falls through the next portal in one seamless motion. The world instantly transforms into a detailed voxel-style universe with block-built cities, roads, trees, clouds, vehicles, and people. His appearance changes into the same voxel style while keeping the same exact outfit and proportions. He continues falling with believable physics, examining his transformed body before spotting another portal beneath him. 12.0–16.0s | Scene 4 Passing through the next portal, everything transforms into a realistic futuristic sci-fi metropolis with advanced architecture, hovering vehicles, holographic displays, and cutting-edge technology. His clothing naturally changes into a sleek high-tech suit matching the environment, still his face and hands visible as the same character . Still falling continuously, he looks at his futuristic gloves and suit with disbelief while another glowing portal forms below. 16.0–20.0s | Scene 5 He enters the final portal in one perfectly smooth transition. The environment

A grandmother who had been watching TV in the living room stands up, turns around, and looks at her grandchildren. The grandmother gently calls to them, “You kids, go take your bath!” The little sisters cheerfully answer, “Okaaay!” line up the geta they took off, and go barefoot into the living room. The older sister, wearing a purple yukata and much older than them, puts away a bucket while calling to the little sisters, “Wipe your feet!”

Create a crisp, clean infographic storyboard poster for THE MILKSHAKE MAKER. Wide 16:9 layout, white background, black borders, bold black typography, premium Pixar 3D stylized rendering, bright vivid colors — creamy vanilla white, vivid red cherry, pure white

SCENE CONTEXT Inside a vast open-air gladiator arena with a polished white circular floor, a lithe swordswoman duels a hulking armored orc gladiator while packed tiered stands of spectators surround the fight. She works frame-left; he holds frame-right.

Ultra-realistic cinematic beauty transformation, 15s, luxury salon commercial, hyper dynamic, seamless match cuts, speed ramps. Start in a bright minimalist studio with a static front-facing shot. A messy girl in an oversized gray T-shirt and round glasses stands with untidy hair, pale skin, tired expression, no makeup. Two black-gloved hands push her backward. Match cut: she lands in a luxury salon chair inside a dark premium salon. Camera switches to first-person stylist POV. Black cape on. Hair wash, shampoo massage, conditioner, rinse, towel dry. Hair is combed, sectioned, precision cut, textured, blow-dried with volume, softly curled, smoothed, finished with oil and shine spray. Makeup: primer, foundation, concealer, powder, contour, blush, highlighter, brows, soft eyeshadow, winged eyeliner, mascara, glossy red lips. Earrings added. Cape is pulled away, revealing a luxurious red evening dress. Final hair styling. The chair rotates to showcase the hairstyle, then returns front. Final reveal: a confident glamorous woman with flawless makeup, voluminous hair, sparkling earrings and radiant skin looks directly into the camera. Premium luxury beauty ad, perfect identity consistency, realistic hands, smooth motion, cinematic lighting, shallow depth of field, ultra-detailed skin and hair, 4K, no glitches, morphing, deformation, extra fingers or camera shake.

Use @image1 as the exact final hero-frame composition. Use @image2 as the strict product identity lock. Animate like a premium tactile editorial paper-cut product reveal: layered cardstock pieces slide, fold, pop up, and settle with tiny stop-motion overshoot. Mostly locked camera, subtle tabletop parallax only. Physical paper shadows under every layer. PRODUCT LOCK: preserve the perfume bottle silhouette, white geometric lattice, aqua-blue inner body, square cap, central RAYHAAN plaque, front-facing readability, and luxury material finish from @image2. SHOT 1, 16:9, 6 seconds: 0-1.2s: The Dubai paper city comes to life. Skyscrapers lift in staggered layers, small clouds slide, and aqua paper water waves shimmer forward. 1.2-2.6s: The product folds into place. White panels flip inward, the aqua inner body slides behind the lattice, the cap drops on, and the bottle settles cleanly on the plinth. 2.6-4.2s: Ingredients animate once around the product. Bergamot and lemon slices rotate gently, grapefruit blossoms open, Calone waves ripple, and sandalwood strips slide into a neat base. 4.2-6s: The note cards fold in top-to-bottom: TOP “Bergamot, Lemon”, MIDDLE “Grapefruit blossom”, BASE “Calone, Sandalwood”. Preserve exact readable text. End fully settled on @image1. Sound design: crisp paper slides, dry cardstock flicks, soft paper taps, tiny adhesive-peel folds, subtle paper-water shimmer. No music, no voiceover, no extra captions. Constraints: no new text, no misspellings, no duplicated labels, no warped product, no melting or liquid morphing, no CGI camera flythrough, no hands, no people, no watermark.

Create a 15-second photorealistic Chinese latiao commercial using @image1 only as a visual reference for the adult female model, study room, snack package, rooftop gathering, food appearance, and scene progression. Convert it into continuous full-screen live-action

High-maintenance luxury beauty/skincare routine with sassy, condescending ASMR elements CAMERA / LOOK: Propped iPhone/Mini DV camcorder footage on a sleek vanity mirror stand. Soft diffuse lighting, delicate lens flare, gentle zoom adjustments, subtle tape

KAEL DRAYN @[Image] — "Frontier Justice" | Action Sequence. 15-second montage, hyper-kinetic rhythmic editing, variable frame rates. Art Direction & Vibe: Premium key art. Unified style: high-end gritty sci-fi anime render, sharp graphic linework, cinematic

Ultra-cinematic FPV drone flight through New York City during golden hour, hyper-realistic, seamless continuous camera movement, one uninterrupted shot, no cuts, no teleportation, aggressive speed ramp transitions, realistic inertia, dynamic acceleration and smooth deceleration. Begin with a breathtaking ultra-wide aerial establishing shot of the entire Manhattan skyline from above the harbor. The camera instantly accelerates toward Lower Manhattan, descending between skyscrapers at extreme speed. Approach One World Trade Center, smoothly slow down and perform a precise cinematic 360° orbit around the tower, then immediately accelerate through the urban canyon with intense parallax and motion blur. Continue flying at high speed above streets and between buildings toward the Statue of Liberty, rapidly decelerate and execute a smooth 360° orbit around the monument before accelerating once again across New York Harbor back toward Midtown Manhattan. Fly low above avenues and skyscrapers, racing directly into Times Square. Smoothly reduce speed for a spectacular 360° orbit around the giant LED billboards and surrounding towers, preserving fluid camera motion. Exit the orbit with an explosive speed ramp, rapidly climbing above Manhattan into a magnificent panoramic aerial view of the skyline at sunset. End with the camera continuing forward over the city as the skyline fills the frame. Ultra-smooth FPV motion, premium travel commercial, IMAX cinematic quality, HDR, 8K, volumetric sunlight, realistic reflections, atmospheric haze, high-detail architecture, natural colors, dynamic motion blur, stable horizon, seamless transitions, no people focus, no text, no logos, no glitches, no flickering, continuous cinematic flight.

Generate a 15-second, 9:16, ultra-realistic original true wireless earbuds ad. Restrained, quiet, with an urban sense of breathing. Main character: a 28-year-old East Asian female graphic designer, short black hair, natural skin tone, charcoal shirt + white tank top + dark straight-leg pants + low-top canvas shoes. Her face, hairstyle, clothing, and body shape must remain consistent throughout the entire film.

