AI Prompt Library

Rules: - Budget-scale theatrical anime quality, Japanese high-end figure-like matte 3DCG - Multi-shot - Fast cuts, many frames per second. Prioritize speed and impact - Professional-grade VFX - Change camera work every shot (no repetition of same movement) - No BGM; ambient sound/SFX only - No subtitles - All dialogue in Japanese - Pacing: Take time to show quiet acting, move quickly during showcase moments - Rain is fine, fast, real rain. Physically accurate depiction of splashes on the ground, light reflections on wet pavement, weight of wet hair and cloth - Night rain. Reflect warm colors from streetlights and neon on wet pavement; do not let the screen sink into gray - Keep the protagonist large in the frame; face and outfit clearly visible. Do not make them tiny in long shots - No text, logos, or numbers on screen @ Image1: Subject - Akane [Consistency] Maintain Akane's face, long hair transitioning from salmon orange to silver tips, red and white round hair ornaments, and red long coat with round buttons and white circular patterns throughout. Only one Akane. The red umbrella belongs to Akane. [Generation Goal] Rain Sound Orchestra (5 stages, 1 continuous video. From a rainy night bus stop to conducting rain across the city) [S1] Rainy night bus stop. The moment a raindrop hits the round button on @ Image1 Akane's coat, a piano note 'Poon' sounds, and a ring of light expands from the button. Camera: Extreme close-up of the button. Capture the instant the raindrop hits. [S2] Akane, sitting alone looking bored on a bench, suddenly looks up. Flicking the button again produces another sound. Akane smiles mischievously. Camera: Front view of bus stop, medium shot. [S3] Akane stands up and waves her closed red umbrella like a conductor's baton. Rain falling on tin roof becomes drums, gutters become xylophones, puddles become cymbals; each raindrop impact creates colorful droplets of light. Camera: Fast cuts zooming in sequentially on roof, gutter, puddle. [S4] Conducting grows larger, rain across the street glows with light, turning the gray night city into a shining colorful rain. Akane's long hair flows from orange to silver. Camera: Orbiting around Akane while rising. [S5] With the final wave, all raindrops stop in mid-air, floating like glowing musical notes. Akane lowers her umbrella and bows; the stopped rain falls all at once, creating applause-like rain sounds. Camera: Front view of bowing Akane, bust shot through glowing raindrops. Akane (shyly) says: {I kind of like rainy days}

