AI Prompt Library

Cinematic photorealistic texture, pure ancient Chinese Xianxia high-tension dual combat. This time completely break out of previous modes: Constant weapon changes Single combat breaking The core becomes: The two protagonists themselves are a continuously moving dual tactical system. One absorbs pressure from the front The other changes the situation from the flank Immediately swap roles in the next second The real thrill is not flashy sword qi, but that the two protagonists almost don't need to turn back to confirm, can constantly cover each other's blind spots, forming stronger and stronger tacit understanding and tension. Character and Asset Locking Strictly lock only @image 1 and @image 2 as the two core characters. @image 1 | Sword Immortal Senior Sister Image 1 Sword Immortal Senior Sister always maintains original: Adult East Asian female identity Face Black long hair half-up White jade hairpin Tall slender proportion White embroidered silk Hanfu Semi-transparent layered wide sleeves Silver waist seal Jade pendant White cloth boots Only one silver straight sword @image 2 | Junior Sister Image 2 Junior Sister always maintains original: Adult East Asian female identity Face Braided black hair Green linen Hanfu Dark belt Wooden hairpin Black cloth shoes Only one dark steel sword Other Characters Enemies, Master, Passersby are all functional characters only, no need for complex face locking, clothing locking. Environment DNA All uploaded background and location reference images this round jointly determine the same set of Environment DNA. Before formal generation, silently analyze compatible elements among them: Terrain Architecture Height differences Spatial scale Material age Vegetation Water bodies Weather Mountain mist Lighting Reflections Air depth Routes passable by characters Then recombine into a unique but credible new space for this round. Space and Route Principles The entire 15 seconds must occur in a continuous understandable combat route, cannot suddenly switch to another world. Background remains dynamically active but narratively neutral: Wind Water Mist Leaves Clothing hems Reflections Distant figures Always naturally active. Only when characters truly: Step Collide Grazing Weapons touching environment Do these appear: Dust Ripples Debris Scratches Clothing displacement etc. passive physical feedback. Strictly Prohibited Bridge suddenly breaking Mist suddenly saving people Tree suddenly blocking sword Building collapsing itself to help either side Segmented Structure 0–5s | Wide shot entering medium shot Same white-robed Sword Immortal Senior Sister and same green-robed Junior Sister standing back-to-back. Three enemy swordsmen who only bear combat function press in actively from different directions. 0–1s Use 24mm fixed wide panorama, letting audience understand at once: Positions of five people Attack directions Space available for movement next Junior Sister lowers voice, says only one line: "This time, don't turn back to save me." Senior Sister never turns back throughout, calmly answers: "Good." As soon as the last word lands, enemies launch simultaneously without warning. Camera quickly moves from fixed 24mm into 35mm medium-close range motion, but doesn't shake randomly, instead brought in by the characters' true movement lines. First Round Engagement One enemy attacks Senior Sister from above Another enemy cuts into Junior Sister's blind side simultaneously The two women explode in opposite directions almost instantly: Senior Sister briefly changes attack line of first sword then directly advances position Junior Sister lowers center of gravity grazing second attack, only counter-attacks enemy's weapon path, doesn't stop to pose Two immediately start migrating forward along routes truly existing in reference environment. A high-speed foreground passing enemy body briefly fills lens, using this real occlusion to complete first hidden cut, audience barely feels camera position has changed. 5–10s | Medium shot continuous follow Maintain: Same space Same two protagonists Same weapon ownership Enemies absolutely cannot queue up to send moves, they continuously: Chase Surround Intercept At this time: Senior Sister bears continuous pressure from two enemies Junior Sister faces another enemy Cannot split screen into "two fighting separately", must let two combat lines constantly interweave. First Tactical Complement Senior Sister deliberately yields half step, bringing one pursuing enemy into Junior Sister's advancing attack line. Junior Sister doesn't look at Senior Sister at all, only at the instant enemy's sword tip truly enters her space, briefly catches and changes weapon direction with dark steel sword, immediately releases, continues handling person in front. Second Tactical Complement Less than a second later, exact opposite happens again. Another enemy launches true attack from behind Junior Sister. Same white-robed Sword Immortal doesn't even turn back, silver sword tip enters from other side of frame at high speed, uses only one extremely short metal impact to push that sword out of dangerous line behind Junior Sister, then silver sword immediately leaves frame, Senior Sister continues own fight. Core State Two people never confirm each other's positions, yet accurately know where the other is. Camera glides smoothly between foreground and midground, utilizing following elements sweeping past lens at high speed to form 2-3 extremely natural hidden transitions: Enemy shoulders White wide sleeves Green clothing hem Weapons Rhythm Requirements Action rhythm isn't one speed from start to finish, but: Two fast exchanges One truly weighted weapon collision Half-beat silence Then sudden explosion Same older Master stays in distant safe zone observing, doesn't act from start to finish, doesn't solve problems for anyone. 