Animation style and character consistency

Mixed-Reality Home Vlog Animation

A complex creative prompt designed for Seedance 2.0 Mini, combining realistic home vlog footage with 2D hand-drawn animation reflected in a mirror to create identity-swap and outfit-change effects.

Skill · Animation style and character consistency

Prompt

【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".

Source heat

Stability

待复测

View case →

AI VideoXオズ →

Japanese Anime-Style Mapo Tofu Cooking Process

A detailed prompt for creating a 15-second 2D hand-drawn animated video showing the steps of cooking mapo tofu with professional animation quality.

Skill · Animation style and character consistency

Prompt

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.

Source heat

Stability

待复测

View case →

AI VideoXCiri →

Studio Ghibli-Style Croissant Bakery

This is a cinematic animated-style video prompt designed for Seedance 2.0, intended to present the detailed process of making croissants in a warm Ghibli-style bakery.

Skill · Animation style and character consistency

Prompt

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.

Source heat

Stability

待复测

View case →

AI VideoXSanskriti Naruka →

Anime Style: Cooking Process for Making Indian Steamed Rice Cakes (Idli)

A detailed anime-style storyboard prompt showing the process of making traditional South Indian steamed rice cakes (Idli), including first-person POV shots and polished close-up food photography.

Skill · Animation style and character consistency

Prompt

A fast-paced, silent 10-second anime cooking montage with NO dialogue. Sequence: POV opening a container with rice and urad dal → grinding into smooth fermented batter → greasing idli molds → pouring batter into the molds → placing molds in a traditional steamer → steaming until perfectly fluffy → beautiful South Indian girl removing the hot idlis → macro shot of soft, spongy, steaming idlis → overhead flat-lay of idlis served with sambar and coconut chutney → close-up of the girl silently taking a delicious bite → final aesthetic shot of the steaming idli platter on a sunlit traditional kitchen counter.

Source heat

Stability

待复测

View case →

AI VideoXEyisha Zyer →

Stop-Motion Animation: Wolf Pack Attack Sequence

This is a realistic stop-motion animation prompt designed for Seedance 2.0, describing a brutal wolf pack attack during a blizzard, with a strong emphasis on physics effects and camera movement.

Skill · Animation style and character consistency

Prompt

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.

Source heat

Stability

待复测

View case →

AI VideoXHania Ai →

3D Baking Animation Sequence

This is a comprehensive prompt designed for Seedance 2.0, intended to transform a visual storyboard into a 10-second 3D animation showing a girl baking cupcakes with a specific timeline of actions.

Skill · Animation style and character consistency

Prompt

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.

Source heat

Stability

待复测

View case →

AI VideoXSoran →

2D Sticker Capybara Kitchen Prank

A mixed-media video prompt for Seedance 2.0 combining a realistic 1st-person kitchen POV with a 2D animated capybara sticker character performing a salt-pouring prank.

Skill · Animation style and character consistency

Prompt

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

Source heat

Stability

待复测

View case →

AI VideoXNoorAI →

Anime Floral Bookmark ASMR

A Ghibli-style anime ASMR scene showing the process of handcrafting a delicate pressed-flower bookmark.

Skill · Animation style and character consistency

Prompt

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

Source heat

Stability

待复测

View case →

AI VideoXPiotr Binkowski →

Hand-Drawn Stop Motion: Blizzard Scene

A refined stop-motion animation prompt designed for Seedance 2.0, aiming to present a hand-drawn 2D style and depict a wolf pack attacking a Kazakh yurt camp in a blizzard.

Skill · Animation style and character consistency

Prompt

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.

Source heat

Stability

待复测

View case →

AI VideoX咲山(AIイラスト・AI動画垢) →

Anime OP-Style Dance Animation

A detailed animation prompt for generating a fast-paced Japanese anime opening-style dance, focused on precise hand movements, cel aesthetics, and character consistency.

Skill · Animation style and character consistency

Prompt

Analyze the character information in the reference image as the highest priority, extracting and preserving the facial features, hairstyle, hair color, eyes, skin, clothing, accessories, body type, color palette, and atmosphere. Do not merely reproduce the appearance; extend the extracted colors, textures, and mood into the text, lighting, hand trajectories, background, camerawork, and impact frames. A bright, fast-paced Japanese metaverse anime OP-style dance. The character faces forward and, in time with a light rhythm, switches quickly through the following movements at short intervals: raise both hands beside the face → extend one hand diagonally upward → place the opposite hand on the waist → take small steps left and right → quickly cross both arms in front of the chest → open both hands widely outward → lightly lift one foot while tilting the body diagonally → point left and right alternately with the index finger → gently wave both hands beside the cheeks. Both feet do not leave the ground. The movements should not be too large; they should be small, fast, slightly comical, and cute. Clearly show the poses of the arms, wrists, and fingertips. This is not a dance with intense hip shaking; the choreography should center on the upper body and hand movements. Insert a brief freeze pose midway, then immediately switch quickly into another pose. The expression is energetic and happy. The camera should basically use a full-body shot from the front. Japanese full-color anime, TV anime style, cel look, flat colors, smooth lines and coloring, light and rhythmic editing like an anime opening.

Source heat

Stability

待复测

View case →

AI VideoXmayv@簡単プロ級プロンプト公開中！ →

Magical Urban Fantasy Battle Animation

An epic high-fantasy anime battle prompt set in a rainy magical city. It includes complex visual effects such as multiple magic gates and beam attacks against a giant dragon, with an emphasis on cinematic quality and 3D toon-rendered aesthetics.

Skill · Animation style and character consistency

Prompt

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

Source heat

Stability

待复测

View case →

AI VideoXmayv@簡単プロ級プロンプト公開中！ →

Cinematic Anime Magic Sword Battle

A highly detailed cinematic animation prompt for an intense 3D toon/cel-style action RPG sword duel, featuring floating swords and precise character interaction.

Skill · Animation style and character consistency

Prompt

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

Source heat

Stability

待复测

View case →

Install into your agent.

Methods stay attached to their makers.

Judge the Skill through finished work.

Mixed-Reality Home Vlog Animation

Japanese Anime-Style Mapo Tofu Cooking Process

Studio Ghibli-Style Croissant Bakery

Anime Style: Cooking Process for Making Indian Steamed Rice Cakes (Idli)

Stop-Motion Animation: Wolf Pack Attack Sequence

3D Baking Animation Sequence

2D Sticker Capybara Kitchen Prank

Anime Floral Bookmark ASMR

Hand-Drawn Stop Motion: Blizzard Scene

Anime OP-Style Dance Animation

Magical Urban Fantasy Battle Animation

Cinematic Anime Magic Sword Battle