Cinematic realistic texture, pure ancient Chinese Xianxia aesthetics. Core focus on mature conceptual conflict, restrained martial arts character performance, and veteran screenwriter-style dialogue driven by subtext, pauses, and reversals. Adopt Arri Alexa film camera texture, natural volumetric lighting, and delicate film grain. This core reversal revolves around the distinction between "loyalty" and "obedience": Everyone thought the senior sword immortal would demand unconditional loyalty from the junior sister The true reversal is she actively teaches the junior sister: True loyalty is not always listening to her, but having the courage to draw a sword and stop her when she goes wrong Strictly use @Image 1 and @Image 2 as character identity anchors. All background and location reference images uploaded this round jointly determine the same environment DNA. Before formal composition, silently reconstruct compatible real terrain, architectural language, material age, vegetation, water bodies, weather, mountain mist, reflections, main light direction, and atmospheric depth, forming a unique, complete, unified new location for this round. Background remains persistently alive but absolutely neutral narratively. Character Settings Character ID A Always the same @Image 1 Senior Sword Immortal Sister: 25-30 year old East Asian female Oval fair face Dark almond eyes Black long hair half-tied, fixed with white jade hairpin Tall and slender figure Wearing same set of white embroidered silk Hanfu Silver waist sash Jade pendant White cloth boots Holding single silver longsword Character ID B Always the same @Image 2 Junior Sword Immortal Sister: 20-25 year old East Asian female Round lively face Black hair braided Petite figure Wearing same set of green linen Hanfu Dark belt Wooden hairpin Black cloth shoes Holding single dark steel sword Other Secondary Characters The following characters exist only as secondary witnesses: An elderly master Two sect disciples Several bystanders A captured enemy commander Segment Structure 0-5s | Wide or Long Shot Clearly establish oath-taking site, character relationships, and spatial order. An elderly master presiding over formal oath-taking. He says solemnly: "Take oath — never disobey senior sister's command in this life." Junior sister prepares to kneel. The same white-robed sword immortal suddenly interrupts: "Delete this line." First half of this segment must quickly form a hook, making viewers mistakenly think she will propose stricter loyalty demands, but she instead negates this oath. 5-10s | Medium Shot or Cowboy Shot Maintain same two women, same costumes, same swords, and completely consistent geographical space. Master clearly confused asks: "Are you afraid she won't be loyal?" Senior sister calmly answers: "I am afraid she is too loyal." Entire venue instantly quiet. In shallow depth of field behind, the same enemy commander's original mocking smile also slightly disappears. Senior sister truly turns to junior sister, only asks: "If one day, I am wrong?" Junior sister freezes completely for the first time. Wind, water, mountain mist, sleeves, hair, and distant figures in background continue natural motion but completely do not participate in this choice. 10-15s | Close-up or Extreme Close-up The same junior sister does not continue kneeling, but slowly stands straight. She only draws the dark steel sword halfway, using the blade not fully sheathed to block horizontally in front of senior sister, forming a clear barrier without killing intent, saying: "Stop you first." Senior sister looks at her, asks: "If you can't stop me?" Full pause of half a beat. Junior sister finally truly raises eyes to meet hers, answers: "Then defeat you." Extreme close-up: The same senior sword immortal's originally serious and restrained expression finally reveals an extremely light, truly approving smile. She uses only two fingers to gently push away the blade blocking in front, saying: "This is more like my junior sister." In shallow depth of field behind: The same elderly master completely silent The same enemy commander slowly lowers gaze Junior sister ultimately does not kneel again Hard Requirements Strict total duration 15 seconds 16:9 landscape Strictly three continuous clear shots Native synchronized Mandarin dialogue Precise lip sync and eye-line relationships Character identity, hairstyle, costume, sword, supporting role positions, and geographical space stable throughout Character micro-expressions must be restrained and realistic Half-draw sword and horizontal blocking actions must be simple, clear, readable Natural physics for silk fabric, metal longsword, and hair Real parallax and synchronized spatial ambient sound maintained across foreground, midground, background No subtitles generated Seedance 2.0 Mini Execution Focus For Seedance 2.0 Mini, emphasize: Reference character consistency Visual hierarchy among multiple characters Few but precise action nodes Camera continuity Light and shadow continuity Sword state continuity Precise audio-visual synchronization of dialogue, sword drawing sound, scabbard friction, fabric sounds, and environmental sounds 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

Create a photorealistic cinematic nighttime lifestyle portrait. Preserve the same reference woman’s recognizable facial structure, face shape, eyes, eyebrows, nose, lips, skin tone, complexion, and natural facial proportions from the reference. Maintain her identity-like appearance consistently. Natural skin texture, subtle pores, realistic details, no facial distortion. She is relaxing comfortably in an elegant cozy bedroom, sitting against soft pillows on a neatly made bed while reading a hardcover book. She wears luxurious ivory satin pajamas with a relaxed low bun and a few natural strands framing her face, plus delicate gold hoop earrings. A fluffy cream-colored cat sleeps peacefully beside her. A warm bedside lamp casts soft golden light while cool blue moonlight enters through a large window, creating a beautiful warm-and-cool cinematic contrast. A cup of tea sits on the wooden nightstand beside the lamp. Soft beige bedding, elegant neutral interiors, realistic fabric textures, intimate peaceful nighttime atmosphere. CAMERA & STYLE: Photorealistic cinematic photography, 50mm lens, natural perspective, shallow depth of field, soft bokeh, realistic skin and hair, subtle filmic lighting, soft shadows, premium luxury lifestyle photography, highly detailed, natural colors, 8K realism. Negative Prompt identity drift, different face, altered facial structure, distorted face, asymmetrical eyes, unnatural eyes, deformed hands, extra fingers, missing fingers, fused fingers, malformed limbs, bad anatomy, plastic skin, overly smooth skin, excessive makeup, unnatural hair, duplicate person, duplicate cat, distorted cat, floating objects, warped book, unreadable text, CGI, cartoon, illustration, 3D render, oversaturated colors, harsh lighting, excessive blur, low resolution, noise, artifacts, watermark, logo, text, cropped face, unnatural pose