10–15s | Close shot entering final wider medium shot Three enemies discover single pursuit ineffective, first time truly change strategy simultaneously, compressing space from three directions, forcing Senior Sister and Junior Sister toward same central area. Form obvious deadlock. Two don't continue retreating. Same white-robed Sword Immortal and same green-robed Junior Sister suddenly burst sprint towards each other simultaneously. Camera doesn't cut immediately, lets audience fully see: Two shoulder lines graze in high speed, bodies cross through each other with minimal distance. At moment of crossing, two fully swap front-back positions. And neither looks at the other. Tactical Flip After Swap Senior Sister while passing Junior Sister, directly takes over enemy originally attacking Junior Sister's blind side Junior Sister simultaneously cuts into line of enemy originally chasing Senior Sister One enemy longsword sweeps across entire camera at high speed, forming only one obvious weapon occlusion hard cut. Cut to brand new reverse axis: Senior Sister now stands at position Junior Sister just left Junior Sister also stands at position Senior Sister just left Both immediately complete two extremely short, extremely direct, no showy rotation reverse breaks: Silver sword tip safely stops one finger-width before an enemy's chin Dark steel sword simultaneously safely stops outside another enemy's sword-wielding wrist Third enemy prepares to strike again, but finds both effective attack lines completely blocked by companion's position, can only force retreat. Sudden Stop Moment Previously dense: Whooshing sounds Metal collisions Shoe sole skid sounds Collapse suddenly at this moment. Leaving only: Two women's true breathing Extremely light residual vibration of swords Silk clothing hems gradually falling Senior Sister still looking at enemy in front, asks without turning head: "Still alive?" Junior Sister pauses almost none: "Easier than you." Senior Sister's mouth corner shows only extremely brief, extremely light hint of smile. Distant same Master finally lightly exhales breath held throughout, but doesn't preach, doesn't explain relationship between two. Ending State After victory confirmed, absolutely no victory poses. Two women lower sword tips simultaneously, maintain original pace continuing forward through same space; three enemies instinctively yield road. Hair, clothing hems, environmental wind, water mist, debris continue natural movement, picture ends directly while characters still moving forward. Camera and Editing Requirements Strict total duration 15 seconds 16:9 landscape Maintain 0–5s / 5–10s / 10–15s three clear narrative segments Visually dominated by one continuous silky camera path Whole film allows only about 4-5 hidden cuts or cuts truly triggered by impacts Prohibit crazy fragmented cutting for "action feel" Seedance 2.0 Mini Execution Focus For Seedance 2.0 Mini, actively control prompt budget. Most important is: Image 1, Image 2 two protagonist identities stable Two swords' ownership stable Hands and bodies continuous Two people's spatial relationship continuous Core environment route continuous Three enemies only need to maintain: Ancient style enemy swordsmen Basic functional appearance That's enough, don't waste model attention strictly locking faces, clothes and details. Sound and Motion Requirements Native synchronized Mandarin dialogue Native synchronized spatial audio effects Focus strengthening: Sword tip brief whoosh Real metal collisions Shoe sole friction Silk clothing hem twitching Characters' true breathing Final sudden quiet sound contrast Motion Texture 24fps cinematic motion texture Natural motion blur Actions must have clear: Start Acceleration Force application Line change Inertia Braking Strictly Prohibited Teleportation

Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing an oversized maroon hoodie and loose casual pants, carrying a simple canvas shoulder bag. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout. Location: Quiet older Seoul neighborhood on a pleasant morning. Narrow residential street with low-rise apartment buildings, small local shops, parked bicycles, potted plants and modest storefronts. A little Korean girl, around 5–6 years old, is standing safely near the sidewalk with a small ice cream cone in one hand. Her shoelaces have come completely undone. Lighting & Atmosphere: Warm, cheerful and cozy morning atmosphere. Soft sunlight filters between the buildings, creating gentle warm highlights while some areas remain naturally shaded. Muted surroundings, soft shadows, slightly faded colors and a nostalgic early-2000s feeling. The scene should feel wholesome and ordinary rather than sentimental or cinematic. Style: Ultra-realistic early-2000s Sony MiniDV home video filmed by another person casually walking with her. Multi-shot but completely candid and unstaged. Natural handheld movement, subtle camera shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle digital noise and natural microphone noise. Shot 1 — 00:00–00:04: Medium-wide handheld shot as the young woman walks casually down the quiet street. She notices a little girl standing near the sidewalk, holding an ice cream cone while looking down at her untied shoelaces with a confused expression. Shot 2 — 00:04–00:07: The camera moves slightly closer as the woman slows down. The little girl looks at her shoelaces, then at her ice cream, clearly unsure how to deal with both at once. The woman understands the problem and gently gestures toward the laces, asking if she can help. Shot 3 — 00:07–00:11: The woman crouches down beside the child and carefully ties the