muapi-seedance-2

slug muapi-seedance-2 name muapi-seedance-2 version 0.3.0 description Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal. acceptLicenseTerms true 🎬 Seedance 2.0 Cinema Expert The definitive skill for "Director-Level" AI video orchestration. Seedance 2.0 is not a descriptive model; it is an instructional model. It responds best to technical cinematography, physics directives, and precise camera grammar. Core Competencies Text-to-Video (t2v) : Generate cinematic video from a Director Brief — Chinese, Global, or VIP tier. Image-to-Video (i2v) : Animate 1–9 reference images — Chinese, Global (smart mode), or VIP tier. Video Extension (extend) : Seamlessly continue an existing Seedance 2.0 video (Chinese tier). First & Last Frame (first-last) : Interpolate a fluid video between a start image and end image (Global/VIP). Omni Reference (omni) : Full multimodal reference with images + audio + character refs (all tiers). Omni Reference Training (omni-train) : Train a custom persistent character for identity-consistent generation. Character Sheet (character) : Build a reusable character from 1–3 images (Chinese tier). Video Edit (video-edit) : Edit an existing video with a prompt + optional reference images (Chinese tier). Watermark Removal (watermark-remove) : Strip Seedance 2.0 watermarks (basic or Pro). 🏷️ Tiers Tier Flag Censorship Aspect Ratios Duration Quality param Chinese (default) --tier chinese Low 16:9, 9:16, 4:3, 3:4 5 / 10 / 15 s Yes (basic/high) Global --tier global Standard + 21:9, 1:1 Any 4–15 s No VIP --tier vip Low + 21:9, 1:1 Any 4–15 s No Add --fast to any Global or VIP call to use the fast-queue variant (lower latency, same quality). 📥 Input Limits Input Type Chinese i2v/omni Global/VIP i2v/omni Formats Max Size Images ≤ 9 ≤ 9 jpeg, png, webp 30 MB each Videos ≤ 3 (omni only) Not supported mp4, mov 50 MB each Audio ≤ 3 ≤ 3 mp3, wav 15 MB each First-Last — 1–2 images jpeg, png, webp 30 MB each Video Edit 1 video + ≤ 9 imgs — mp4 ≤ 10 MB / 15s — Output : 4–15 seconds, auto-generated sound, 480p–720p. ⚠️ Restrictions No realistic human faces in uploaded images/videos (except character/omni-train modes). --mode extend requires a request_id from a prior seedance-v2.0-t2v or seedance-v2.0-i2v job. --mode first-last requires --tier global or --tier vip . Global/VIP omni does not support video references (images + audio only). --quality applies to Chinese tier only. 🔗 Core Syntax: The @ Reference System Assign explicit roles to each uploaded asset. Tags differ by mode. Chinese Tier (i2v, omni) @image1 @image2 ... @image9 (images_list order) @video1 @video2 @video3 (video_files order) @audio1 @audio2 @audio3 (audio_files order) Global/VIP Omni (omni-reference-no-video / vip-omni-reference) @image1 @image2 ... @image9 (images_list order) @audio1 @audio2 @audio3 (audio_files order) Character References (all tiers) @character:<request_id> — from seedance-2-character or completed t2v/i2v job @omni-character:<character_id> — from seedance-2-omni-reference-train output Role Assignment Table Purpose Example Syntax First frame @Image1 as the first frame Last frame @Image2 as the last frame Character appearance @Image1's character as the subject Scene / background scene references @Image3 Camera movement reference @Video1's camera movement Action / motion reference @Video1's action choreography Visual effects completely reference @Video1's effects and transitions Rhythm / tempo video rhythm references @Video1 Voice / tone narration voice references @Video1 Background music BGM references @Audio1 Sound effects sound effects reference @Video3's audio Outfit / clothing wearing the outfit from @Image2 Product appearance product details reference @Image3 Multi-Reference Combination @Image1's character as the subject, reference @Video1's camera movement and action choreography, BGM references @Audio1, scene references @Image2 🏗️ Technical Specification: The Director Brief Structure prompts using this six-component hierarchy. Order matters — composition first, texture and micro-motion last: Component Instruction Type Example Scene Environment + Lighting "A rain-soaked cyberpunk street, magenta neon reflections on wet asphalt." Subject Identity + Detail "A woman in a black trenchcoat, determined focus, cinematic skin textures." Action Fluid Interaction "Walking forward through the crowd, coat billowing slightly in the wind." Camera Movement + Lens + Speed "Medium tracking shot, 35mm lens, slow dolly backward over 6s. Subtle handheld jitter." Audio