A premium 15-second cinematic 8K commercial for a retro soda brand. Begins with a slow camera push-in on a chilled, rocket-shaped glass bottle with sparkling condensation in a sepia-toned desert sunrise. The bottle cap pops open in slow motion, releasing a burst of fizzy red carbonation and glowing crimson energy. Dynamic FPV drone sweep following the crimson energy as it transforms the barren desert into a vibrant, colorful 1950s raygun-gothic retro-futuristic city. Cheering people in vintage blue and yellow jumpsuits celebrate, a floating metallic retro robot serves drinks, and a character in a heavy dieselpunk armor suit toasts with a bottle. The camera pans up to a magnificent rocket-styled soda fountain under warm golden-hour light, ending on a hero shot of the bottle overlooking the radiant neon city. Anamorphic lens, 8K resolution, volumetric lighting, smooth camera motion, luxury advertising aesthetic.

Classic 1990s Disney-style hand-drawn animation, colorful forest, expressive animal faces, exaggerated physical comedy, smooth cinematic motion, family-friendly humor. Scene 1 — 0–3s: A mischievous raccoon spots a picnic basket hanging from a tree. He stands on a sleepy turtle’s curved shell, stretching upward and saying, “Stay still!” Scene 2 — 3–6s: A tiny butterfly lands on the turtle’s nose. The turtle’s eyes cross, his cheeks puff up, and he desperately tries not to sneeze. The raccoon wobbles above him. Scene 3 — 6–10s: The turtle releases a huge sneeze and pulls into his shell. The shell suddenly rolls forward like a wheel, carrying the terrified raccoon around the pond as he shouts, “Wrong way!” Scene 4 — 10–13s: The shell hits a tree root, launching the raccoon through the air and directly into the hanging picnic basket. Food and fruit explode everywhere. Scene 5 — 13–15s: The raccoon lands face-first in a cream pie. The turtle calmly catches a falling sandwich, takes a bite, and asks, “Did we get it?” The raccoon silently gives him a cream-covered thumbs-up. Fast pacing, clear visual storytelling, natural character motion, playful sound effects, no subtitles, no watermark.

@referance image As first frame. A sharply dressed man in a dark blazer and black shirt stands facing a tall ornate mirror in complete darkness. His reflection stares back — but the reflection smiles while he does not. 0–2s: Medium shot, symmetrical composition — the man on the left, his reflection on the right. Camera holds perfectly still. A cold overhead spotlight illuminates only him and the mirror. His expression is stone-cold. His reflection slowly tilts its head and grins wider. In a deep voice with metallic reverb: "You're not me." The reflection mouths the words simultaneously but slightly delayed. A dissonant string tone swells underneath. 2–5s: On the bass hit, he punches the mirror. Time shifts to extreme slow motion at the moment of impact. The glass cracks in a radial spiderweb pattern from his fist outward. Each crack emits a thin line of white light. Macro detail: his knuckles pressing into the fracture point, glass beginning to separate, light bleeding through. The shards start to lift outward toward the camera, each one containing a different version of his reflection — one laughing, one screaming, one calm, one looking away. Bass reverberates with a metallic distortion. 5–9s: The music drives forward. He steps through the broken mirror frame into a mirrored void — infinite reflections of himself stretching in every direction. Camera pulls back into an extreme wide shot revealing thousands of copies. He walks forward, each copy mirroring his movement but one beat delayed, creating a cascading wave effect. Camera tracks alongside him in a smooth lateral dolly. The copies begin diverging — some stop walking, some turn to face him, some dissolve into particles. He keeps walking, unflinching. 9–12s: The music reaches maximum intensity. He stops. Every copy stops. He turns to face the camera directly. Every copy turns to face him. Silence. Then on the final beat, every copy shatters simultaneously into mirror fragments that fly toward the camera. He remains standing, untouched, as thousands of reflective shards stream past the lens. Final frame: him alone in darkness, no mirror, no copies. One last shard floats past — in it, the smiling reflection winks. Hard cut to black. Cinematic texture, film grain, anamorphic lens flare, shallow depth of field. Lighting: cold overhead spot, white light through glass cracks, infinite reflections multiplying light sources. Audio: dissonant strings, metallic voice reverb, glass impact, slow-motion crack propagation, cascading footstep echoes, silence-to-shatter, massive final impact. 4K Ultra HD. Maintain consistency.

P01: Continuation wide. Vex crouches at the rooftop edge, spotlight sweeping over her as police close in behind. P02: She commits—launching across a rooftop gap in a full-extension jump, hair and bag whipping in the wind. P03: Hard landing

Referencing the face, hairstyle, and body proportions of image_1 — this exact young Asian woman with shoulder-length black hair with bangs, delicate features, and slender figure must remain 100% identical across all outfit changes. Face never changes. 9:16 vertical, 15 seconds, high-saturation commercial style: photo-realistic character on flat graphic animation backgrounds, red-black-white color palette. [0–1.7s] Pure white studio background. Full-body 35mm shot. Character wears simple grey-black outfit, faces camera, holds a transparent plastic cola bottle filled with deep-brown carbonated liquid, red label, red cap. She leans in and twists the cap open with effort. [1.7–2.2s] Cap pops off with a burst — dense bubbles rush upward, cold mist sprays out. Her face shows delighted surprise. A red flash wipes the frame. [2.2–3.5s] Background instantly transforms: deep crimson flat-design. A giant matte-black cola bottle silhouette dominates center frame. Character shrinks and stands inside the silhouette, tilts head back to drink. Bold red and black geometric shapes slide rapidly behind her. [3.5–4s] A giant condensation-covered cola bottle sweeps horizontally across the full frame at high speed with motion blur — TRANSITION 1. [4–6s] Bottle clears. OUTFIT 1 — sporty sweet: red-black cropped top, black shorts, red cap, black sneakers. Same face. She raises one leg, holds cola bottle, energetic jump pose. Floating props: red headphones, black camera, ice cubes, red bottle caps. [6–8s] Cola bubbles explode across frame — TRANSITION 2. OUTFIT 2 — street casual: black oversized tee with red graphic, black wide shorts, red jacket tied at waist, red-black sneakers. Same face. She spins, lands, turns back to camera and raises cola bottle with cool confidence. [8–10s] Giant red bottle cap spins into frame — TRANSITION 3. OUTFIT 3 — hot athletic: red off-shoulder crop top, black high-waist shorts, red-black wristbands, black ankle boots. Same face. She leaps sideways mid-air, one hand drinking from cola. Floating: skewers, straws, ice cubes, cola bubbles. [10–12s] Dark brown cola liquid splashes across body — TRANSITION 4. OUTFIT 4 — cool summer: black cropped top with red trim, red-black shorts, light summer shoes. Same face. Hair gently blown by air current. She floats sideways, holds cola bottle. Floating: red-black swim ring, sunglasses, walkman, small tote bag. [12–13s] A giant ice-frosted cola bottle rises fast from bottom of frame. Character shrinks, floats beside the bottle. Red-black accessories explode outward in a shockwave. Background: deep red and black diagonal geometric blocks. [13–15s] Cut to product close-up: cola bottle front view, transparent body filled with deep-brown carbonated liquid, dense fine bubbles rising continuously, real condensation droplets coating the glass, red label with clean white 'COLA' text only. Black ice cubes and red bottle cap float a

Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, eye color, skin tone, body proportions, and natural expressions throughout. She wears a white fitted crop top, emerald green pleated mini skirt, white sneakers, silver jewelry, and sunglasses resting on her head. Bright summer afternoon, colorful downtown plaza with murals, fountains, palm trees, and skate park. Premium commercial cinematography, vibrant green-and-white Sprite-inspired color palette, photorealistic 4K HDR, 16:9. The video opens with her smiling confidently at the camera while balancing an ice-cold Sprite can on her palm. She flips the can into the air, catches it effortlessly, and pops it open with a crisp "pssst!" A cinematic macro shot captures sparkling fizz, crushed ice, lime slices, and condensation glistening in the sunlight as she takes a refreshing sip. Instantly energized, she laughs while running through dancing fountains, playfully chases floating bubbles, then joins friends at a skate park where she briefly rides a skateboard and celebrates together. Dynamic handheld tracking shots capture genuine smiles, splashing water, and carefree summer energy. The final hero shot shows her stepping toward the camera, holding the chilled Sprite can close to the lens as the fountain sparkles behind her. She smiles and says, "Stay cool. Stay fresh." Natural ambient audio only: can opening, fizzy bubbles, splashing fountain water, skateboard wheels, footsteps, laughter, birds, gentle breeze, and city ambience. No background music, no subtitles, no logos, no watermarks, and no on-screen text (except the Sprite branding on the can). Premium beverage advertising, realistic liquid physics, cinematic handheld and gimbal movement, shallow depth of field, vibrant summer storytelling.

Use the uploaded reference image as the exact character reference. Preserve her facial identity, hairstyle, makeup, skin tone, body proportions, white sleeveless fitted top, light blue wide-leg jeans, pearl choker, rings, and bracelets consistently throughout the video. Premium lifestyle lipstick commercial, 8 seconds, bright luxury apartment, natural afternoon lighting, soft cinematic shadows, realistic beauty campaign. The video opens with the woman standing beside a full-length mirror, smiling into the camera while holding a lipstick. She twists it open and applies it naturally before checking the result in the mirror. Macro shots showcase the lipstick gliding smoothly across her lips and the glossy finish. She picks up her sunglasses and handbag, then confidently walks toward the apartment door. Before leaving, she turns back toward the camera, lifts the lipstick beside her cheek with a playful smile, and the camera slowly pushes in for the final beauty shot. Photorealistic lifestyle advertisement, premium beauty cinematography, shallow depth of field, luxury lighting, glossy lips, elegant camera movement, 4K HDR.

[Style] Trendy beverage fashion transition ad, vertical 9:16, photorealistic + cutout collage graphic style, smooth beat-synced outfit transitions, 8K ultra HD, three-color system of cola red #E61A27 / pure black / pure white [Duration] 15 seconds [Scene] Opening: pure white studio background; from second 2 onward, switch to a solid cola-red background + a huge white curved cola-bottle-shaped cutout frame in the center of the image (classic curved bottle silhouette), with a layer of large dark-red italic “COLA” text pressed into the background; no real brand logo throughout [Character] Protagonist @Image 1 (keep the reference image’s appearance and hairstyle; opening outfit: black raglan long-sleeve top + black wide-leg shorts; all outfit transitions use red, black, and white color schemes) [00:00-00:02] Shot 1: Beat-Synced Cap Twist (White Studio Open) Medium shot on a pure white background: the protagonist @Image 1 holds an unlabeled cola bottle (dark brown soda + red bottle label), crosses both arms, and performs two beat-synced cap-twisting motions. On the third beat, she twists off the cap with a “pop,” and fizz rises. Sound effects: two beat sounds, bottle-cap “pop,” carbonated fizz hiss. [00:02-00:03] Shot 2: One Sip Cuts the World (Snap Transition) She tilts her head back and takes a sip. At the moment she swallows, the background switches entirely with a “snap”: cola-red background + white bottle-shaped cutout frame covering her full body, with dark-red italic “COLA” lettering running across the background. Sound effects: swallowing sound + one deep bass “boom” freeze. [00:03-00:07] Shot 3: Outfit Change 1 - Street Rhythm (Transition Pop / Floating Props) Instant outfit transition: red baseball cap worn backward, white sunglasses on her head, black vest layered over a red tank top, white tights with black polka dots + black shorts, red platform shoes, holding a cola bottle. She does light, upbeat dance steps inside the bottle-shaped frame: one-foot hops, hip twists, and bottle-holding poses. Red-and-white props float around her: cassette Walkman, Polaroid camera, over-ear headphones, sampler, with white 3D text “气泡拉满” distributed across the four corners. Sound effects: beat-synced rhythm + “whoosh” sounds as props fly in. [00:07-00:10] Shot 4: Outfit Change 2 - Present Energy (Kick Jump Pose) Instant outfit transition: white baseball cap, white T-shirt printed with a red graphic, red-and-black jacket tied around the waist, black shorts, red high-top canvas shoes. She does a kick-jump freeze pose, then lands, turns, and swings her hips. Floating props change to: red canvas shoes, white cap, red-and-white camera, sunglasses, and the 3D text changes to “痛快当夏”. Sound effects: continuing beat + “bang” on jump landing. [00:10-00:13] Shot 5: Outfit Change 3 - Floating Summer (Floating Summer) Instant outfit transition: white off-shoulder crop top, red-and-white striped shorts, barefoot, body lying diagonally in a floating swimming pose inside the bottle-shaped frame, holding a cola bottle. Floating around her: red-and-white striped swim ring, yellow rubber duck, red flip-flops, white mesh bag, and 3D text “离开地心引力”. Sound effects: beat turns light + bubbling “glug” sound. [00:13-00:15] Shot 6: Product Poster Ending (End Card) Instant cut to poster image: red-and-black diagonally split two-color background, a close-up of an unlabeled cola bottle in the center (dark brown soda, red bottle label, white “COLA” lettering), with fine water droplets on the bottle. Large white italic text pops in from both sides: “可乐爽人瓶”, with a smaller line below: “#爽出你的痛快#”. Freeze frame, no fade-out. Sound effects: final heavy accent + ending carbonated fizz hiss.