loose shoelaces into a secure bow while the child stands still, carefully holding her ice cream away from them. The woman's movements are gentle and efficient. Shot 4 — 00:11–00:14: She gives the finished shoelaces a quick little check and stands back up. The child looks down at her shoes, then looks up at the woman with a small grateful smile. Shot 5 — 00:14–00:17: The woman gives the child a warm little smile and a tiny nod, then continues walking down the street. The child happily takes another bite of her ice cream. Shot 6 — 00:17–00:20: As the woman walks away, she briefly turns toward the camcorder and gives a quiet, contented smile before looking forward again and continuing down the street. Audio: Natural sound only—soft footsteps, distant traffic, subtle neighborhood ambience, children's distant voices, light breeze, fabric movement and the natural sounds of the street. The ch

cinematic street racing sequence at night, a focused driver inside a high-performance car grips the steering wheel, intense eye focus, city lights reflecting on windshield, tension building before sudden acceleration camera: rapid multi-angle system with seamless transitions, interior close-up → over-the-shoulder → exterior tracking → low ground shots, ultra dynamic camera movement, whip pans + speed ramp transitions + motion blur masking cuts, continuous flow illusion (0-2s) interior close-up on driver, hand tightens on gear shift, subtle breathing, dashboard lights glowing (2-4s) over-the-shoulder shot, road ahead stretching into neon-lit city, engine vibration building (4-6s) extreme close-up on finger pressing NOS button, instant ignition reaction (6-8s) explosive acceleration, camera snaps to exterior side tracking shot, car launches forward with violent speed surge (8-10s) ultra low ground shot near asphalt, wheels spinning at extreme velocity, environment streaking past (10-12s) high-speed chase through tight streets, sharp turns, camera whip pans between angles, reflections and light trails enhancing speed Dense urban night environment, wet asphalt reflecting neon lights, tunnel passages, street lights streaking, high-speed city atmosphere Ultra realistic, fast and furious inspired energy, photorealistic lighting, intense motion blur, high contrast neon reflections, cinematic depth of field, extreme sense of speed, fluid transitions, no distortion, no stretching

Created a 20 seconds cinematic Japanese-style scene of a young schoolgirl walking alone through a quiet Japanese residential street during warm golden-hour sunlight, shown from behind as she slowly approaches a railway crossing with a train passing in the background, then transitioning to a close-up of her face and flower-decorated hair as she watches the train, followed by a wider shot of her standing near a quiet canal with soft evening light reflecting on the water, then showing her gently touching small white flowers in a golden field, with close-up shots of her hand and the flowers moving naturally in the breeze, gradually transitioning to a wide sunset landscape with the girl standing peacefully in the field, and finally ending with a warm close-up of her face as she softly looks toward the camera, maintaining the same character, hairstyle, school uniform, realistic skin details, natural expressions, smooth cinematic camera movement, soft depth of field, warm sunset lighting, realistic Japanese environment, subtle film grain, peaceful emotional atmosphere, and a dark fade-out at the very end.

People are not magical instruments, nothing needs to be useful prompt: Cinematic realistic texture, pure ancient Chinese Xianxia aesthetics. Centered on mature social tension, restrained dark humor, and authentic character relationships, thoroughly translating the current mood where "all interests seem to have to become skills, grades, profits, and self-improvement" into an ancient Xianxia character drama. Core Principles No modern vocabulary Avoid cliché twists like "seemingly useless hobby actually hides peerless martial arts, hidden inheritance, key combat ability" The cup is just an ordinary, even slightly warped cup from start to finish It truly carries character values References and Environment Strictly use @image 1 and @image 2 as character identity anchors. Silently reorganize all newly uploaded background and location reference images into a unified environmental DNA, naturally blending compatible elements: Ancient architectural language Real terrain Spatial scale Weathered materials Vegetation Water bodies Roaming mountain mist Slow-moving clouds Reflections Main light direction Atmospheric depth The entire environment must remain vivid but absolutely neutral narratively. Character Settings Character ID A | Sword Immortal Senior Sister Always the same @image 1 Sword Immortal Senior Sister: 25–30 year old East Asian female Oval fair face Dark almond eyes Black hair half-tied, fixed with white jade hairpin Tall slender figure Wearing the same set of white embroidered silk Hanfu Translucent wide sleeves Silver waist seal Jade pendant White cloth boots Holding the only silver long sword Character ID B | Junior Sister Always the same @image 2 Junior Sister: 20–25 year old East Asian female Round lively face Black hair braided Small stature Wearing the same set of green linen Hanfu Dark belt Wooden hairpin Black cloth shoes Holding the only dark steel sword Other Secondary Characters One elderly master One competitive fellow disciple Several disciples who just returned from seven-day rest Segment Structure 0–5s | Wide or Long Shot Disciples display their seven-day gains in order: Some bring back sword manuals Some bring back demon cores Some collect precious medicinal herbs When it's Junior Sister's turn, she quietly takes