Realistic 3:4 photo, vertical portrait. Do not change the girl’s appearance. Natural hairstyle, hair lying freely on the shoulders. Medium-length square manicure in a milky color. The girl is wearing a dark brown cropped leather jacket, a brown plaid shirt, and black leggings. She is standing by a modern metal railing, leaning slightly back, right hand behind her head. Face in left profile, eyes closed, head slightly tilted upward. Background of dense autumn foliage: bright orange, yellow, red, and green leaves, a tree trunk with green ivy on the left. Soft natural daylight, no harsh shadows. Background sharp, no blur. Pinterest and lifestyle aesthetic, high detail and natural skin texture, shot in iPhone 17 Pro style. A lively spontaneous frame without posing, natural everyday look.

A highly detailed, photorealistic portrait of a beautiful South Asian woman with long, voluminous wavy brown hair. She is looking downward with a gentle, serene smile. With both hands, she is elegantly lifting a sheer, deep magenta dupatta (veil) over her head. The veil features delicate pearl embellishments along its border and scattered across the fabric. She is wearing a rich, dark burgundy velvet kurta decorated with ornate gold floral button closures down the center front. Her traditional jewelry includes large gold jhumka earrings and multiple stacked gold and pearl bangles on both wrists. She has soft, flawless glamour makeup with subtle eyeliner and peachy-pink lips. The background is a dreamy, soft-focus warm bokeh created by glowing festive fairy lights. Cinematic lighting, romantic atmosphere, hyper-realistic, 8k resolution, masterpiece. keep original face and hairstyle 100% reference

{ "style_prompt_template": { "subject": "{argument name="person" default="{{PERSON_NAME_OR_IMAGE}}"}", "aspect_ratio": "9:16 vertical", "canvas_size_guidance": "1080x1920 or equivalent 9:16", "shot_type": "medium portrait shot, zoomed out 50% from tight close-up, head-to-mid-torso visible, facing camera", "photography_style": "dramatic black and white studio portrait, editorial/fine-art photography", "composition": { "face_position": "subject's face centered both horizontally and vertically in the frame", "face_size_in_frame": "face occupies roughly 20-25% of frame height, not tightly cropped, ample negative space around subject", "eye_line": "eyes aligned at approximate vertical center of the canvas", "headroom": "generous margin above the hair, clear dark space visible above head", "crop": "visible down to mid-chest or waist, more of the suit and shoulders shown, wider view than a tight headshot", "surrounding_space": "large area of negative black space surrounding subject on left, right, top, and bottom", "alignment": "subject facing straight into camera, symmetrical framing, no off-center offset" }, "lighting": { "type": "single hard top-down spotlight (butterfly/Paramount lighting)", "quality": "harsh, narrow beam creating strong falloff", "key_highlight": "top of hair and forehead catch bright rim light", "shadow_behavior": "deep shadows under brow, cheekbones, and jawline; steep light-to-dark gradient across face", "background_light": "none; background falls into near-total darkness with faint gradient near top edge, spotlight cone visible in wider frame" }, "color_treatment": "monochrome black and white, high contrast, deep blacks, no gray midtone flatness", "background": "solid black or near-black, subtle vignette, no visible texture or props, large expanse of negative space", "wardrobe": "dark tailored suit jacket, white dress shirt, dark tie, formal/business attire, full torso visible", "expression_and_pose": "neutral to serious expression, calm and composed, minimal smile, direct gaze into lens, relaxed shoulders", "skin_and_texture_detail": "visible natural skin texture, pores, fine wrinkles, stubble if present, unretouched realism", "hair_detail": "individual strands visible and crisply lit, natural texture, not overly styled", "camera_and_lens": "shot as if on medium format camera, 50mm-85mm equivalent lens, greater working distance from subject, shallow depth of field, tack-sharp focus on eyes", "grain_and_finish": "fine film-like grain, high dynamic range, crisp micro-contrast, glossy editorial finish", "mood": "intense, powerful, cinematic, timeless" }, "negative_prompt": "color cast, flat lighting, soft focus, blown highlights on face, busy background, smiling broad" }