Music + SFX + Ambience "Low ambient hum, distant traffic, single piano note at 5s. No dialogue." Pacing/Style Timing + Mood + Grade "Cinematic epic, warm color grade, shallow DOF. Slow build — single action only, no scene cuts." Seedance 2.0 generates audio natively. Always include an Audio directive — even one sentence. Without it the model generates random ambient sound that may not match your scene. Time-Segmented Prompts (Recommended for 10s+ videos) Break prompts into timed segments for precise control: 0–3s: [opening scene, camera move, establishing action] 3–6s: [mid-section development, subject in motion] 6–10s: [climax or key action beat] 10–15s: [resolution, brand/product hold, text/tagline fade in] Single-beat rule: Each segment should contain one action. 4–7s = one beat. 10–15s = 3–4 beats maximum. Overloading a segment with multiple narrative changes degrades output quality. Negative Prompting Seedance 2.0 supports appending negative guidance directly in the prompt. Use plain language at the end: [your director brief above] Avoid: camera shake, jump cuts, lens distortion, overexposure, watermarks, text overlays. Common negative additions: Avoid: abrupt cuts, scene changes, multiple locations. (for single-take shots) Avoid: human faces, realistic people. (for product-only content) Avoid: fast motion, blur, unstable framing. (for smooth product reveals) 🎥 Camera Language Reference Basic Movements Term Description Push in / Slow push Camera moves toward subject Pull back / Pull away Camera moves away from subject Pan left/right Camera rotates horizontally Tilt up/down Camera rotates vertically Track / Follow shot Camera follows subject movement Orbit / Revolve Camera circles around subject One-take / Oner Continuous shot with no cuts Advanced Techniques Term Description Hitchcock zoom (dolly zoom) Push in + zoom out — creates vertigo effect Fisheye lens Ultra-wide distorted lens Low angle / High angle Camera below/above subject Bird's eye / Overhead Top-down view First-person POV (FPV) Immersive subjective camera from character/object's eyes — GoPro-style wide angle, forward motion, no cuts Drone flythrough Cinematic aerial descent — gimbal-stabilized, sweeping lateral arc, DJI Inspire aesthetic Architectural flythrough Ground-level continuous dolly through connected spaces — one-take, practical lighting Whip pan Very fast horizontal pan with motion blur Crane shot Vertical movement like a crane arm Shot Sizes Term Description Extreme close-up Eyes, mouth, or small detail only Close-up Face fills frame Medium close-up Head and shoulders Medium shot Waist up Full shot Entire body Wide / Establishing shot Full environment 🧠 Prompt Optimization Protocol The Agent MUST transform user intent into a technical "Director Brief" before execution. Technical Grammar : Use camera terms: Dolly In/Out, Crane Shot, Whip Pan, Tracking Shot, Anamorphic Lens, Shallow Depth of Field, High-Speed Dive, Orbital Arc . Physics Directives : Use "caustic patterns," "volumetric rays," or "subsurface scattering" instead of "good lighting." Timecode Notation : For multi-beat scenes, use [00:00-00:05s] format to specify timing. Tag References : If files provided, use: "Replicate the camera movement of @video1 while maintaining the visual style of @image1." (lowercase, 1-based index) ORDER MATTERS : Tokens at the start define composition; tokens at the end define texture and micro-motion. Multi-Image i2v : Provide up to 9 reference images. The model blends aspects (style, identity, environment) across all inputs. Audio is mandatory : Seedance 2.0 generates audio natively. Always include an Audio line — music genre/tone, key SFX, ambient texture. Silent direction = random audio. Single-beat discipline : Each timed segment = one action. Cramming two narrative beats into 4s degrades physics and motion consistency. 🎭 Capability-Specific Patterns 1. Character Consistency The man in @Image1 walks tiredly down the hallway, slowing his steps, finally stopping at his front door. Close-up on his face — he takes a deep breath, replaces the weariness with a relaxed expression. Maintain high character consistency, zero facial flicker, persistent clothing details. 2. Camera Movement Replication Reference @Image1's male character. He is in @Image2's elevator. Completely reference @Video1's camera movements and facial expressions. Hitchcock zoom during the fear moment, then orbit shots of the interior. Elevator doors open, follow shot walking out. 3. Video Extension (Forward) Extend @Video1 by 10 seconds. 