seedance-20
seedance-20
Seedance 2.0 quad-modal AI filmmaking skill for text-to-video, image-to-video, video-to-video, and reference-to-video workflows.
Operating Principle
Direct the model. Do not micro-manage it. State the intended subject, action, feeling, camera behavior, lighting logic, reference roles, audio layer, and constraints. Use references to show what should be preserved; use text to say what should change.
Workflow Router
- Vague idea, concept only, or no clear scene: load
[skill:seedance-interview]. - Clear concept or reference assets supplied: load
[skill:seedance-prompt]. - Need short Chinese prompt or prompt compression: load
[skill:seedance-prompt-short]and the relevant vocabulary skill. - Image-to-video: load
[ref:i2v-guide]and describe only what the image cannot show. - Video/reference-to-video: load
[ref:reference-workflow]; map each reference to a role. - Camera, motion, lighting, character, style, VFX, or audio specialization: load only the matching sub-skill.
- Bad output: load
[skill:seedance-troubleshoot]; then load the specific failure-area skill. - Copyright, celebrity, brand, franchise, real-person, or likeness risk: load
[skill:seedance-copyright]before finalizing. - Blocked or degraded prompt: load
[skill:seedance-filter]and preserve intent while changing risky surface wording.
More from emily2040/seedance-2.0
seedance-vfx
Specify VFX physics contracts, energy effects, particle systems, destruction physics, and multi-layer VFX hierarchies for Seedance 2.0. Use when adding explosions, fire, water, lightning, magic effects, or any physically simulated element to a scene.
1seedance-motion
Control motion timing, beat density, action choreography, and sequential video extension chains for Seedance 2.0. Covers fight-scene physics, per-shot motion contracts, and multi-clip continuation techniques. Use when motion is too fast, too slow, or jittery, when choreographing action sequences, or when extending a video across multiple clips.
1seedance-audio
Design sound layers, specify dialogue lip-sync, and troubleshoot audio failures for Seedance 2.0 video generation. Covers @Audio1 reference input, multi-character constraints, known failure modes (silent output, desync, audio rewrite bug), and the boundary between Seedance 2.0 video generation and the separate Jimeng Digital Human tool. Use when adding audio to a Seedance prompt, fixing lip-sync errors, building multi-character dialogue scenes, or diagnosing why uploaded audio is ignored or replaced.
1seedance-recipes
Apply genre recipe templates to Seedance 2.0 — product ads, fight scenes, brand films, mood pieces, dialogue clips, one-take journeys, music videos, novel adaptations, architecture walkthroughs, and action transfers. Use when you need a ready-made prompt structure for a known genre or format.
1seedance-style
Control visual style, render-engine tokens, animation registers, period aesthetics, CGI material contracts, and style transfer via reference for Seedance 2.0. Use when setting a specific look — cinematic, anime, 3D, vintage, photorealistic — or when style is inconsistent across a shot chain.
1seedance-camera
Specify camera movement, shot framing, multi-shot sequences, and anti-drift locks for Seedance 2.0. Covers dolly, crane, orbit, push-in, one-take, and storyboard reference methods. Use when writing camera instructions, shooting a scene with a specific angle or movement, or fixing a wandering or locked camera.
1