Face/Hair: Conform to the attached face photo. Hair State: Hair tips flowing in wind, emphasizing speed and messiness. Expression: Mouth half-open, expression mixing excitement and shyness. Top: Oversized vintage T-shirt (black base, slightly faded design) with bright colored nylon jacket (e.g., neon yellow or pink) draped over it, sleeves rolled up. Material reflecting city night lights. Bottoms: High-waist distressed denim shorts. Belt has accessories like chains/small pouches, active impression. Feet: Thick-soled sporty high-cut sneakers. Shoelaces slightly untied, reinforcing 'unstoppable'/'busy' atmosphere. Accessories: Specified small heart motif silver necklace and simple earrings. Plus smartwatch and randomly stacked colorful rubber bands/bracelets on arms (symbolizing many things to do). Pose: Dynamic pose twisting upper body forward while looking back. Right hand extended forward, as if trying to grab something or slice through city lights. Foreground/Background: Subject centered in focus. Background blurred with strong motion blur. Composition: Dynamic composition cutting diagonally across vertical 9:16 screen. Subject's gaze directed 'ahead' outside frame, stimulating viewer imagination. Location: Urban nightlife district. Neon signs, car tail lights, crowds becoming abstract light trails (bokeh). Wet pavement after rain reflecting lights. Lighting: High contrast night portrait. Colorful lights from neon/street lamps illuminate subject contour, dramatic side lighting on face. Photography: Commercial photo style portrait. Approx 35mm wide-angle lens, immersive feeling as if shot close to subject. Texture: Realistic depiction of T-shirt cotton, jacket nylon, denim roughness, skin texture. Style: Live-action/photorealistic, extremely shallow depth of field (approx f/1.8) creating dimensional commercial portrait where subject pops from background. Ratio: Vertical 9:16 / 1080x1920px (horizontal not allowed)

Ultra-realistic, hyper-detailed, 8K cinematic portrait of a 23 year old young stylish man, using the uploaded image for exact face and hairstyle. Outfit: Black t-shirt, blue sunglasses, wearing a bracelet, ring, chain, and a tattoo on the arm. Pose: One arm raised resting on a diagonal metallic pole, messy hair spreading over the sunglasses, candid and relaxed posture. Background: A softly blurred natural outdoor scene with trees, giving a cold daylight winter feel. Keep my face 100% same as in the reference image.

A high-angle, close-up studio shot of a single matte black mechanical keyboard keycap resting on a clean white surface. The keycap is a large rectangular modifier size (like a spacebar or shift key) with slightly rounded edges and a subtle texture. Engraved deeply into the top center of the keycap is the text "B.AI" in a sleek, modern sans-serif font. Four small silver screws are visible at the corners of the keycap's top face, adding an industrial detail. Soft, diffused lighting creates gentle shadows around the base of the keycap, emphasizing its three-dimensional form against the minimalist background.

Transform every visible person in the uploaded image into realistic LEGO-style minifigure toys while preserving each person’s recognizable identity, hairstyle, outfit, colors, accessories, relative height, pose, and relationship to each other. FORMAT LOCK — NON-NEGOTIABLE Vertical 3:4 aspect ratio. Full-body product composition. All figures must be fully visible from head to toe. Do not generate square, landscape, widescreen, close-up, cropped, or half-body compositions. PERSON COUNT LOCK — NON-NEGOTIABLE Detect all visible people in the uploaded image. If there is 1 person, create 1 LEGO-style minifigure. If there are 2 people, create 2 LEGO-style minifigures. If there are 3 or more people, create the same number of LEGO-style minifigures. Do not remove, merge, ignore, duplicate, or replace any person. Every person visible in the reference image must appear as their own separate LEGO-style minifigure. REFERENCE LOCK — NON-NEGOTIABLE Use the uploaded image as the only reference for all subjects. Preserve each person’s recognizable facial identity as much as possible within the simplified LEGO minifigure style. Maintain each person’s hairstyle and hair color, adapted into molded LEGO-style plastic hairpieces. Preserve each person’s facial expression, clothing colors, clothing design, visible patterns, accessories, and styling. The final figures must clearly represent the same people translated into LEGO-style toy form. Do not create generic minifigures. Do not redesign outfits or invent new accessories. CLOTHING DETAIL LOCK Recreate each person’s outfit as accurately as possible in LEGO minifigure form. Preserve the exact clothing color palette, layering, garment type, collar shape, neckline, sleeves, jacket shape, pants or skirt style, shoes, visible patterns, seams, buttons, zippers, belts, logos, jewelry, bags, glasses, hats, and accessories. Translate real clothing into printed LEGO torso and leg graphics with clean toy-style linework. Outerwear should appear as molded or printed LEGO-style clothing details. Shoes should be simplified into LEGO foot/leg prints while keeping the original color and style. Do not replace outfits with generic LEGO clothing. Do not simplify clothing so much that the original styling is lost. GROUP COMPOSITION Keep the same number of people from the uploaded image. Preserve the relationship between subjects. Preserve relative height differences. Preserve basic pose direction and body language. If the reference shows a couple, create a matching LEGO-style couple. If the reference shows a group, create the full group as separate minifigures. Arrange the figures naturally together in a clean product-style composition. LEGO MINIFIGURE STRUCTURE Use authentic LEGO-style minifigure proportions for every figure. Cylindrical heads. Simplified printed facial features. Block-shaped torsos. Printed clothing details on each torso. Sta