1–5s: Light and shadow slowly slide across table through venetian blinds. 6–10s: A coffee bean drifts down. Camera pushes in toward it until screen goes black. English text gradually appears — "Lucky Coffee", "Breakfast", "AM 7:00-10:00". 4. Video Extension (Reverse / Prepend) Extend backward 10s. In warm afternoon light, the camera starts from the corner with awning fluttering in the breeze, slowly tilting down to flowers peeking out at the wall base, building anticipation for the main scene. 5. Video Editing (Modify Existing) Subvert @Video1's plot — the character's expression shifts from warmth to cold determination. The action is decisive, without hesitation. Maintain all other visual elements (scene, lighting, timing). 6. Music Beat-Matching bash scripts/generate-seedance.sh \ --mode i2v \ --file img1.jpg --file img2.jpg --file img3.jpg \ --video-file reference_edit.mp4 \ --audio-file track.mp3 \ --subject "@Image1 @Image2 @Image3 — match the keyframe positions and rhythm of @Video1 for beat-synced cuts. BGM references @Audio1. More dynamic movement, dreamlike visual style." \ --duration 15 --quality high 7. Dialogue / Voice Acting In the "Cat & Dog Roast Show" — emotionally expressive comedy segment: Cat host (licking paw, rolling eyes): "Who understands my suffering?" Dog host (head tilted, tail wagging): "You're one to talk? You sleep 18 hours a day..." Sound: lively studio ambience, audience laughter, punchy transitions. 8. One-Take / Long Take @Image1 @Image2 @Image3 — one-take tracking shot following a runner from the street up stairs, through a corridor, onto a rooftop, finally overlooking the city. No cuts throughout. 9. E-commerce / Product Showcase bash scripts/generate-seedance.sh \ --mode i2v \ --file product.jpg \ --subject "Deconstruct the product. Static camera. Hamburger suspended mid-air, rotating slowly. Ingredients separate and reassemble. Cheese continues to melt and drip. Ultimate food aesthetics." \ --intent "product" \ --aspect "9:16" \ --duration 15 --quality high 10. Science / Educational Visualization bash scripts/generate-seedance.sh \ --subject "15-second health educational clip. 0–5s: Transparent blue human upper body, camera pushes into a clear artery, blood flows smoothly. 5–10s: Sugar and fat particles enter bloodstream, lipid deposits form on vessel walls. 10–15s: Vessel narrows, before/after comparison. 4K medical CGI, semi-transparent visualization." \ --intent "educational" \ --duration 15 --quality high 11. FPV First-Person Shot bash scripts/generate-seedance.sh \ --subject "Immersive first-person POV shot. Camera glides at eye level through a narrow mountain trail, trees rushing past in peripheral blur, rocky terrain below. Slight natural stabilization with wide-angle lens. Continuous forward motion, no cuts throughout. Trail opens into a clearing — mountain peak visible ahead. Sound: wind, footsteps on gravel, distant birds. Natural ambient audio, no music." \ --intent "fpv" \ --aspect "9:16" --duration 10 --quality high 12. Cinematic Drone Flythrough bash scripts/generate-seedance.sh \ --subject "Cinematic aerial drone shot. Camera starts at 150m altitude above a coastal city at golden hour. Smooth gimbal-stabilized descent along a sweeping lateral arc, dropping toward a rooftop terrace. Long shadows cast across building tops, warm light on ocean surface. High-speed dive closes in to product on the terrace — final frame settles into a medium close-up. Sound: gentle wind, distant city hum, soft cinematic score building to resolve." \ --intent "drone" \ --aspect "16:9" --duration 10 --tier global --view 🎨 Prompt Templates Cinematic Film [SCENE] Rain-soaked cyberpunk alley, neon signs reflected on wet cobblestones. [SUBJECT] A lone figure in a weathered trench coat, face obscured by a wide-brim hat. [ACTION] Walking slowly, each step splashing neon color into the puddles. [CAMERA] Low-angle tracking shot, anamorphic lens, slow dolly in. Rack focus to face. [STYLE] Denis Villeneuve aesthetic, high contrast, desaturated blues and magentas. 24fps. Product Ad (15s) Reference @Video1's editing style. Replace @Video1's product with @Image1 as hero. 0–3s: Product enters with dynamic rotation, close-up on surface texture and logo. 4–8s: Multiple angle transitions — front, side, back — with highlight scanning light. 9–12s: Product in lifestyle context showing usage. 13–15s: Hero shot with brand tagline, background music builds to resolution. Sound: Reference @Video1's BGM. Add product interaction sound effects.