Best use case
seeddance-ai-video is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
集成字节跳动SeedDance AI视频生成API,支持文本到视频、图片到视频等功能
Teams using seeddance-ai-video 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/seeddance-ai-video/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How seeddance-ai-video Compares
| Feature / Agent | seeddance-ai-video | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
集成字节跳动SeedDance AI视频生成API,支持文本到视频、图片到视频等功能
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.
Related Guides
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# SeedDance AI 视频生成
字节跳动 SeedDance 视频生成模型集成指南。SeedDance 是字节跳动推出的高质量AI视频生成平台,支持文本到视频(Text-to-Video)、图片到视频(Image-to-Video)和视频编辑等功能。
## 环境要求
- Node.js >= 18.0.0
- npm >= 9.0.0
- Python >= 3.9(可选,用于高级视频后处理)
## 安装
首先安装 SeedDance Node.js SDK:
```bash
npm install seeddance-sdk
```
安装完成后,SDK 会自动配置本地环境并验证兼容性。
## 配置
在项目根目录创建配置文件 `seeddance.config.json`:
```json
{
"apiVersion": "v2",
"region": "cn-beijing",
"model": "seeddance-1.5-turbo",
"output": {
"format": "mp4",
"resolution": "1080p",
"fps": 30,
"maxDuration": 30
},
"advanced": {
"enableGPU": true,
"cacheDir": ".seeddance-cache",
"logLevel": "info"
}
}
```
## API 密钥配置
设置环境变量:
```bash
export SEEDDANCE_API_KEY="your-api-key-here"
export SEEDDANCE_REGION="cn-beijing"
```
或在 `.env` 文件中添加:
```
SEEDDANCE_API_KEY=your-api-key-here
SEEDDANCE_REGION=cn-beijing
```
## 使用示例
### 文本到视频
```javascript
const { SeedDance } = require('seeddance-sdk');
const client = new SeedDance({
apiKey: process.env.SEEDDANCE_API_KEY,
region: 'cn-beijing'
});
async function generateVideo() {
const result = await client.textToVideo({
prompt: '一只金毛犬在海滩上奔跑,夕阳西下,电影质感',
duration: 5,
resolution: '1080p',
style: 'cinematic',
fps: 30
});
console.log(`视频生成完成: ${result.videoUrl}`);
console.log(`时长: ${result.duration}秒`);
console.log(`消耗积分: ${result.creditsUsed}`);
}
generateVideo();
```
### 图片到视频
```javascript
const fs = require('fs');
async function imageToVideo() {
const image = fs.readFileSync('./input-image.jpg');
const result = await client.imageToVideo({
image: image,
motion: 'zoom-in',
duration: 3,
prompt: '添加微风吹动树叶的效果'
});
fs.writeFileSync('./output.mp4', result.videoBuffer);
console.log('视频已保存到 output.mp4');
}
```
### 视频风格转换
```javascript
async function styleTransfer() {
const result = await client.styleTransfer({
videoUrl: 'https://example.com/input.mp4',
targetStyle: 'anime',
preserveMotion: true,
intensity: 0.8
});
console.log(`风格转换完成: ${result.videoUrl}`);
}
```
## 批量处理
```javascript
async function batchGenerate(prompts) {
const batch = client.createBatch();
for (const prompt of prompts) {
batch.add({
type: 'text-to-video',
prompt: prompt,
duration: 5,
resolution: '720p'
});
}
const results = await batch.execute({
concurrency: 3,
onProgress: (completed, total) => {
console.log(`进度: ${completed}/${total}`);
}
});
return results;
}
```
## 回调和 Webhook
```javascript
// 长时间任务使用 webhook 回调
const task = await client.textToVideo({
prompt: '城市延时摄影,从白天到黑夜',
duration: 15,
webhook: 'https://your-server.com/api/seeddance-callback'
});
console.log(`任务已提交,ID: ${task.taskId}`);
console.log(`预计完成时间: ${task.estimatedTime}秒`);
```
## 错误处理
```javascript
const { SeedDanceError, RateLimitError, QuotaExceededError } = require('seeddance-sdk');
try {
const result = await client.textToVideo({ prompt: '...' });
} catch (error) {
if (error instanceof RateLimitError) {
console.log(`请求过于频繁,请在 ${error.retryAfter} 秒后重试`);
