# bytedance-seedance-2-0

Wraps ByteDance Seedance 2.0 (Fast) on EachLabs: prompt-to-clip or animate a still, with sound produced in the same pass.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 165 installs · ★ 48 repo stars
- Author: eachlabs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eachlabs/skills/tree/HEAD/skills/bytedance-seedance-2-0/SKILL.md
- Updated: 2026-10-07
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/bytedance-seedance-2-0

## What it does

The skill hands the agent a working recipe for EachLabs' Predictions API and two Seedance 2.0 Fast models. `bytedance-seedance-2-0-text-to-video-fast` builds a clip from a prompt; `bytedance-seedance-2-0-image-to-video-fast` animates a first frame and can aim it at a final one with `end_image_url`. Audio (effects, ambience, lip-synced speech) arrives in the same pass, so there is no separate TTS step.

Calls go in order. Check the model schema, POST to `https://api.eachlabs.ai/v1/prediction` with `version: "0.0.1"`, then poll `GET /v1/prediction/{id}` until `success`, or take a webhook and answer it with 2xx inside 30 seconds. The video URL comes back in `output`. Clips run 4–15 seconds at 480p or 720p; 720p is the default, length and aspect ratio sit at `auto`.

Auth is one header, `X-API-Key`, read from `EACHLABS_API_KEY`. Without it nothing runs. Source images need a public HTTPS URL, JPEG, PNG or WebP, up to 30 MB. Billing counts seconds of output: $0.2419 at 720p, $0.1129 at 480p. Audio does not change the bill.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill bytedance-seedance-2-0 -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/bytedance-seedance-2-0/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/bytedance-seedance-2-0/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill bytedance-seedance-2-0 -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/bytedance-seedance-2-0/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill bytedance-seedance-2-0 -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/bytedance-seedance-2-0/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills skills/bytedance-seedance-2-0
```

2. **Manually: put the files in place**
- File: `.github/skills/bytedance-seedance-2-0/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill bytedance-seedance-2-0 -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eachlabs/skills --path skills/bytedance-seedance-2-0
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/bytedance-seedance-2-0/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill bytedance-seedance-2-0 -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/eachlabs/skills/tree/HEAD/skills/bytedance-seedance-2-0/SKILL.md

## When to use it
- turn a written prompt into a 6-second 720p clip
- animate a still and pin where the shot ends
- get sound and lip-sync without a second TTS call
- drive generation from a webhook instead of polling
- estimate the cost of a clip before spending on it

## Example prompts
- Generate a 6-second 720p Seedance 2.0 clip: slow push-in on an astronaut at a canyon edge, wind ambience
- Animate `lion.jpg` — camera drifts from wide to close-up, add a narrator voice
- Run Seedance 2.0 image-to-video on `frame-start.jpg` and `frame-end.jpg`, 8 seconds

## Similar
- [seedance-video](https://affpapa.org/en/nevibecode/skills/seedance-video.md) — skill · 241 installs
- [muapi-seedance-2](https://affpapa.org/en/nevibecode/skills/muapi-seedance-2.md) — skill · 3100 installs
- [seedance-20](https://affpapa.org/en/nevibecode/skills/seedance-20.md) — skill · 519 installs
- [byted-seedance-video-generate](https://affpapa.org/en/nevibecode/skills/byted-seedance-video-generate.md) — skill · 188 installs
- [venice-video](https://affpapa.org/en/nevibecode/skills/veniceai-venice-video.md) — skill · ★ 176 repo stars
- [seedance](https://affpapa.org/en/nevibecode/skills/seedance.md) — skill · 14500 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 102 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