out a self-fired, slightly warped, obviously not beautiful ordinary clay cup from her bundle and places it in the center of the table. The master looks for a moment, then says: "Seven days of rest, others broke realms and understood swords — you just fired a cup?" Junior Sister nods naturally: "Mhm." The first shot must immediately form a contrast hook. 5–10s | Medium or Cowboy Shot Maintain same characters, clothing, clay cup, and completely consistent spatial relationships. The competitive fellow disciple picks up the clay cup, asking with a bit of incomprehensible smile: "Can it break realms?" Junior Sister answers: "No." Fellow disciple continues: "Can it exchange for spirit stones?" Junior Sister answers: "No." The master finally asks the question everyone wanted to ask: "Then why learn it?" This time, Junior Sister hesitates briefly for the first time. Even a bit embarrassed because the answer is too simple. After pausing half a beat, she says: "...I want to learn." Surrounding disciples glance at each other, some suppress laughter. Just when viewers think Senior Sister will also scold her, the same white-robed sword immortal says nothing, calmly takes back the warped clay cup from the disciple's hand, and pours herself a cup of tea. Wind, water bodies, mountain mist, vegetation, cloud shadows, fabrics, and distant pedestrians in the background continue to change realistically and naturally, but must never participate in character conflicts. 10–15s | Close-up or Extreme Close-up Master looks at Senior Sister, asking: "Internal sect assessment is imminent, are you still letting her play?" The same Sword Immortal Senior Sister lowers her head to seriously look at the warped rim, directly answering: "This doesn't count as progress." Junior Sister's eyes visibly darken for a moment, causing viewers to misjudge again—Senior Sister actually doesn't agree with her either. Fully preserve a deceptive half-beat. The next second, Senior Sister naturally drinks a sip of tea with this cup, adding: "That's why it's rare." Master frowns: "What does that mean?" Extreme close-up falls on Senior Sister. She doesn't look at Master, but looks at Junior Sister, saying: "She finally did something — not used to prove herself." The scene falls completely silent. Junior Sister's previously uneasy gaze slowly relaxes. That fellow disciple still quietly adds: "But it's still useless." Senior Sister hands the clay cup back to Junior Sister, saying only: "People are not magical instruments." Full pause for the final half-beat, then delivering the last line: "Nothing needs to be useful." Ending Hard Constraints Never arrange applause Never suddenly reward Never let master announce exceptional promotion Never let the clay cup suddenly exhibit any magical abilities This warped cup remains just an ordinary warped cup at the end Hard Requirements Strict total duration 15 seconds 16:9 Landscape Strictly three consecutive clear shots Native synchronized Mandarin dialogue Precise lip-sync and gaze relationships Character identities, hairstyles, clothing, long sword, clay cup, and supporting character positions stable throughout Micro-expressions restrained and realistic Action nodes few and clear Clay pottery, tea, silk fabric, and hair physics natural Foreground, midground, background maintain real parallax and synchronized spatial ambient sound No subtitles generated Seedance 2.0 Mini Execution Focus For Seedance 2.0 Mini, emphasize: Multi-reference character identity consistency Clear multi-character visual hierarchy Limited but dramatically meaningful actions Stable camera continuity Lighting continuity Core clay cup prop continuity Precise audio-visual sync of dialogue, clay cup hitting table sound, pouring tea sound, fabric friction sound, sword sheath subtle sound, and environmental sound Negative blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

FORMAT: 15s / 720P / 16:9. REFERENCES: Image1 is the storyboard and sequential visual guide. SCENE: One career woman races through the final hours of Friday in a modern city office, finishes her last task, and steps into an inviting golden evening. STYLE: contemporary live-action cinematic realism, brisk pacing, cool blue-gray office shifting into amber sunset and warm city lights. LENS / LIGHT / GRADE: 35mm full-frame with 85mm close-ups; cool overhead office light shifting to golden-hour backlight from screen-right; subtle film grain. STATIC LOCKS: same adult woman, face, tailored workwear, hair and accessories throughout; coherent office geography, screen direction and light progression. DYNAMIC MOTION: quick clock glance, purposeful typing, notifications, brisk lateral tracking, decisive laptop close, forward stride through glass doors, gentle city drift, settle into stillness. TIMELINE: 0-1.5s tight clock and anticipatory eyes; 1.5-3.2s wide office typing as colleagues wind down; 3.2-5s notifications then controlled exhale; 5-7s tracking as she finishes a call and gathers her coat; 7-8.8s final email sent, laptop shuts, relief; 8.8-10.8s she exits into golden evening; 10.8-13s city walk opens into warm weekend atmosphere; 13-15s she smiles, phone goes into her bag, holds a calm liberated final frame. AUDIO / VOICE: ticking clock and soft keyboard taps build over light rhythmic instrumental music; laptop click, office ambience recedes into evening street sounds; music opens into warm buoyant weekend energy. No dialogue or voiceover. RULES: one continuous cinematic video, not a storyboard slideshow; no panel borders, captions, masthead, arrows, overlays or readable screen text; no extra featured characters; preserve natural movement and identity. NEGATIVE: no identity drift, frantic unreadable cuts, garbled text, split-screen or frozen montage.

