What makes Seedance Video notable?

1.6K downloads. Trust evidence available

How should Seedance Video be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Seedance Video

使用字节跳动 Seedance 生成 AI 视频：文生视频、图生视频（首帧/首尾帧/参考图）、异步任务查询。支持 Seedance 2.0（多模态输入、视频续生、视频编辑）等多个模型。 Use when: (1) 用户说"生成视频"/"做个视频"/"AI视频"/"text to video", (2) 用户要求... Skill: Seedance Video Owner: lovensky1992-wk Summary: 使用字节跳动 Seedance 生成 AI 视频：文生视频、图生视频（首帧/首尾帧/参考图）、异步任务查询。支持 Seedance 2.0（多模态输入、视频续生、视频编辑）等多个模型。 Use when: (1) 用户说"生成视频"/"做个视频"/"AI视频"/"text to video", (2) 用户要求... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-05-06T06:29:11.655Z | user Weekly sync v1.0.2 | 2026-04-26T12:31:02.704Z | user Weekly sync v1.0.1 | 2026-04-19T04:03:01.106Z | user Daily sync v0.1.3 | 20

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.6k

Updated

Oct 10, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.6K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.3release · observed May 6, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dsprt4znvnqphy9hhy68va983nsqs:seedance-video-gen

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-lovensky1992-wk-seedance-video-gen/snapshot"

Documentation

CLAWHUB

144,342 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: seedance-video
description: >
  使用字节跳动 Seedance 生成 AI 视频：文生视频、图生视频（首帧/首尾帧/参考图）、
  异步任务查询。支持 Seedance 2.0（多模态输入、视频续生、视频编辑）等多个模型。
  Use when: (1) 用户说"生成视频"/"做个视频"/"AI视频"/"text to video",
  (2) 用户要求根据图片生成视频/动画/"图生视频"/"image to video",
  (3) 用户提到 Seedance/字节视频生成,
  (4) 用户说"帮我做段视频"/"生成一段动画"。
  NOT for: 从已有视频中抽帧/截图（用 video-frames）、
  视频剪辑/转码/格式转换（用 ffmpeg 直接操作）、实拍视频处理。
version: 1.0.0
category: file-generation
argument-hint: "[text prompt or task ID]"
---

# Seedance Video Generation

使用字节跳动 Seedance 模型通过火山引擎 Ark API 生成 AI 视频。

## Step 0: 前置检查

1. **API Key**：确认 `ARK_API_KEY` 环境变量已设置
   ```bash
   echo $ARK_API_KEY | head -c 8  # 只显示前 8 位确认存在
   ```
   未设置 → 提示用户在 [火山引擎控制台](https://console.volcengine.com/) 获取
2. **Python CLI 工具**：确认 `{baseDir}/seedance.py` 存在
   - 不存在 → 降级用 curl（见 `references/curl-api-reference.md`）

## Step 1: 需求分类

| 用户意图 | 模式 | 跳转 |
|----------|------|------|
| "帮我生成一段视频" / 纯文字描述 | **文生视频** | → Step 2，Mode text |
| "用这张图生成视频" / 给了一张图 | **图生视频（首帧）** | → Step 2，Mode image |
| 给了两张图（开头和结尾） | **首尾帧视频** | → Step 2，Mode first-last |
| "参考这几张图" / 给了多张参考图 | **参考图视频** | → Step 2，Mode ref |
| "查下之前那个视频任务" / 给了 task ID | **任务查询** | → Step 4 |

## Step 2: 确认参数

**必须在调 API 前跟用户确认以下内容：**

1. **Prompt**：向用户展示将使用的 prompt，确认后再提交
2. **模型选择**（根据场景推荐）：

| 场景 | 推荐模型 | 理由 |
|------|---------|------|
| 日常文/图生视频 | Seedance 1.5 Pro（默认） | 稳定，支持音频 |
| 需要最高质量 | Seedance 2.0 | 多模态，最强效果 |
| 快速预览/测试 | Seedance 2.0 Fast | 生成快，质量略低 |
| 预算有限 | 1.5 Pro + Draft mode | 先低成本预览 |
| 纯文生视频、低成本 | 1.0 Lite T2V | 最便宜 |
| 多参考图 | 1.0 Lite I2V | 支持 1-4 张参考图 |