Use the uploaded image as the exact visual reference. Create a photorealistic luxury lifestyle portrait of the same woman sitting inside a premium modern car with deep burgundy/red leather interior. Preserve her exact facial identity, facial structure, hairstyle, skin tone, body proportions, and natural features. She is wearing an elegant dusty-rose/mauve embroidered corset-style dress with delicate floral detailing. She holds a fluffy cream-colored Pomeranian puppy gently in one arm, looking playfully toward the puppy while making a cute claw-like gesture with her other hand near her face. Natural playful expression with slightly open mouth and tongue visible. Long dark hair tied into a neat high ponytail with soft front strands framing her face. Elegant gold wristwatch, subtle jewelry, natural manicured nails. Capture the scene from inside the car at a slightly low, candid angle. Visible luxury burgundy leather seats, door panel, center console, window, ceiling handle and realistic car details. City architecture and soft evening lights visible through the window in the background, naturally blurred with shallow depth of field. Realistic flash photography mixed with ambient evening light, soft highlights on skin and hair, detailed fabric embroidery, realistic puppy fur, authentic skin texture and pores, physically accurate hands and fingers, natural body posture. High-end editorial photography, candid celebrity lifestyle aesthetic, ultra-photorealistic, realistic proportions, cinematic depth of field, 50mm lens, f/2.0, subtle flash, crisp subject detail, soft background bokeh, premium fashion magazine quality, natural color grading, realistic reflections, detailed textures, 4K, vertical 4:5 composition. Negative Prompt cartoon, anime, CGI, 3D render, plastic skin, over-smoothed face, altered identity, different person, face distortion, asymmetrical eyes, deformed hands, extra fingers, missing fingers, fused fingers, malformed arms, unnatural pose, bad anatomy, distorted legs, duplicated puppy, extra limbs, unrealistic fur, blurry face, low resolution, oversharpening, excessive makeup, artificial skin, warped car interior, floating objects, distorted clothing, messy embroidery, unnatural lighting, excessive HDR, oversaturated colors, text, logo, watermark, captions, frame, AI artifacts

A space crew continues their adventures in simulation holodeck they walk through a black-and-gold grid room and the floor beneath them warps step by step into a dusty Old West street — cool digital light melting into warm sunbaked wood and sandstone. grid room to old west, walking transformation, glowing circuitry lettering, saloon reveal, digital-to-analog shift, cinematic sci-fi western

Make this image into her wearing same outfit and a blue vail in her hair the riding a camel with music Tinariwen in the background delete the picture keep the part where she is riding stoand ,eliminate the dialogue why is riding backwards put Tiwhyye...

Redfish tailing in the calm water. A butterfly lands on a beautiful sea flower. Lighting strikes in the distance and a fog full of monsters rolls in.

Cinematic photorealistic drone shot of Mount Fuji at sunrise, Lake Kawaguchi reflecting the mountain, cherry blossom branches in the foreground, soft morning mist, slow forward dolly, 4K film look

Pitter-patter, pitter-patter… I'm the soft rain, gently tapping on the leaves like tiny silver bells in the breeze....

