seedance-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.

492 stars

Best use case

seedance-motion is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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.

Teams using seedance-motion should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/seedance-motion/SKILL.md --create-dirs "https://raw.githubusercontent.com/Emily2040/seedance-2.0/main/skills/seedance-motion/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/seedance-motion/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How seedance-motion Compares

Feature / Agentseedance-motionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# seedance-motion · Intent-First Choreography (v5.0)

This skill covers motion control, action choreography, and video extension for Seedance 2.0, prioritizing intent-driven descriptions over micro-management.

## The Guiding Philosophy

> For action, describe the **intent** and **consequence**, not the precise timestamps. Let the AI director handle the interpolation.

---

## 1. The Recommended Workflow: Intent + @Video Reference

This is the most reliable method for all action and fight scenes.

### Step 1: Find a Reference Video

Find a real-world video clip (e.g., from a movie, a stunt performance, or a video game) that captures the style of action you want. Upload it as `@Video1`.

### Step 2: Write an Intent-Based Prompt

Describe the high-level action in 1-3 sentences. Use degree adverbs and physics consequences. Then, explicitly tell the model to reference the uploaded video.

```
// Recommended Prompt Structure

Characters: A references @Image1; B references @Image2.

Choreography: The archer fires two arrows; the mage deflects them with a violet energy shield, then closes distance and blasts the archer into a tree with a shockwave. The archer draws a short blade and counter-attacks in close combat.

Reference: Reference the fight actions, character movements, and camera work from @Video1.

Style: Match the gritty, handheld style of @Video1.
```

**Why this works:** The `@Video1` reference provides the model with a rich, dense, and unambiguous understanding of the desired motion, physics, and camera language, which consistently outperforms any text-only description.

*For more on the @reference system, see [ref:reference-workflow].*

---

## 2. The Text-Only Workflow: Intent-Based Description

Use this when you don't have a reference video. The key is to keep it simple and enforce the **"One Action Per Shot"** rule.

```
// Text-Only Fight Scene Example

Characters: A references @Image1; B references @Image2.

Shot 1: A throws a right hook at B's jaw.
Shot 2: B ducks under the punch and sweeps A's legs.
Shot 3: A jumps, landing a spinning back kick to B's shoulder.
Shot 4: B staggers backward two steps, recovering his balance.

Camera: Medium shot, tracking the action. Slight handheld shake on impacts.
Physics: Dust puffs up from the ground on the leg sweep. A wet impact sound accompanies each hit.
```

### Key Principles for Text-Only Action

- **One Action Per Shot:** Do not chain multiple distinct actions (e.g., punch, block, kick) into a single sentence or shot. Break them down.
- **Degree Adverbs:** Use words like `violently`, `gracefully`, `slowly`, `frantically` to guide the model's interpretation of the action.
- **Physics Consequences:** Describe the results of the action. `Dust erupts`, `sparks fly`, `water sprays`, `the character staggers`.

---

## 3. Experimental Workflow: Micro-Choreography

> **⚠️ Warning:** This is an advanced, experimental technique that is unreliable for most users and often results in jitter, morphing, and failed generations. Use the Intent-Based workflows above for production.

Micro-choreography involves specifying actions with timestamps or in a grid format. While it offers the highest potential for control, it is also the most likely to fail.

### The Grid Method (25宫格)

| Beat | Camera | Action | SFX |
| :--- | :--- | :--- | :--- |
| 1 | Full shot, locked | B right punch → A face | drum "dong" + wind |
| 2 | Close-up | A crossguard block | impact "peng" |
| 3 | Medium | A wrist flip counter | ground crack |

### Timestamp Method

`0-1s: A throws a punch. 1-2s: B blocks. 2-3s: A follows with a kick.`

**When to use:** Only for short, highly technical sequences where the exact timing of each beat is critical and you are prepared to iterate many times to get a usable result.

---

## Diagnostic Tools

Use these concepts to diagnose failing motion prompts, not as prescriptive rules for building them.

- **Beat Density:** If your output is blurry or jittery, you may have too many actions packed into a short duration. The model can typically handle 1-2 distinct beats every 5 seconds. High-density prompts require the experimental micro-choreography format.
- **Timing Language:** Use relative terms (`eases in over 2 seconds`) or descriptive adverbs (`accelerates into a run`) instead of hard timestamps for smoother, more natural motion.

---

*Maintained by [Emily (@iamemily2050)](https://github.com/Emily2040)*

Related Skills

seedance-vocab-zh

492
from Emily2040/seedance-2.0

Look up 550+ Chinese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 22 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Mandarin, translating a production concept into Chinese Seedance vocabulary, or verifying term accuracy.

seedance-vocab-ru

492
from Emily2040/seedance-2.0

Look up 450+ Russian cinematic, photography, and production terms rooted in the Eisenstein/Tarkovsky Soviet montage tradition, with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Russian or translating production concepts into Russian Seedance vocabulary.

seedance-vocab-ko

492
from Emily2040/seedance-2.0

Look up 450+ Korean cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Korean or translating production concepts into Korean Seedance vocabulary.

seedance-vocab-ja

492
from Emily2040/seedance-2.0

Look up 450+ Japanese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Japanese or translating production concepts into Japanese Seedance vocabulary.

seedance-vocab-es

492
from Emily2040/seedance-2.0

Look up 450+ Spanish cinematic, photography, and production terms — Castilian and Latin American — with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Spanish or translating production concepts into Spanish Seedance vocabulary.

seedance-vfx

492
from Emily2040/seedance-2.0

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.

seedance-troubleshoot

492
from Emily2040/seedance-2.0

Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.

seedance-style

492
from Emily2040/seedance-2.0

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.

seedance-recipes

492
from Emily2040/seedance-2.0

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.

seedance-prompt

492
from Emily2040/seedance-2.0

Construct a production-ready prompt for Seedance 2.0 using the Director\'s Formula. Use when a user has a clear vision and needs to translate it into a genre-aware, intent-driven prompt. Covers genre routing, I2V gate, 30-100 word target, physics language, and anti-slop check.

seedance-prompt-short

492
from Emily2040/seedance-2.0

Build, validate, and compress Seedance 2.0 prompts to a hard 2000-character limit using the Five-Layer Stack, @Tag delegation, and the new Compression Engine. Use when constructing or debugging any T2V, I2V, V2V, or R2V prompt for the short-form workflow.

seedance-pipeline

492
from Emily2040/seedance-2.0

Integrate Seedance 2.0 with ComfyUI nodes and post-processing chains covering upscale, frame interpolation, color grade, composite, and metadata cleanup. Use when building automated video pipelines, connecting Seedance to external tools, or finishing and delivering a generated video clip.