3. **默认参数**（用户不指定则用默认值）：
   - 分辨率：720p | 比例：16:9（文生）/ adaptive（图生）| 时长：5秒 | 音频：开

## Step 3: 执行生成

所有模式统一用 Python CLI：

```bash
# 文生视频
python3 {baseDir}/seedance.py create \
  --prompt "描述文字" \
  --ratio 16:9 --duration 5 --resolution 720p \
  --wait --download ~/Desktop

# 图生视频（首帧）
python3 {baseDir}/seedance.py create \
  --prompt "动作描述" --image /path/to/photo.jpg \
  --wait --download ~/Desktop

# 首尾帧
python3 {baseDir}/seedance.py create \
  --prompt "过渡描述" --image first.jpg --last-frame last.jpg \
  --wait --download ~/Desktop

# 参考图（1-4张，Lite I2V）
python3 {baseDir}/seedance.py create \
  --prompt "[图1]的人物在跳舞" --ref-images ref1.jpg ref2.jpg \
  --model doubao-seedance-1-0-lite-i2v-250428 \
  --wait --download ~/Desktop

# Draft 模式（便宜预览）
python3 {baseDir}/seedance.py create \
  --prompt "描述" --draft true --wait --download ~/Desktop

# 从 Draft 生成正式版
python3 {baseDir}/seedance.py create \
  --draft-task-id <DRAFT_TASK_ID> --resolution 720p \
  --wait --download ~/Desktop
```

**`--wait --download` 会自动轮询等待 + 下载，无需手动轮询。**

### 超时保护
- `--wait` 默认超时 10 分钟
- 超时后展示 task ID 给用户，可后续用 `status` 查询
- 正常生成时间：文生 1-3 分钟，图生 2-5 分钟

## Step 4: 任务管理

```bash
# 查询状态
python3 {baseDir}/seedance.py status <TASK_ID>

# 等待并下载已有任务
python3 {baseDir}/seedance.py wait <TASK_ID> --download ~/Desktop

# 列出任务
python3 {baseDir}/seedance.py list --status succeeded

# 取消/删除
python3 {baseDir}/seedance.py delete <TASK_ID>
```

## Step 5: 验证与交付

1.

README.md

# Seedance Video

Generate AI videos using ByteDance Seedance models for OpenClaw.

## Features

- 🎬 **Text-to-Video**: Generate videos from text prompts
- 🖼️ **Image-to-Video**: Animate from first frame or first+last frame
- 🎵 **Audio Support**: Generate videos with audio (Seedance 1.5 Pro)
- 🎨 **Draft Mode**: Quick preview generation
- 📊 **Task Management**: Query status and retrieve generated videos

## Prerequisites

- OpenClaw agent environment
- Python 3.8+
- Volcengine Ark API key

## Installation

### Via ClawHub (Recommended)

```bash
clawhub install seedance-video
```

### Manual Installation

1. Clone to `~/.openclaw/skills/seedance-video`
2. Set your API key:
   ```bash
   export ARK_API_KEY="your-api-key-here"
   ```

## Usage

Talk to your OpenClaw agent:

```
生成一个视频：海边日落，浪花拍打礁石
Generate a video from this prompt: a cat playing piano
查询视频生成任务状态: task-id-here
```

## Supported Models

- **Seedance 1.5 Pro**: Text/image to video with audio
- **Seedance 1.0 Pro**: Text/image to video
- **Seedance 1.0 Pro Fast**: Faster generation
- **Seedance 1.0 Lite**: Budget-friendly text-to-video

## License

MIT License - see [LICENSE.txt](LICENSE.txt) file

_meta.json

{
  "ownerId": "kn7cy12yzara9p2s370vsanfe9824vnm",
  "slug": "seedance-video-gen",
  "version": "1.0.3",
  "publishedAt": 1778048951655
}

references/curl-api-reference.md

# Seedance curl API 参考

> 完整 curl 命令参考。日常使用推荐 Python CLI（`{baseDir}/seedance.py`），此文件仅供调试或 CLI 不可用时参考。

## Base URL

```
https://ark.cn-beijing.volces.com/api/v3
```

## 创建任务

### Mode A: 文生视频

```bash
TASK_RESULT=$(curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [{"type": "text", "text": "YOUR_PROMPT"}],
    "ratio": "16:9", "duration": 5, "resolution": "720p", "generate_audio": true
  }')
TASK_ID=$(echo "$TASK_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
```