Created a 15-second cinematic photorealistic video of a peaceful alpine countryside during golden morning light, with majestic snow-covered mountains rising in the background and a cozy wooden farmhouse surrounded by rustic fences and open fields. A beautiful young woman with long dark hair, wearing a warm cream knitted sweater and natural winter outfit, slowly walks toward a calm brown horse standing near the wooden stable. She gently approaches the horse, smiles softly, and lovingly strokes its head while the horse remains peaceful and relaxed. The camera captures intimate close-up shots of her hand touching the horse and the horse’s expressive face, followed by smooth medium shots showing their connection. Warm sunlight shines through the mountain peaks, creating soft cinematic highlights and natural lens flare. Light morning mist drifts around the distant cabins and mountains while subtle smoke rises from a farmhouse chimney. The camera slowly tracks beside the woman as she walks back toward the cozy wooden house, keeping her appearance and outfit consistent throughout. Realistic horse movement, natural body motion, detailed skin and hair texture, authentic countryside atmosphere, soft depth of field, cinematic color grading, 35mm lens, gentle handheld movement, ultra-realistic 8K quality, peaceful emotional storytelling, no text, no logos, no watermark.

KAZEMIRU: THE JADE-WIND BLADE: ONE-TAKE CASTLE ASSAULT Duration: 30 seconds | Aspect Ratio: 16:9 | No music ONE-TAKE LOCK: This is ONE SINGLE UNBROKEN CONTINUOUS SHOT lasting the full 30 seconds. ZERO cuts. ZERO dissolves. ZERO fades. ZERO match-cuts. ZERO time jumps. ZERO scene resets. The camera never leaves the action and every location change happens physically inside the shot: the camera passes through torn doors, over railings and up the roof with Kazemiru. Time runs in real time. STYLE: Ultra-photorealistic live-action Japanese dark-action cinema with restrained subtle VFX. Impossible anime-inspired dual-sword choreography performed by real human bodies. Large-format cinema look, natural daylight, muted earthy color palette, soft realistic shadows, no oversaturated colors. @Image1 is KAZEMIRU. Preserve her exact face, silver-white ponytail, torn ivory kimono, charcoal split hakama, wind-swirl forearm tattoo and gold hoop earrings in every frame. @Image2 shows the five elite guards. @Image3 shows Captain Tetsugan. POSITIVE LOCKS (true for all 30 seconds): - Exactly ONE Kazemiru with exactly TWO real steel katanas, one in each hand, both always visible and independently controlled. - Her face always matches @Image1. - Every enemy comes from @Image2 or @Image3 and stays visually consistent. - Her body physically crosses every distance, with no teleportation. - It is always daytime with bright natural light. PERSONALITY: Cold, calm, battle-hungry. Minimal expression, steady breathing, focused eyes. Her hunger shows through relentless speed and escalating ferocity, never through grinning or shouting. JADE-WIND EFFECT: Every fast movement leaves a thin, soft jade-green wind trace that follows her exact physical path and fades almost instantly: sword arcs leave fine blade trails, spins bend the air, footsteps kick tiny wakes, supersonic bursts add a brief compressed-air ripple. Always thin, subtle and realistic. No aura, no smoke, no glowing body, no effects moving on their own. CAMERA (one continuous handheld-style pursuit): Constant dutch angle of 25–35°. Wide field of view around 75° in the interior and courtyard, tightening to about 50° for the rooftop duel. Kazemiru moves first and the camera follows 0.1–0.3 seconds late: whip-pan, overshoot, correct, reacquire at the moment of contact. The camera flows through rear over-the-shoulder, low-angle pursuit, side tracking, ground-level chase and front three-quarter retreat, always in one connected movement. Never static, never perfectly smooth. ══ 0:00–0:10: THE GRAND AUDIENCE HALL ══ Setting: bright daylight through large shoji panels, gold folding screens, tall dark timber pillars, tatami sections, raised platform, armor displays, low lacquer tables, silk curtains. 0:00–0:03: Rear over-the-shoulder, five guards closing in. Her fingers tighten on both hilts. BURST: a thin jade streak snaps across the hall and the silk curtains whip. The camera loses her, whip-pans, and finds her inside Guard 1's reach. Left blade parries, right blade slashes diagonally, a pivot, a reverse cut. He drops. 