Create a premium UGC-style tropical beverage commercial featuring a beautiful young woman with long wavy dark hair, glowing sun-kissed skin, and a fresh natural look. Tropical beach with crystal-clear turquoise water, white sand, swaying palm trees, bright summer sunshine, cinematic handheld camera, ultra-realistic lifestyle photography. The video opens with the woman smiling directly into the camera while holding an ice-cold tropical sparkling drink beside her face. She playfully rotates the chilled can in her hand as condensation glistens under the bright sunlight. Ocean waves roll gently behind her while the breeze naturally moves her hair. She walks barefoot along the shoreline carrying the drink, smiling and looking back toward the camera. Close-up shots capture her footprints in the sand as waves gently wash over her feet. She pops the can open with a satisfying crisp fizz. Cinematic macro shots reveal sparkling bubbles, cold vapor, and water droplets exploding into the air. The sparkling drink pours elegantly into a glass filled with crystal-clear ice cubes as floating lemon slices, strawberries, mint leaves, and sparkling bubbles surround the glass in slow motion. She relaxes on a beach towel beneath a colorful umbrella, takes a long refreshing sip, closes her eyes, and smiles while enjoying the ocean breeze. Warm sunlight reflects across the chilled can and her glowing skin. The scene transitions to her playfully running into the shallow waves while holding the drink. Water splashes around her legs as she laughs naturally. Slow-motion tracking shots capture sparkling droplets flying through the air. As golden hour approaches, she sits on a wooden beach swing facing the ocean, gently swinging while enjoying another refreshing sip. The sunset creates warm reflections across the water and the aluminum can. The product becomes the focus as the chilled can floats among splashing water, crystal-clear ice cubes, floating strawberries, lemon slices, mint leaves, and shimmering droplets. The camera slowly slowly circles around the product with premium commercial lighting. The final sequence shows the woman standing at the shoreline during sunset, smiling toward the camera as she raises the chilled drink for one final refreshing sip. She then walks barefoot along the beach with the can in her hand while the camera slowly pulls back to reveal the glowing tropical coastline under the golden sky. Style: premium UGC beverage commercial, luxury tropical lifestyle, realistic commercial cinematography, cinematic handheld and drone shots, macro product photography, vibrant tropical colors, realistic water physics, sparkling condensation, shallow depth of field, photorealistic, commercial-quality visuals, 4K HDR, 16:9 widescreen. Negative Prompt: No text, no captions, no subtitles, no logos, no product labels, no watermarks, no UI elements, no duplicate people,

Create a 35-second anime/Ghibli-inspired 2D commercial for Starbucks Bottled Coffee featuring a young man enjoying a bright morning in the city. He picks up a Starbucks Caffè Latte from a convenience store, takes a refreshing sip, then works and socializes with friends in a cozy café while using his laptop and notebook. Warm sunlight, soft colors, expressive character animation, and upbeat acoustic music create a cheerful, inspiring atmosphere. End with a close-up of the Starbucks Caffè Latte bottles.

Create a whimsical, cinematic claymation-style animation of a playful black-and-white cat transforming a grayscale world into a vibrant paradise. As the cat flips, runs, and lands, each step splashes rainbow paint and colorful confetti, bringing grass, flowers, rivers, trees, houses, mountains, and the sky to life. The camera follows with smooth dynamic movements, revealing a charming floating island filled with smiling celestial characters, lush vegetation, and colorful details. End with the cat proudly holding a red flower in a fully transformed, cheerful miniature world. Pixar-quality lighting, handcrafted clay textures, smooth animation, vibrant colors, and magical storytelling.

Create a humorous animated short showing a chaotic morning where a man oversleeps, wakes up in panic, rushes through his routine, grabs a quick breakfast, gets ready in a hurry, and runs through a rainy city trying to catch the bus. After arriving at work, he faces a stressful moment with his boss, only to suddenly fall backward and reveal it was all a nightmare. Use expressive characters, fast-paced action, exaggerated emotions, and a playful cartoon style.

A battle-worn knight in blackened plate armor stands alone on a ruined stone bridge above a bottomless canyon as an army of orcs, trolls and armored war beasts charges through a thunderstorm, the knight lowers a massive glowing sword, sprints into the first ranks, cuts through shields, slides beneath a giant’s axe and climbs onto the creature’s back while lightning tears across the sky; the bridge begins collapsing under the weight of the army, forcing the knight to leap between falling sections, drive the sword into the giant’s skull and release a wave of blue magical energy through the ancient stones; begin with an immense ultra-wide aerial view of the bridge and approaching army, descend into a low-angle tracking shot beside the knight, transition into brutal handheld combat, sharp telephoto impacts and brief slow motion during the final leap, cold moonlight mixed with orange fire, rain, sparks, flying rubble and volumetric mist, desperate mythic atmosphere, ending with the bridge exploding into glowing fragments beneath the invading army while the knight lands safely on the opposite cliff, silhouetted against a colossal lightning strike.

A legendary female knight with long platinum hair, striking green eyes, athletic physique, intricately engraved black steel armor with a flowing crimson cape and a massive enchanted greatsword stands alone atop the crumbling walls of an ancient fortress overlooking a vast battlefield where tens of thousands of soldiers, cavalry and towering siege engines are locked in brutal combat, a colossal dragon suddenly bursts through the clouds breathing an ocean of fire across the battlefield as a gigantic horned demon emerges from a collapsing mountain, without hesitation she leaps from the castle wall, falling hundreds of meters before landing with earth-shattering force that sends armored warriors flying in every direction, immediately charging straight toward the demon while dodging collapsing towers and dragon fire, climbing across the creature's massive body as it tears apart the landscape before driving her glowing sword directly through its skull, triggering an enormous magical explosion that tears open the storm clouds and floods the battlefield with golden light, cinematic IMAX aerial photography, seamless FPV dive, dynamic crane shots, dramatic orbit camera, slow-motion impacts, ultra-photorealistic medieval fantasy, volumetric sunlight, practical debris, cinematic smoke, epic orchestral atmosphere, blockbuster realism, Unreal Engine 5 quality.