### Mode B: 图生视频（首帧）

**URL 图片：**
```bash
curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
      {"type": "text", "text": "YOUR_PROMPT"},
      {"type": "image_url", "image_url": {"url": "IMAGE_URL"}, "role": "first_frame"}
    ],
    "ratio": "adaptive", "duration": 5, "resolution": "720p", "generate_audio": true
  }'
```

**本地图片（base64）：**
```bash
IMG_BASE64=$(base64 < /path/to/image.png | tr -d '\n')
IMG_DATA_URL="data:image/png;base64,${IMG_BASE64}"
# 用 IMG_DATA_URL 替换上面的 IMAGE_URL
```

### Mode C: 首尾帧

```bash
"content": [
  {"type": "text", "text": "YOUR_PROMPT"},
  {"type": "image_url", "image_url": {"url": "FIRST_URL"}, "role": "first_frame"},
  {"type": "image_url", "image_url": {"url": "LAST_URL"}, "role": "last_frame"}
]
```

### Mode D: 参考图（Lite I2V）

```bash
"content": [
  {"type": "text", "text": "[图1]的人物在跳舞"},
  {"type": "image_url", "image_url": {"url": "REF_URL"}, "role": "reference_image"}
]
# model 必须用 doubao-seedance-1-0-lite-i2v-250428
```

## 轮询任务状态

```bash
while true; do
  STATUS_RESULT=$(curl -s -X GET ".../tasks/${TASK_ID}" -H "Authorization: Bearer $ARK_API_KEY")
  STATUS=$(echo "$STATUS_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['status'])")
  [ "$STATUS" = "succeeded" ] && break
  [ "$STATUS" = "failed" ] || [ "$STATUS" = "expired" ] && break
  sleep 15
done
```

## 其他操作

```bash
# 查询任务
curl -s -X GET ".../tasks/${TASK_ID}" -H "Authorization: Bearer $ARK_API_KEY"

# 列表（分页）
curl -s -X GET ".../tasks?page_num=1&page_size=10" -H "Authorization: Bearer $ARK_API_KEY"

# 删除/取消
curl -s -X DELETE ".../tasks/${TASK_ID}" -H "Authorization: Bearer $ARK_API_KEY"
```

## Draft Mode（Seedance 1.5 Pro）

```bash
# 1. 创建草稿（便宜预览）
"draft": true, "resolution": "480p"

# 2. 从草稿生成正式视频
"content": [{"type": "draft_task", "draft_task": {"id": "DRAFT_TASK_ID"}}],
"resolution": "720p"
```

## 连续视频（用尾帧串接）

```bash
# 第一段设置 "return_last_frame": true
# 完成后获取 last_frame_url，作为下一段的 first_frame
```

CHANGELOG.md

# 更新日志

## v1.1.0 (2026-02-12)

### 新增功能

- **飞书视频发送指南**：新增 `how_to_send_video_via_feishu_app.md` 文档，详细说明如何在 OpenClaw 中将生成的视频通过飞书 App 发送到聊天中。
  - 完整的操作步骤：生成视频 → 本地保存 → message 工具发送 → 飞书 API 上传 → 飞书分发
  - 包含 message 工具调用示例
  - 飞书 Open API 调用细节（上传凭证、CDN 上传、消息发送）
  - 权限认证说明（ARK_API_KEY、飞书 app_access_token）
  - 关键技术细节（文件大小限制、支持格式、超时处理、速率限制）

## v1.0.0

- 初始版本
- 支持 Seedance 1.5 Pro、1.0 Pro、1.0 Pro Fast、1.0 Lite 模型
- 文本生成视频、图片生成视频（首帧、首尾帧、参考图）
- Python CLI 工具 (`seedance.py`)
- 完整的 curl 命令示例

Github ReposUpdated 14h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.