Convert this image to a 1:1 square aspect ratio. Keep the core subject (the glowing skull candle) prominent and well-framed with smart recomposition or cropping. Maintain the original artistic style, lighting, colors, details, quality, and composition...

Create a continuous 15-second cinematic exploration beginning from this exact image. No cuts. The alien does NOT walk, fly, or move like a human. 0–3 seconds: The camera slowly approaches the alien from behind. It remains almost motionless, overloo...

animate, intense eye contact as it moves forward, wings remain in full view even if they must wrap around and twirl the dragon, deep black ebony edges

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.

Create a 30-second, 1080p ultra-realistic cinematic action video featuring Elsa. Use the provided Elsa Master Character Set only as the strict identity reference for Elsa. Use the provided 20-panel Master Storyboard as the exact visual and chronological guide for the entire video. Do not copy any identity from the storyboard. The storyboard controls the action, shot progression, locations, framing and choreography, while the Master Character Set controls Elsa's face and physical identity. CHARACTER CONSISTENCY: Preserve Elsa's exact facial identity, facial proportions, hairstyle, skin tone, body proportions and recognizable appearance throughout the entire video. Keep her outfit consistent: black cropped top, fitted black pants, black leather jacket, black boots and a black shoulder bag. The same Elsa must appear in every shot. STYLE: Ultra-realistic live-action cinematic action sequence set inside a modern underground subway corridor. The environment should feel real and lived-in: tiled walls, fluorescent ceiling lights, concrete floors, distant commuters, signage, subway entrances and realistic urban details. Use cinematic handheld camera work combined with controlled action cinematography. Natural motion blur, realistic lighting, realistic shadows, physically accurate movement and believable human reactions. No fantasy powers, no supernatural effects, no exaggerated wire-fu and no impossible movements. ACTION: Keep the confrontation clearly fictional and choreographed for cinematic storytelling. Avoid graphic injury, blood or gore. SHOT 1 — 00:00–00:01 Elsa walks alone through the subway corridor carrying her shoulder bag. Use a medium-wide tracking shot from the front as commuters move naturally in the background. SHOT 2 — 00:01–00:02 Cut to a closer side angle as Elsa senses movement behind her. She slightly turns her head and looks over her shoulder. Her expression becomes alert but controlled. SHOT 3 — 00:02–00:03 Reveal several suspicious figures approaching from behind. Use a longer lens perspective that compresses the corridor and creates tension. SHOT 4 — 00:03–00:04 Close-up on Elsa's face. She notices the situation and remains calm and focused. Use shallow depth of field with the subway corridor softly blurred behind her. SHOT 5 — 00:04–00:05 Elsa turns into a narrower side passage. The camera follows quickly behind her as the atmosphere becomes more confined. SHOT 6 — 00:05–00:06 The figures block Elsa's path. Use a frontal medium shot showing Elsa surrounded by the group while maintaining clear spatial geography. SHOT 7 — 00:06–00:08 One attacker reaches toward Elsa's arm. Elsa reacts immediately, pulling her arm away and creating distance. Use a dynamic side angle with realistic body mechanics. SHOT 8 — 00:08–00:09 Elsa performs a quick defensive movement to escape the grab. Keep the choreography controlled and realistic. The camera moves with the action rather than using exaggerated effects. SHOT 9 — 00:09–00:11 A second attacker moves toward her. Elsa pivots out of the way and uses a controlled defensive counter, causing the attacker to lose balance and fall safely. Use a wider shot so the complete movement is readable. SHOT 10 — 00:11–00:12 Elsa creates space between herself and the attackers. Her shoulder bag swings naturally with the movement. Use a fast handheld camera adjustment. SHOT 11 — 00:12–00:14 An attacker moves toward Elsa again. Elsa uses the shoulder bag defensively to create distance and escape the immediate threat. Do not depict graphic impact. SHOT 12 — 00:14–00:15 Elsa performs a fast controlled kick that stops the attacker's advance. Use a low three-quarter angle emphasizing the movement while keeping realistic proportions. SHOT 13 — 00:15–00:17 Another attacker approaches. Elsa quickly changes direction, evades the incoming movement and performs a controlled defensive strike. Use a dynamic tracking camera. SHOT 14 — 00:17–00:18 Close action beat as Elsa completes the defensive sequence and creates separation. Keep the movement realistic and clearly choreographed. SHOT 15 — 00:18–00:20 Wide shot of the corridor. The attackers are now on the ground or backing away while Elsa remains standing and composed. No blood, wounds or graphic injury. SHOT 16 — 00:20–00:22 The tension disappears. Elsa calmly fixes her hair and adjusts her jacket. Use a close-up that contrasts her calm expression with the action that just occurred. SHOT 17 — 00:22–00:24 Elsa picks up and adjusts her shoulder bag. Use a medium close-up with natural handheld movement. SHOT 18 — 00:24–00:27 Elsa walks confidently down the subway corridor. The camera tracks backward in front of her. Commuters naturally move through the background. SHOT 19 — 00:27–00:29 Elsa approaches the subway exit stairs. Use a rear tracking shot as she walks toward the brighter exit. The lighting gradually becomes warmer and brighter. SHOT 20 — 00:29–00:30 Before leaving, Elsa briefly turns her head and looks back toward the camera with a calm, confident expression. Hold for a short cinematic beat. Cut to black. CAMERA LANGUAGE: Use a mixture of wide establishing shots, handheld tracking shots, close facial shots, side angles, low three-quarter angles and dynamic action framing. Every camera movement should be motivated by the action. Use short speed ramps only where they naturally emphasize an important movement. Do not overuse slow motion. Maintain clear spatial continuity so the viewer always understands where Elsa and the other characters are positioned. PHYSICS & CONTINUITY: Realistic human anatomy and movement. Realistic weight transfer. Natural hair and clothing movement. Natural shoulder-bag physics. Realistic footsteps and body momentum. No teleportation. No duplicated characters. No disappearing props. No impossible body deformation. AUDIO: Authentic subway ambience throughout. Footsteps, distant train sounds, station announcements, ventilation, commuters talking, clothing movement, bag movement and subtle action impacts. Music should be minimal and cinematic, building tension during the confrontation and becoming quieter as Elsa walks toward the exit. No dialogue. No subtitles. No text overlays. No logos. No watermark. FINAL LOOK: Premium ultra-realistic live-action action cinema with believable choreography, strong visual continuity and a grounded urban atmosphere. The sequence should feel tense, stylish and cinematic while remaining physically realistic and non-graphic.