High-quality anime video. Refer to the character in the source reference image, and strictly maintain them as the same person throughout the entire video. Use the reference image only to preserve the character’s face, facial outline, eye shape, iris color, hairstyle, hair color, hair volume, outfit, accessories, physique, body proportions, silhouette, atmosphere, and character colors. Do not reproduce the reference image’s background, room, furniture, pose, expression, camera angle, or framing. Only the expression, gaze, mouth, pose, breathing, and natural movement of the hair and outfit may change. Mixing features, averaging the face, changing the hairstyle, changing the hair color, swapping the outfit, losing accessories, changing the body type, turning the character into a different person, cloning, and adding extra people are prohibited. Throughout the entire video, consistently maintain the highest-quality anime expression best suited to the character in the reference image. Use a delicate hand-drawn anime style as the base, with fine lines, elegant transparent colors, and soft, premium anime-style rendering for the skin, hair, fabric, and accessories. If the reference image has a bright mood, make it fresh and airy; if it is calm, lean toward an elegant and quiet direction. However, keep the art style itself consistent, and do not use thick outlines, low-budget TV anime style, semi-realism, live action, plastic-like CG, an excessive 3D feel, or mixed styles. Keep the setting fixed throughout the entire video as a bright outdoor luxury resort space. Maintain white architecture, blue sky, an open terrace, parasols, distant palm trees, and soft daytime natural light as the basic composition. The background should be fresh and bright, with light bokeh and depth so the person appears as the main subject. Preserve the structure of the place, the outdoor resort setting, white architecture, blue sky, terrace, parasols, and palms. On that basis, naturally adjust only the parasols, cushions, flowers, table props, decorative cloth, reflected light, and accent colors in the background to match the reference character’s colors, outfit color scheme, decorative motifs, and personality. The background should remain a supporting element that enhances the character and should not stand out more than the person. Do not change it to a different location. This video is not a strict recreation of the original video; it should keep the same fresh atmosphere while redesigning the camera work into a social-media-ready style that makes the body look attractive. Exact reproduction of expressions is unnecessary, but the face must remain clearly readable throughout. Include multiple face-reward moments where the face, eyes, cheeks, and mouth are clearly visible. Expressions should match the character’s original mood, mainly using a natural soft gaze, slight smile, subtle shyness, or a modest calm smile. The video begins with a medium shot visible down to the thighs. The character faces slightly three-quarters, in a composition where the legs, waist, chest, shoulders, hair flow, and main outfit decorations can all be read at once. From the start, the camera enters with a slightly energetic, smooth forward and diagonal movement, pleasantly tracing upward from bottom to top so the eye flows from the thighs to the waist, chest, shoulders, and face. However, do not leave the face behind; secure enough time for the face and eyes to be clearly visible. The character naturally raises both hands from below. The hands should not hide the face; they rise while passing in front of the thighs, waist, and chest. The fingertips are softly open and relaxed. In sync with that movement, the camera combines a slightly faster slide, light push-in, and shallow orbit to show the body line, outfit structure, decorations, and hair flow one after another. When the hands pass close to the lens, they may create light foreground bokeh, but the face, eyes, cheeks, and mouth must always remain readable. Do not let the hands hide the face for long. The camera is not fixed front-on; it quickly and shallowly orbits left and right as if gliding across the front of the character, showing the thighs, waistline, chest details, shoulders, nape, profile, flowing hair, and outfit decorations at a good tempo. It has momentum but is not too rough, preserving elegance. Occasionally use a slightly lower viewpoint looking upward to show the leg length and the beautiful line from the thighs to the waist. As needed, briefly move from a medium shot visible down to the thighs into a chest-up close shot, then return to the thigh-level medium shot. Create a social-media-ready rhythm through changes in camera speed. In the middle section, compose the sequence so the eye flows from the chest to the hands, from the hands to the hair, and from the hair to the face. Any movable elements present in the reference image, such as hair, skirt hem, coat hem, ribbons, lace, and accessories, should sway softly half a beat behind the body’s movement. The character slightly twists their shoulders, lightly shifts their weight onto one leg, and stands in a way that naturally and beautifully shows the body type and outfit silhouette. Prioritize a refined way of showing the body like a fashion video rather than big acting. Somewhere in the middle section, include a shot closer to chest-up, showing the face and eyes clearly from a more front-facing angle. In the final section, you may use a flow where both arms rise upward, but the camera should not pull back to show the full body. While maintaining a range from a medium shot visible down to the thighs to a chest-up close shot, use a slightly faster diagonal rise, light orbit, and short push-in to beautifully show the shoulders, arms, chest, waist, thighs, hair spread, and main decorations. Prioritize the face reward at the end. The camera naturally moves in from chest-up to bust-up, and the character looks toward the camera from a near-front angle. In the final moment, the character looks at the camera and shows a natural small smile that suits them. The eyes are bright, the cheeks soften gently, and the mouth smiles elegantly. End on the moment when that camera-facing smile looks most attractive. Overall, the camera should not move slowly and observationally; it should follow the person slightly quickly, smoothly, rhythmically, and pleasantly in order to frame them attractively. Make it fresh and elegant, slightly like a fashion PV, bright, refined, and social-media-ready. No text, no subtitles, no logo, no watermark, no extra people, no clones, no collapsed face, no changes to eye shape or iris color, no multiplication of hands, arms, or fingers, no outfit changes, no missing accessories, no hairstyle changes, no hair color changes, no body type changes, no ending pulled back to full body, no hand movements that hide the face for long, no camera that stops abruptly, no stiff standing pose, no background location change, no mixed art styles.

Create an epic cinematic 3D animation/VFX camera showcase featuring a golden Garuda-like mythical warrior battling a celestial masked goddess above floating islands and glowing clouds. Demonstrate a sequence of cinematic camera techniques including extreme wide aerial shots, low-angle monster introductions, tracking circles, dynamic orbits, spirals, close-ups, and fast action angles as both characters unleash fiery orange and cyan energy attacks that culminate in a colossal mid-air beam clash and shockwave explosion. Display a 16-panel storyboard reference grid along the bottom of the screen labeled with each camera move and lens focal length, with the active camera technique highlighted by a glowing white border as the sequence progresses.

Open on an extreme close up of his face reflected in a rain covered bus stop glass panel, breathing hard while distant city lights distort behind him. Without warning, a passing bus completely wipes the frame, and when it clears he is already sprinting full speed down the opposite side of the street. Camera whips across traffic barriers and catches him only partially framed, creating the feeling the operator almost loses him. A flickering overhead streetlight briefly freezes his silhouette in three harsh photographic flashes synchronized to the beat. On the final flash, smash cut to a low rear chase shot as he disappears down a narrow fluorescent underground entrance.