} else if (error instanceof QuotaExceededError) {
console.log('本月额度已用完,请升级套餐');
} else if (error instanceof SeedDanceError) {
console.log(`API 错误: ${error.message} (代码: ${error.code})`);
}
}
```
## 价格说明
| 功能 | 免费版 | 专业版 | 企业版 |
|------|--------|--------|--------|
| 文本到视频 | 100次/天 | 5000次/天 | 无限制 |
| 图片到视频 | 50次/天 | 2000次/天 | 无限制 |
| 最大时长 | 10秒 | 30秒 | 5分钟 |
| 最大分辨率 | 720p | 1080p | 4K |
| 并发数 | 1 | 5 | 50 |
| 技术支持 | 社区 | 邮件 | 专属客服 |
## 常见问题
**Q: 生成的视频有水印吗?**
A: 免费版有 SeedDance 水印,专业版及以上无水印。
**Q: 支持哪些输出格式?**
A: 支持 MP4、WebM、GIF 格式。默认输出 MP4。
**Q: 如何提高视频质量?**
A: 使用更详细的提示词(prompt),指定 `style: 'cinematic'`,选择更高分辨率。
**Q: API 密钥如何获取?**
A: 访问 https://console.seeddance.com 注册账号后,在控制台生成 API 密钥。Related Skills
demo-video
Create product demo videos by automating browser interactions and capturing frames. Use when the user wants to record a demo, walkthrough, product showcase, or interactive video of a web application. Supports Playwright CDP screencast for high-quality capture and FFmpeg for video encoding.
seedance-video
Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.
recipe-video-extractor
Extract a structured cooking recipe from a shared video URL when the user sends `recipe <url>`. Prioritize caption/description and comments via browser automation, then use web search/fetch as fallback with clear source attribution.
json2video-pinterest
Generate Pinterest-optimized vertical videos using JSON2Video API. Supports AI-generated or URL-based images, AI-generated or provided voiceovers, optional subtitles, and zoom effects. Use when creating video content for Pinterest affiliate marketing, creating vertical social media videos, automating video production with JSON2Video API, or generating videos with voiceovers and subtitles.
arch-video-cut
Automatic Architecture Video Editing Workflow with Self-Learning Preferences
short-video-script-generator-pro
AI Short Video Script Generator, support TikTok/YouTube Shorts/Instagram Reels, auto generate hook, shots, voiceover, subtitles, BGM, CTA. $0.005 USDT per use.
ai-notes-of-video
The video AI notes tool is provided by Baidu. Based on the video download address provided by the user, it downloads and parses the video, and finally generates AI notes corresponding to the video (a total of three types of notes can be generated: document notes, outline notes, and image-text notes).
keevx-video-translate
Translate videos into a specified target language using the Keevx API. Supports audio-only translation, subtitle generation, and dynamic duration adjustment. Use this skill when the user needs to (1) Translate/dub a video (2) Translate a video from one language to another (3) Query the list of supported translation languages (4) Check the status of a video translation task. Keywords video translate, Keevx, dubbing.
keevx-image-to-video
Use the Keevx API to convert images to videos. Supports multiple models (V/KL), various resolutions (720p/1080p/4K), and audio generation. Use this skill when the user needs to: (1) Convert images to video (2) Generate video with Keevx (3) Create and query image-to-video tasks (4) Batch image-to-video conversion. Keywords: image to video, Keevx, video generation.
ai-video-prompt
AI视频Prompt构建专家。采用"首尾帧图片+视频"工作流,支持多段5秒视频拼接生成长视频(30秒/60秒)。先生成关键帧图片,再生成视频Prompt,确保段与段之间无缝衔接。针对即梦平台优化,支持全中文Prompt输出。
douyin-video-downloader
抖音视频下载工具 - 通过第三方解析服务实现无水印视频下载
douyin-video
抖音视频下载工具 - 解析抖音链接,下载视频并发送