15 seconds, realistic smartphone shooting texture, continuous handheld long shot, only brief slow motion during the aerial flip. Adult female character, wearing preset #2 yoga outfit (screenshot reference), strictly locking the color, style, cut, and fabric from the reference; white sneakers, hair tied back, character's face, body shape, and clothing consistent throughout. The scene is a cinematic fictional high-altitude cantilevered platform with Raffles City Chongqing and the surrounding Two Rivers cityscape as the background, not corresponding to real rooftop facility layouts. Two adjacent platforms extend outward from the building, separated by a fixed-width narrow gap, connected on the building side by a continuous walkway. The woman jumps laterally from one platform to the other, movement direction roughly parallel to the building facade; the landing area inside the opposite platform is clear and spacious. Opening establishes the takeoff platform, narrow gap, landing zone, and inner walkway simultaneously, structure remains unchanged afterwards. Afternoon natural sunlight, light haze over Chongqing city, soft reflection on distant river surface, ground shadows consistent with light source. 0-3s: Woman jogs forward on the takeoff platform, camera positioned behind and to the side near the building, following at slightly below chest height. Frame retains her full body, the narrow gap ahead, and the landing area opposite, distant city below the outer edge provides sense of height. Another black-clad adult male stays behind on the inner side of the takeoff platform holding a phone to film, not entering her path. Footsteps and wind sounds audible, occasional gust brushing microphone. 3-5s: She briefly accelerates, gaze fixed on opposite platform, action transitions naturally from running to jumping without posing pauses. Main cameraman moves forward along the inner connecting walkway, forming a side view, lens always sees solid platforms on both sides of the gap. She leaves ground moving toward opposite platform, begins one continuous front flip; entire motion towards landing area, no deviation outwards. 5-8s: Brief aerial phase after jump presented in slow motion. Full body in frame, center of gravity follows continuous arc rising then falling, rotation speed changes coherently, hair ends and fabric show natural inertia. She completes only one front flip, then body expands, feet approaching opposite platform. Lens still shoots from inner walkway, does not go outside building or pass under person; slow motion does not increase actual airtime nor show hovering. 8-11s: Returns to normal speed before shoe sole contacts platform. She lands inside opposite platform, body sinks clearly upon contact, then performs a compact roll due to remaining forward momentum, continuing inward. Contact sequence of sole, hands, and body with ground is clear, no clipping or frictionless sliding. Main cameraman continues along inner walkway, reaches side-front as she slows down, stops and rotates lens, fully retaining landing and rolling process. 11-15s: She stands up nearby, bends over with hands on knees, exhales sharply, shoulders rise and fall naturally. Expression shifts from intense focus to slight trance after tension release, then looks up at camera, breathing still unsettled. Cameraman steps closer slightly, frame tightens naturally from full body to waist-up, not sudden close-up. Black-clad male still filming from inner side of takeoff platform, position unchanged. Retain realistic skin, slight sweat, fabric stretch, and natural motion blur. Slight camera shake but key contact actions visible, do not use violent shaking to hide flips or landings. Prohibited: changing platform size, exaggerating distance, teleportation, repeated flips, mid-air acceleration, joint inversion, clothing change, floating landing. No music, subtitles, watermarks, or UI elements.