High-quality anime footage. A high-speed sword battle for a cinematic action RPG set in a near-future academy city, rendered in dense 3D toon/cel look. Feature-film-level key animation, high-quality compositing, translucent lighting, and highly detailed background art. @1 is calm and overwhelmingly superior; @2 is a challenger relying on speed and number of attacks. Connect attack, parry, counterattack through reaction force, and maximum collision without interruption. [Reference Images and Character Lock] Interpret the @1 reference image and **@2 reference image as two separate people. Use the reference images only to maintain the face, eye shape, iris color, hairstyle, hair color, outfit, ornaments, physique, silhouette, atmosphere, character colors, and existing weapon design. Do not reproduce the background, room, furniture, text, split layout, pose, composition, angle of view, or framing from the reference images. Throughout the entire sequence, each of the two remains the same individual, same person, same character identity. Only expressions, gaze, mouth shape, posture, breathing, and natural movement of hair and clothing may change. Averaging facial features, mixing traits, swapping hair colors, swapping outfits, swapping weapons, turning them into different people, cloning, duplicates, or adding extra people is prohibited. Extract each person’s main color, secondary color, accent color, material feel, decorative motifs, and worldbuilding from the reference images, and use them from then on as @1's unique colors and @2's unique colors**. Do not swap colors between the two. Redesign the background, props, glowing guide lines, floor reflections, air, steam, lighting, and effects so they harmonize with the two characters’ outfits, ornaments, personalities, and worlds while maintaining the fixed stage structure. However, do not change the flow of the fight, positional relationships, points of contact, or camera order. [Fixed Art Style] Thin, delicate colored outlines. Clear two- to three-level cel shading and translucent mid-shadows on the face, hair, outfit, and equipment. Use the unique colors from the reference images in clear high saturation, with multilayer highlights in the eyes and hair. High density down to the face, hair strands, embroidery, ornaments, metal, gems, and weapon fittings. Distinguish fabric, leather, metal, gems, wet floor, and glass with different reflections and roughness. Use each person’s unique colors in the key light and shadow colors, and keep the background one level darker than the characters. Do not use thick black outlines, flat single-layer cel shadows, simplified TV anime, generic 3D pretty-girl faces, more mature-looking designs, smooth plastic CG, semi-realism, realism, low-density backgrounds, muted colors, or mixed art styles. [Stage and Atmosphere] A rain-washed near-future academy city, a wet rooftop training ground at dusk. Glowing guide lines, colored reflections on the floor, high-rise school buildings, glass walls, city skyline, thin steam. No one is present except the two characters. Architectural ornaments, floor patterns, handrails, lighting fixtures, training equipment, and abstract patterns in distant ads should be matched to the motifs of the reference characters, but no text, logos, or UI should appear. [Camera] Instead of a fixed side view, use, in order: a low three-quarter angle close to the floor following @2, an oblique front view above @1’s chest, an over-the-shoulder view from @1, a roughly 60-degree orbit around the point of contact, and a low diagonal aerial camera closing in on the final collision. The camera and background rotate; do not rotate the characters pointlessly. [Fixed Weapons] Each of the two holds only one sword, two swords total. If a weapon appears in a reference image, maintain its shape, length, decoration, and color scheme; if it is not a sword, redesign it as a single sword that inherits that design language. Fix the number, blade, guard, hilt, sheath, and tassel connections across all cuts. Hands grip only the hilt behind the guard. Move the blade, guard, and hilt as a single weapon from the shoulders, elbows, waist, and support leg; do not rotate only the blade or tip. @1 holds the hilt near the waist with the right hand only at the moment of parrying, and uses the left index finger. @2 holds the sword with both hands. [Movement] Cut 1: Start from the moment when **@1's unique-colored horizontal slash light at the end of the previous clip crosses in front of the lens. The light is a curved afterglow attached tightly to the sword’s sweep plane, not an independent laser. Once the light passes, the camera connects to a low three-quarter position behind @2’s left side, close to the floor. @2 kicks off the wet floor with the left foot and delivers a diagonal downward slash from upper right to lower left toward @1’s right shoulder with a two-handed sword. Water droplets, hair, and cloth lag and stream opposite the direction of acceleration. @2's unique-colored** sword light covers the lens, becoming an occluding wipe into the next close-range cut. Cut 2: When @2's sword light passes, show **@1 from an oblique front view above the chest. @1 does not retreat a single step and remains expressionless. With the right hand holding the sword low, form only one thin @1 unique-colored hexagonal defense plane in front of the left index finger. @2's slash hits the single point of contact at the center of the defense plane, synchronizing a localized flash, hexagonal ripples, and @2 unique-colored sparks. When @1 flicks the finger and wrist a few centimeters outward, the entire defense plane tilts, deflecting @2's trajectory about 45 degrees upward from outside @1's shoulder. Reverse reaction force returns into @2**'s arms, shoulders, and waist, and the support leg steps again. The camera follows the deflected trajectory with a whip pan. Cut 3: At the end of the whip pan, enter **over @1's shoulder. @2 uses the returned reaction force, pivots once on the left foot, flips the waist, and makes a low return slash. @1 returns the left hand to the hilt, receives the strike at a single point between the centers of the blades, then after a short hit stop, slides along the contact surface and knocks @2's sword upward and outward. Immediately, @1 steps into range and counters with an @1 unique-colored rising slash from lower left to upper right. The camera orbits about 60 degrees around the point of contact, and the railing and floor reflections move dramatically. @2 is pushed diagonally backward, performs a half-turn in the air, lands on the right foot, and slides briefly. @1 advances without stopping. Asymmetric movement in which only @2 is pushed back**. The water splash from the landing covers the lower part of the frame. Cut 4: Beyond the water splash, use a low diagonal aerial composition with @1 large in the left foreground and @2 in the right background. Do not place the two side by side. At the end of the slide, @2 replants the right foot and, without stopping, makes an **@2 unique-colored downward slash from upper right toward the center. @1 also continues advancing and makes an @1 unique-colored rising slash from lower left toward the center. From around and behind each person’s feet, huge flame-like auras in their respective unique colors surge upward, accompanied by glowing cracks in the floor, thin lightning, and an updraft. The two colors do not mix. Let the shape of the two swords be readable only for the instant when they enter the same contact point; after contact, hide them in the glow. From the same contact point as the source, @1's straight trajectory and @2's curved trajectory form a giant X. Make only the narrow incandescent center pure white, leaving both characters’ unique colors around it. Maintain large areas of highly saturated color, and spread radial shockwaves, concentric pressure waves, vertical flame-like auras, volumetric light, lightning, sparks, floor water, steam, dust, debris, hair, and clothing outward from the same collision core. Colored effects occupy most of the frame. @1's pressure breaks @2's defensive posture.** The camera briefly rushes toward the contact point, is pushed slightly backward by the shockwave, and tilts a few degrees. Do not turn the entire screen white. [Critical Negative Prompts] Fixed side-view fighting-game perspective, symmetrical full-body composition, resetting the fight by moving the two to the far left and right edges, simultaneous reversal, mirrored simultaneous dash, long run-up, long sword bind, meaningless continuous spinning, independent laser, third beam of light, two-color fusion, full-screen whiteout, text, subtitles, logos, watermarks, UI, no sound generation. [Ending] @1's energy pushes the contact point **toward @2, and the water smoke and dust on @2's side swell backward. @2's silhouette begins to collapse diagonally backward, while @1** keeps a low center of gravity and continues driving force forward. The huge two-color X-shaped light expands to its maximum, and at the moment of contact when the characters and blades are hidden in the light, immediately cut on the frame that captures the beginning of the collapse. Action continues.

Subjects: two men and one woman, who are friends Scene: a bar, where the three of them sit around a table drinking tea Here, one of the men, Man A, says: “Here’s something interesting.” The woman says: “What is it?” Man B says to Man A: “You tell it.” Man A says: “When we were little, boys all liked electric toys, and girls all liked dolls.” The woman says: “That’s true.”

CRITICAL INSTRUCTION: The reference image contains a 9-step chronological cooking storyboard for a Korean BBQ Platter. Animate the chef seamlessly through these exact 9 steps in order. Start at Step 1 (Slice marinated galbi beef ribs), flow into Step 2

<<<image_1>>> Animate each of the 12 frames into a smooth, connected emotional vlog. Natural handheld camera movement with gentle shake. Flow the scenes naturally: sakura walk → teahouse → Philosopher’s Path → torii gate → bamboo grove → street