0:03–0:06: Guards 2 and 3 converge. She ducks under a swing, plants a foot on a pillar and pushes off, dust bursting from the wood. Mid-air her left sword deflects Guard 2 and her right sword cuts down. She lands on the edge of a lacquer table, which slides back, and rebounds straight toward Guard 3. 0:06–0:10: Aerial right slash, left reverse slash, dual cross-slash with two separate jade trails. She lands low and bursts across the floor. Guard 4's spear thrusts: she runs two steps up a wall, flips off, and cuts him down through a folding screen. Guard 5 charges: she catches his blade with one sword, vaults the railing above him, and finishes with a cross-slash as she lands behind him. ══ 0:10–0:20: THE PALACE COURTYARD ══ Transition inside the same shot: she does not pose. Both swords still in hand, she drives straight through the paper doors in one burst. The torn paper flutters past the lens as the camera follows her through the doorway onto the wooden veranda and out into a stone courtyard with lanterns, a koi pond, a red lacquer arched bridge and pine trees. Eight new guards: swordsmen below and archers on the roofs. 0:10–0:13: A volley of arrows. She cuts two out of the air with a spinning double slash and a third grazes her sleeve. She sprints along the veranda, pivoting off each post, a jade ripple following her feet. 0:13–0:16: She kicks off a stone lantern, which tips over, and leaps onto the bridge railing. Three swordsmen charge. She runs along the rail, slashes the first, flips over the second, and lands in the koi pond with a huge splash. In the water she parries two blades and cuts both guards. Droplets scatter across the lens. 0:16–0:20: She bursts out of the pond and sprints up a pine trunk in three steps. The camera tilts up with her. She launches onto the roof among the archers: left sword disarms, right sword strikes, roof tiles scatter. Two archers fall. ══ 0:20–0:30: THE ROOFTOP DUEL ══ Transition inside the same shot: she keeps climbing over the roof ridge and the camera rises with her, tightening to a 50° field of view. The tiled castle rooftop opens up with wind in her ponytail and the town far below. Captain Tetsugan (@Image3) waits with his naginata, calm and unflinching. 0:20–0:23: Tetsugan sweeps the naginata in a wide arc. Kazemiru ducks, slides down the sloping tiles, and crosses both swords to stop the blade. Sharp metal sound as his strength pushes her back a step. Her expression stays cold. 0:23–0:27: Fast exchange: his thrust, her left parry, her right slash that cuts his armor cord. He spins the pole and sweeps for her feet: she jumps, kicks off the shaft, and flips over him. Mid-air she cuts both swords across his back armor. Tiles crack under their feet and a faint jade wake curves around her path. He staggers, strikes back, and she narrowly dodges as the blade cuts a roof beam. 0:27–0:30: Supersonic burst along the ridge line, the jade streak slightly brighter but still thin. She slides under the naginata, and as she rises both swords slice through the shaft in a clean cross-cut. Tetsugan drops to one knee, defeated but alive. Kazemiru stands, both swords still in hand, and the last jade filaments disappear. She turns her cold eyes toward the courtyard far below, where dozens more guards pour in. The camera slowly pulls back and up to a wide shot of the whole castle. She lowers her body for the next burst. THE FIGHT CONTINUES. AUDIO: Sword resonance, compressed-air whooshes, metal clashes, footsteps on wood and tiles, arrows, water splashes, fluttering silk and paper, enemy shouts, wind over the rooftops. No dialogue, no music. HUMAN-FIRST LOCK: Kazemiru is always a real human: natural skin pores, real eyes, individual hair strands, believable anatomy and cloth physics. Only her choreography is anime-level impossible. NEGATIVE: cuts, edits, dissolves, fades, scene transitions, time jumps, multiple shots, single-sword fighting, missing or duplicate sword, duplicate Kazemiru, clones, teleportation, thick aura, smoke, glowing body, neon or oversaturated colors, detached VFX, random flips, decorative acrobatics, idle pose, static camera, perfectly smooth tracking, slow combat, floating, broken anatomy, CGI or plastic skin, anime rendering, blood, gore, subtitles, logos, watermark.