Rules: - Theatrical anime quality with a budget of 500 million yen, Japanese 2D cel animation style - Multi-shot - Fast cuts, high frame count. Prioritize speed and impact - Professional VFX quality - Change camera work every shot (no repetition of movement) - No BGM; ambient sound/sound effects present - No subtitles - All dialogue in Japanese - Pacing: Show quiet acting slowly with pauses, then move quickly during key moments - Draw rain with thin, fast lines; include splashes, puddle reflections, and wet clumped hair in the artwork - Night rain. Reflect streetlight and neon colors on wet pavement; ensure pale blue and white characters do not blend into gray background - Keep protagonists large in the frame; faces and costumes must be clearly visible. Do not make them tiny dots in long shots - No text, logos, or numbers on screen @ Image1: Subject - Sylvie @ Image2: Subject - Ayle [Consistency] Maintain consistent appearance throughout for Sylvie (silver bob hiding right eye, visible eye is yellow-green. Light blue demon horns and frilly head dress, small light blue bat wings and thin tail, pure white frilly dress with light blue ribbon, light blue and white striped socks) and Ayle (blue straight-cut bob, white round feather ornaments on both sides of head, small blue and white wings on shoulders, white dress with blue circular patterns, long trailing skirt of blue feathers). Do not mix up the two characters. Ayle is an angel above the clouds, Sylvie is a demon on the ground. [Generation Goal] Can meet only on rainy days (6 stages, one continuous video. Coming down along rain threads to meet until the rain stops) [S1] Above the clouds. Ayle from @ Image2 grabs falling rain threads from gaps in the clouds and slides down to the ground like a slide (face full of impatient joy). Camera: High-speed dolly following Ayle sliding down along the rain threads from directly above. [S2] On the roof of a town on a rainy night. Sylvie from @ Image1 waits looking up at the sky without an umbrella. Raindrops fall off her light blue horns and bat wings. Camera: Low angle from the roof showing Sylvie's profile as she looks up. [S3] Ayle lands softly on the roof, facing each other. Sylvie turns away shyly, but the tip of her tail wags happily. Camera: Two-shot from the side showing both. Pull back to show tail wagging. Ayle (cheerful voice) says: {I came} [S4] They sit side by side on the roof. Sylvie spreads her bat wings like an umbrella over Ayle. Lights of the rainy town blur and glow beneath them. Camera: Looking down at the rainy night cityscape from behind the two. [S5] Rain weakens, moonlight breaks through clouds. Ayle's body floats up gently drawn by the light, returning to the sky. Sylvie reaches out. Their fingertips separate. Camera: Close-up of separating fingertips, then pan up to Sylvie's face looking up. Ayle (crying smile) says: {Next rainy day} [S6] Alone on the dry roof, Sylvie holds one of Ayle's blue feathers in her palm. She squeezes it tight and smiles faintly while looking up at the sky. Camera: Close-up of the feather, then pull back to Sylvie looking up at the night sky.

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