Super casual real smartphone home video footage of a sunny beach day outing with friends. Natural mobile phone camera recording with slight authentic handheld shake, normal frame rate with smooth natural motion, rapid-fire montage with constant quick jump cuts every 1–2 seconds like scrolling through phone memories. Unpolished authentic phone recording of a mixed group laughing, playing in the sand, snacking and clicking pictures. Pure raw home video feel with no cinematic polish or heavy effects. Use the provided reference photo as the STRICT ONLY visual reference for the main woman. Maintain her exact appearance with zero deviation: [her described features]. Generate a mixed group of friends of all ages around her on the beach. 0–2.5s: Shaky handheld rapid cuts of the main woman laughing with friends near the shoreline. Wind gently moves her hair. Quick flashes of feet in warm sand and waves washing over them. 2.5–5s: Abrupt jump cuts showing a close-up of her smiling with sunglasses pushed up onto her head, followed by the group splashing water and taking casual selfies together. 5–7.5s: Fast handheld footage of her sitting on a beach towel chatting animatedly with friends. Snacks and cold drinks are scattered around. Natural sunlight creates subtle lens reflections and realistic exposure changes. 7.5–10s: Quick cut to a close-up of her giving a big warm smile toward the camera and waving playfully. The footage immediately jumps to the group building a small sandcastle together while laughing naturally. 10–12.5s: Abrupt edit showing everyone gathered beneath a beach umbrella, casually passing chips and cold drinks around. Friends cheerfully toast with cans while talking over one another. 12.5–15s: Final rapid transition showing the main woman relaxed and sitting among her friends, softly smiling while looking toward the ocean. The video ends naturally with a gentle phone sway as if someone simply stopped recording. VISUAL STYLE: - Natural smartphone video quality. - Slight realistic handheld shake. - Smooth normal frame-rate motion. - Authentic casual interactions and physics. - Realistic sunlight and exposure adaptation. - Stable main character consistency. - Unpolished home phone recording aesthetics. - No professional stabilization. - No cinematic color grading. - No beauty filters. - No artificial effects. - No AI artifacts or glitches. IMPORTANT GENERATION REQUIREMENTS: - Consistent identity throughout the video. - Realistic human anatomy and hand interactions. - Natural walking and body movement. - Authentic beach ambience and environmental audio. - Physically correct lighting and shadows. - Rapid memory-style jump cuts every 1–2 seconds. - No duplicated people or objects. - No facial distortions. - No impossible movements. - Preserve the casual smartphone home-video feeling from beginning to end.

Create a luxurious 15-second skincare commercial featuring a beautiful young woman promoting "LUMINA GLOW Brightening Face Wash." Elegant bathroom setting with soft natural sunlight, warm tones, premium beauty-commercial aesthetics, glowing skin, shallow depth of field, smooth cinematic camera movements, realistic facial expressions, high-end skincare advertisement, ultra-realistic, 4K quality. Scene Breakdown: 0-2s: Model holds the LUMINA GLOW Face Wash and smiles at the camera. Product displayed prominently. Text: "Cleanse • Refresh • Glow." 2-4s: Close-up of her applying the face wash to her cheeks and forehead. Soft lighting highlights healthy skin. 4-7s: She gently massages the product into a rich creamy lather. Slow-motion beauty shots, detailed foam texture. 7-9s: Model rinses her face with clear water. Water splashes captured in cinematic slow motion. 9-11s: She dries her face with a white towel, revealing fresh, clean, radiant skin. 11-13s: Close-up beauty shot showcasing glowing, smooth, hydrated skin. Natural smile and confidence. 13-15s: Hero product shot on a premium countertop with flowers and soft bokeh background. Brand logo appears with slogan: "LUMINA GLOW – Let Your Natural Glow Shine." Style Keywords: Luxury skincare commercial, beauty ad, cinematic lighting, realistic skin texture, premium cosmetics marketing, elegant female model, smooth transitions, commercial-grade production, soft glow effect, photorealistic, 4K, high detail, advertising quality, vertical social media ad.

GPT Image 2 Storyboard prompt: “Create a crisp, clean infographic storyboard poster for THE CROISSANT BAKER. Wide 16:9 layout, white background, black borders, bold black typography, premium Pixar 3D stylized rendering, bright vivid colors — warm golden yellows, rich buttery creams, flaky browns, soft pastry whites, warm French bakery morning light. Top header: THE CROISSANT BAKER TOTAL VIDEO TIME: 12 SECONDS 8 SHOTS · WARM · FLAKY · IRRESISTIBLE Legend icons: ACTION, HEAT, TIME HINT, INGREDIENT Thin warm golden accent line running full width beneath header Same Pixar-style young French male baker throughout: white baker's jacket, flour-dusted hands, warm authentic French boulangerie setting, marble countertop, warm morning light streaming through windows, bread racks in background. Bright, warm, delicious. Every panel a completely different composition and color. 8 panels: THE OPENER — Wide shot of baker arriving at the boulangerie before dawn, tying apron, switching on the warm kitchen lights, marble counter visible, bread racks behind, flour dusting the air, full world established, bright and cinematic THE BUTTER BLOCK — Baker slams a massive cold block of European butter onto the marble counter with both hands, dramatic impact, flour cloud puffing up, close-up on hands, this is the bones moment — the start of everything THE LAMINATION — Baker folding the dough over the butter block precisely, rolling pin pressing down hard, layers building, side angle shot showing the beautiful layering beginning, confident and skilled THE ROLL — Dough rolled out into a large thin sheet, baker leaning into the rolling pin with full body weight, marble counter, flour dusting everywhere, wide shot showing the scale of the dough THE SHAPE — Triangles cut from the dough, baker rolling each one from the wide end into a tight crescent, hands moving fast and confident, close-up on the shaping, beautiful and precise THE EGG WASH — Baker brushing golden egg wash over each shaped croissant with a pastry brush, each one glistening beautifully, close-up overhead angle, warm golden color, stunning composition THE OVEN — Croissants slid into the blazing hot oven on a tray, oven door closed, through the oven glass croissants visibly puffing and turning deep golden, layers separating dramatically, warm orange glow THE TEAR — Baker pulls a perfect golden croissant from the rack, holds it up, tears it open slowly revealing hundreds of impossibly flaky buttery layers inside, steam escaping, butter glistening — this is the cheese pull moment, the hero shot of the entire video Footer: VIDEO FLOW: 8 shots × 1.5s = 12 seconds. Butter block to the tear. CAMERA TIPS: wide on opener, close-up on butter slam and shaping, side angle on lamination, overhead on egg wash, oven glass for panel 7, extreme close-up on the tear reveal LIGHT & STYLE: warm golden French bakery morning light, buttery cream tones, flour dust in the air, bright vivid Pixar colors, shallow depth of field on close-ups BAKER NOTES: one baker, one perfect croissant, one irresistible tear. The lamination layers and the final tear are everything — make them stunning.” Seedance 2.0 prompt: “Use the attached THE CROISSANT BAKER storyboard image as the exact reference. Create a 12-second 16:9 animated croissant-making sequence that follows the 8-shot storyboard exactly. Preserve the same Pixar-style young French male baker, white jacket, flour-dusted hands, warm authentic French boulangerie, marble counter, and bright golden color aesthetic throughout. Rules: •Follow the sequence exactly from 1 to 8 •One shot per panel, approximately 1.5 seconds each •No skipped steps, no extra steps beyond the storyboard •Maintain character and bakery continuity throughout •Emphasize the butter slam, lamination layers, crescent shaping, egg wash glisten, oven puff, and final flaky tear reveal Shot sequence: 1.Baker arrives before dawn, ties apron, switches on warm kitchen lights — wide establishing shot, full boulangerie world visible 2.Massive cold butter block slammed onto marble counter — dramatic impact, flour cloud explosion, close-up hands only 3.Dough folded precisely over butter, rolling pin pressing down hard — side angle, beautiful layers building 4.Dough rolled into large thin sheet — baker leaning into rolling pin with full body weight, flour dusting everywhere 5.Triangles cut and rolled into tight crescents — hands moving fast and confident, close-up on shaping 6.Golden egg wash brushed over each croissant — pastry brush close-up, each one glistening, overhead angle 7.Croissants in blazing oven — through oven glass puffing dramatically, turning deep golden, layers separating, warm orange glow 8.Baker tears open a perfect golden croissant — hundreds of flaky buttery layers revealed, steam escaping, butter glistening, pure satisfaction Camera: •Wide establishing shot for the opener •Close-up hands only for butter slam and crescent shaping •Side angle for the lamination •Wide shot for the dough roll •Overhead for the egg wash •Oven glass shot for panel 7 •Extreme close-up hero shot for the final tear Style: •Warm golden French bakery morning light throughout •Buttery cream tones, flour dust particles in the air, marble counter •Pixar CGI vivid expressive animation •Shallow depth of field on close-up shots •Smooth satisfying cuts, warm and joyful energy throughout Goal: A mouth-watering 12-second croissant journey from butter block to flaky tear — warm, golden, layered, and impossible to scroll past.“