Shot 1 (0.0–1.2s): Character A, matching reference face/outfit, sits on a couch in a large suburban living room at night, phone in hand, warm lamp light against dark windows. Shot 2 (1.2–2.4s): Static wide shot of an empty hallway leading upstairs, dim nightlight, complete stillness. Shot 3 (2.4–3.4s): Close-up of her phone lighting up with an unknown number; she hesitates before answering. Shot 4 (3.4–4.4s): She answers. A distorted voice whispers, “Have you checked on the kids?” Her expression turns uneasy. Shot 5 (4.4–5.4s): She hangs up and nervously looks toward the dark staircase as the house creaks above. Shot 6 (5.4–6.6s): Wide static staircase shot; she slowly rises from the couch and heads upstairs. Shot 7 (6.6–7.8s): She cautiously climbs the stairs, gripping her phone tightly, floorboards creaking. Shot 8 (7.8–9.0s): Long upstairs hallway; she slowly walks through, checking each door. Shot 9 (9.0–10.0s): Close-up of her opening a child's bedroom door; two children sleep peacefully under a soft nightlight. Shot 10 (10.0–11.2s): She exhales in relief, gently closes the door, and turns back toward the stairs. Shot 11 (11.2–12.4s): Her phone rings again. She freezes mid-hallway. Shot 12 (12.4–13.6s): Close-up of the same unknown number. She answers hesitantly. Shot 13 (13.6–14.8s): The distorted voice repeats, “Have you checked on the kids?” She looks back toward their room. Shot 14 (14.8–16.0s): She demands to know who's calling, her voice trembling as the hallway feels darker and larger. Shot 15 (16.0–17.2s): The voice says, “I'm calling from inside the house.” The line immediately goes dead. Shot 16 (17.2–18.2s): Close-up of her terrified face as realization hits and her phone slips in her trembling hand. Shot 17 (18.2–19.2s): Wide hallway shot; a floorboard suddenly creaks from an unchecked room behind her. Shot 18 (19.2–20.2s): She turns slowly. A closet door at the hallway's end hangs slightly open. Shot 19 (20.2–21.2s): She backs toward the children's room, pulling out her phone to call for help. Shot 20 (21.2–22.2s): Close-up of the phone: no signal. Panic rises. Shot 21 (22.2–23.0s): The closet door slowly creaks farther open in the static hallway shot. Nothing visible inside. Shot 22 (23.0–23.8s): She grabs the children's door handle and looks back down the hallway. Shot 23 (23.8–24.6s): A violent shadowy figure suddenly lunges from the closet, breaking the stillness. Shot 24 (24.6–25.4s): She screams, throws open the children's door, and slams it shut as footsteps rush toward her. Shot 25 (25.4–26.4s): Close-up: her back against the door, breathing heavily as the handle violently rattles. Shot 26 (26.4–27.6s): Wide shot of the children waking terrified; she shields them as the door violently shudders. Shot 27 (27.6–30.0s): Final shot holds on the straining door and her terrified face turned toward camera, cinematic home-invasion horror, unresolved

15 seconds, 16:9 aspect ratio, realistic live-action texture, modern Chinese urban background. The first half features natural intimate dialogue between a couple; the second half hard cuts to a Western-style wedding in a future hotel. The camera slowly pulls back to gradually reveal male guests with different colored hair, forming an absurd and awkward comedy twist. Character performances are restrained; environment, skin, fabric, and lighting are realistic and natural. [Characters and Continuity] The female lead is a young adult Chinese girl @image (31). In the future wedding, the bride must be the same girl, maintaining facial features and contours, only changing hairstyle, makeup, and clothing. The male lead is a young adult Chinese man, starting with normal black short hair and daily casual clothes. In the future wedding, his facial features, face shape, body type, and hairstyle contour remain consistent, but he wears a well-fitted suit and dyes his hair distinctly green, fulfilling the girl's request from the opening. He must not look like a different person due to scene/hair changes. The groom is another adult Chinese man, slightly chubby, with black hair, clearly different appearance from the male lead, wearing formal groom attire. There are multiple adult male guests at the wedding site, dyed red, blue, purple, yellow, orange, and one other green-haired man. Their appearances, heights, builds, hairstyles, and suits are all distinct. Hair dye retains real hair strands, roots, and luster, looking like natural dyed hair rather than wigs or glowing colors. [0–7s: Daily Couple Dialogue] Ordinary city park or residential area downstairs, evening, soft natural light, slight ambient life sounds in the background. The girl and boy sit side by side on a bench. Medium close-up shot, clearly recognizable faces. The girl turns to look at the boy, holding his hand, speaking affectionately, seriously, with a touch of coquettishness, as if casually mentioning something romantic. The boy looks at her deeply. The girl speaks completely and clearly: "Baby, if you're not the one marrying me in the future, you must dye your hair green to come to my wedding, so I can spot you at a glance." Spoken at a natural, slightly fast, coherent daily pace, not deliberately dragged out, no swallowed words, no mechanical acceleration. While the girl speaks, the boy listens, showing a faint smile moved yet puzzled, adding no response. Maintain continuous performance, clearly establishing the male lead's appearance. The girl does not smirk early, wink at the camera, or foreshadow the twist. [7–9s: Hard Cut to Future Wedding, See Same Face Then Green Hair] Immediately after the girl says "you", hard cut to the hotel wedding scene. Ambient sound switches synchronously from outdoor life sounds to banquet hall applause and blurred voices. Cut to a frontal close-up of the same male lead's