GPT Image 2 Prompt: Create a raw kung fu performance storyboard focused on extreme physical action. Use reference image for the character. 16:9 storyboard sheet, 12 cinematic panels. The actual storyboard drawings must be black and white only: rough pencil lines, minimal detail, fast gesture drawing energy, simple anatomy construction and strong silhouette readability. Keep the artwork lightweight, dynamic and unfinished like early fight choreography previs. Start directly in action. Do not begin with a calm stance, preparation shot or slow introduction. A solitary female performer executes an aggressive Tibetan kung fu master-style routine inside a vast ancient temple. The choreography is exaggerated, explosive and constantly escalating: flying diagonal kicks, monk-style low stances, rapid palm strikes, spinning cloth-like body turns, animal-form hand shapes, deep lunges, aerial twists, floor-level sweeps, sudden drops, claw-like blocks, back-arched jumps, sliding recoveries and violent sculptural impact poses. Every panel must contain visible motion and strong body momentum. Avoid static standing poses. The performer should feel like a ritual warrior moving with discipline, fury, spiritual pressure and total body control. Action progression: 1. begin mid-air with a flying diagonal kick already in motion 2. handheld close-up palm sweep cutting through air 3. orbiting wide shot of a full-body spin 4. low-angle impact palm strike with shockwave 5. long-lens side profile spinning kick 6. top-down aerial turn with body, hair and fabric flaring outward 7. hard floor stomp cracking the temple stone 8. sliding low sweep across the floor 9. aggressive close-up flurry of elbows, palms and backfist strikes 10. extreme low monk-style beast stance with energy rising 11. spinning elemental vortex around the body 12. final airborne action pose, suspended above the temple floor, body twisted in a powerful kung fu strike, all elements converging around her before impact Add selective elemental energy effects as VFX-style storyboard accents. The effects should feel spiritual, ritualistic and cinematic, not superhero-like: air bursts around spins and flying kicks, dust and stone fragments lifting from stomps, water-like floor ripples during slides, fire-like trails around explosive strikes, heat distortion around high-intensity movement, elemental vortex near the climax. Element progression: early panels: subtle wind, dust and pressure lines middle panels: stronger stone fragments, floor ripples and air shockwaves late panels: controlled fire trails and energy spirals final panel: the strongest combined elemental surge while the performer is still airborne Use cinematic arthouse action camerawork: handheld energy, whip-pan feeling, orbiting camera moves, overhead shots, side silhouettes, aggressive close-ups, long-lens compression, extreme low angles, wide negative space, strong parallax. Keep the temple environment minimal and atmospheric: towering stone columns, worn temple floor, drifting incense smoke, hanging fabric, harsh light shafts, faint dust in the air, subtle wet floor reflections. Do not overcrowd the frames. Annotation color system: red arrows = body movement blue arrows = camera movement green marks = framing / composition notes orange marks = lighting direction yellow marks = elemental VFX / energy effects black text = short lens notes and panel labels No timestamps. No dialogue. No singing. No extra characters. No enemies. No logos. No watermark. Seedance 2.0 Prompt: Create a 15-second cinematic kung fu performance video. Use @[image1] as the fixed character sheet reference. The character must strictly match the character sheet. Use @[image2] as the storyboard reference. Follow the storyboard shot by shot as the main source for action order, camera rhythm, body movement, framing, movement direction, camera angles and visual progression. Treat each storyboard panel as a sequential keyframe. Preserve the shot order and make the video feel like the storyboard has been translated into continuous live-action motion. The sequence must end on a frozen final frame while the performer is still airborne. Do not add text, captions, storyboard labels, arrows, UI, logos or watermarks. Do not treat the storyboard as a single image. Do not redesign the character, change the costume or alter the face. Do not begin with a calm stance, preparation pose or slow introduction. Do not make the elemental effects look like superhero powers or excessive fantasy glow. Visual style: stylized cinematic realism, high-end 3D painterly animation quality, dynamic cloth simulation, expressive silhouette design, rich cinematic lighting, controlled color palette, natural motion blur, dramatic scale, beautiful but aggressive physicality, premium feature-animation aesthetic. Environment: vast ancient temple, towering stone columns, worn temple floor, drifting incense smoke, hanging fabric, harsh light shafts, faint dust in the air, subtle wet floor reflections, high contrast shadows. The performance is a solitary female kung fu routine inside a vast ancient temple. The routine starts immediately in action, with no calm stance, no preparation pose and no slow introduction. The movement should feel aggressive, ritualistic, disciplined, physically extreme and spiritually charged. This is not a fight against an enemy. It is a solo performance of force, control, exhaustion, fury and release. Follow story board for choreography direction. Element progression: early sequence: subtle wind, dust and pressure lines responding to movement. middle sequence: stronger air shockwaves, stone fragments, floor cracks and water-like ripples across the temple floor. late sequence: controlled fire trails, heat distortion and energy spirals around explosive strikes and kicks. climax: wind, dust, stone, water ripple and fire accents combine into a stronger elemental vortex. final beat: the performer is airborne above the temple floor in a powerful kung fu strike, body twisted mid-air, hair and fabric flaring outward, with all elements converging around her before impact. Elemental VFX must feel spiritual, ritualistic and cinematic. The effects should be integrated with the choreography and motivated by physical movement. Keep the energy raw, elemental, atmospheric and grounded in the temple environment. Use Laban movement logic throughout: weight: strong, heavy, grounded during impacts, with brief lightness during jumps and aerial twists time: quick during strikes, kicks, drops and turns, sustained during suspended holds and recovery transitions space: direct during attacks, blocks and lunges, indirect during spinning turns and elemental vortex moments flow: bound during rooted stances and precise strikes, free during aerial motion, spinning fabric movement and elemental release