face. Initial frame top edge cropped below the hairline, temporarily hiding hair, letting viewers recognize him as the previous boy. He sits in the wedding guest seats, wearing a suit, expression slightly reserved with complex anticipation, gaze towards the entrance aisle. The camera then slowly, steadily moves backward, gradually revealing his full head—he has dyed his hair green. The green is seen clearly by viewers for the first time. He was already green-haired when entering the wedding shot; no live color-change effect occurs. [9–12s: Bride and Groom Entrance, Other Colors Appear] Camera continues moving back, expanding from close-up to medium shot, adjusting horizontally to keep the green-haired male lead on one side and gradually reveal the central wedding aisle. The site is a real hotel banquet hall arranged for a Western wedding, with light-colored floral arrangements, white/beige chairs, warm ceiling lights, and carpeted entrance aisles. Lighting has clear sources; wedding dress retains fabric details, avoiding dreamy fairy-tale effects. In the background aisle, the opening girl enters in a wedding dress, arm-in-arm with the slightly chubby groom. The groom's appearance and build are clearly different from the green-haired male lead. The male lead originally watches the bride, forcing a faint smile. As the camera pulls back, a red-haired male guest and a blue-haired male guest enter the frame near him. He inadvertently glances at the red-haired man beside him, smile pausing slightly, then looks at the green-haired man on the other side, brow twitching, starting to feel something is wrong. [12–15s: Reveal More Colored-Hair Men, Male Lead Looks Around in Surprise] Camera continues moving back along the same trajectory, expanding to a wider frame containing the male lead, several rows of surrounding guests, and the wedding aisle. The wedding segment remains continuous, no further cuts. More male guests with different hair colors gradually enter the frame: purple, yellow, orange, and another red-haired man distinct from the male lead in appearance, build, and hairstyle. Including the male lead, about six to eight colored-hair men are scattered across adjacent rows, intermingled with ordinary black-haired guests. Not all guests have dyed hair, nor are they arranged in a neat rainbow line. They vary: some thin, some sturdy, some chubby; some buzz cuts, some short side parts, some curly. Suits are black, dark blue, gray, brown, with obvious differences in fit, ties, and shirt combinations, resembling independent real wedding guests. These people were seated in place from the start of the wedding shot, merely hidden by the initial tight framing, becoming visible as the camera pulled back; they cannot appear suddenly or change hair color abruptly. The male lead looks left, then right, finally turning slightly back to see another green-haired man. His expression shifts from confusion to surprise and embarrassment, lips parting slightly, realizing he might not be the only one who received such a promise. Other colored-hair men mostly continue watching the wedding; a few may briefly exchange glances with him, not collectively turning heads or reacting in sync. The ending simultaneously retains the male lead's surprised look-around, surrounding differently colored-hair male guests, and the bride/groom continuing to enter in the background. The screen ends naturally, without extra dialogue explaining the joke. [Cinematography, Performance, and Realistic Atmosphere] Opening uses natural daylight; wedding uses hotel warm indoor lighting. Skin tones are normal, retaining texture; suits have real wrinkles; wedding dress has weight; dyed hair has natural shading layers. The first half feels like real couples chatting casually; the second half feels like an awkward discovery happening at a real wedding. The male lead expresses emotions through eyes, micro-expressions, and looking around, avoiding cartoonish eye-widening, mouth-opening, or face-covering actions. The wedding pull-back uses actual camera movement, steady speed, with pre-arranged guest positions so different hair colors enter sequentially. Depth of field increases gradually after pull-back, ensuring relationships between male lead, colored-hair guests, and background newlyweds are discernible; do not blur surrounding people into color blocks throughout. Avoid retro DV quality, exaggerated shaking, fisheye, sudden zooms, high-speed orbits, slow motion, plastic skin, or heavy filters. [Sound] Opening retains girl's dialogue and slight outdoor life sounds. After hard cut, enter natural applause, fabric rustle, chair creaks, and blurred conversation of the hotel banquet hall. Dialogue accurately matches girl's lip movements; male lead does not speak for her or interrupt. No clear dialogue added in wedding segment. No narration, background music, canned laughter, twist alert sounds, or explanatory subtitles. [Core Constraints] Total length 15 seconds. The only hard cut occurs after the girl finishes her line, switching from daily couple scene to future wedding. Wedding part starts with male lead's facial close-up, continuously pulling back slowly. Information revelation order fixed: Same boy's face -> His green hair -> Same girl and different groom entering -> Surrounding gradual appearance of different colored-hair male guests -> Male lead discovers another green-haired man, looks around in surprise. Girl's line requests "dye hair green"; male lead indeed dyes hair green in future, consistent. Bride is same person as opening girl; green-haired male lead is same person as opening boy; groom is different person. Other guests have independent faces, no cloned faces, face swaps, abrupt hair color changes, or sudden appearances. No subtitles, date stamps, explanatory text, or watermarks.