seedance
Seedance harnesses Volcengine's video synthesis models to create dynamic videos from text descriptions, reference images, or audio input. The skill supports multiple generation modes including text-to-video, image-to-video with first-frame or first-and-last-frame guidance, multi-image reference blending, and audio-synchronized video creation on select models. Configure your API key via environment variables and use command-line parameters to control duration, aspect ratio, model selection, and polling behavior.
Seedance generates AI videos from text prompts, images, or audio using Volcengine's video synthesis models.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
Seedance generates AI videos from text prompts, images, or audio using Volcengine's video synthesis models. Seedance harnesses Volcengine's video synthesis models to create dynamic videos from text descriptions, reference images, or audio input. The skill supports multiple generation modes including text-to-video, image-to-video with first-frame or first-and-last-frame guidance, multi-image reference blending, and audio-synchronized video creation on select models. Configure your API key via environment variables and use command-line parameters to control duration, aspect ratio, model selection, and polling behavior.
Use it when
- Seedance enables video generation through multiple modes: provide a text prompt for text-to-video synthesis.
- Yes, Seedance converts static images into animated videos through its image-to-video mode.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
netease-youdao/LobsterAI/seedance · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can Seedance do with AI video generation?
Seedance harnesses Volcengine's video synthesis models to generate videos from text descriptions, reference images, or audio input. The skill supports text-to-video creation, image-to-video conversion with frame guidance, multi-image blending, and audio-synchronized video generation on select models. You control duration, aspect ratio, and model selection via command-line parameters.
How do I generate videos with AI using Seedance?
Seedance enables video generation through multiple modes: provide a text prompt for text-to-video synthesis, supply reference images for image-to-video conversion, or use audio input for synchronized video creation. Configure your Volcengine API key via environment variables, then use command-line parameters to specify duration, aspect ratio, and your preferred model before initiating generation.
Does Seedance support image-to-video conversion?
Yes, Seedance converts static images into animated videos through its image-to-video mode. You can provide a first frame only or both first-and-last-frame guidance to direct the animation. Seedance also supports multi-image reference blending to influence the generated video's visual style and content based on multiple reference images.
Can Seedance create videos with audio synchronization?
Seedance supports audio-synchronized video generation on select Volcengine models. This capability enables you to create dynamic video content that aligns with audio input, making it ideal for producing short-form social media videos and other audio-driven content efficiently.
What is the Volcengine Seedance API and how do I access it?
Seedance provides access to Volcengine's Seedance API, a video synthesis service. Configure access by setting your Volcengine API key as an environment variable. Once configured, Seedance handles polling and model management, allowing you to focus on crafting your video generation requests through text prompts, images, or audio inputs.
Is Seedance free to use?
Seedance is released under the MIT license. Access to Volcengine's underlying video synthesis models requires a Volcengine account and API key; pricing and free tier availability depend on Volcengine's current service terms, which you should verify directly with Volcengine.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Seedance 视频生成
使用火山引擎 Seedance 模型生成高质量 AI 视频，支持文本生成视频（T2V）、图片生成视频（I2V）、音画同步等多种创作模式。
> ✨ Node.js 版本：此脚本使用 Node.js 实现，无需 Python 环境。通过入口脚本自动检测 Node.js 运行时（优先使用系统 node，回退到 LobsterAI 内置运行时），Windows 和 Mac 用户都可以开箱即用。
配置
- Base URL:
https://ark.cn-beijing.volces.com/api/v3 - API Key: 从环境变量
ARK_API_KEY读取 - 认证方式:
Authorization: Bearer {API_KEY} - SDK: 兼容火山方舟 Python SDK
如何配置 API Key
方式一：通过环境变量配置（推荐）
在终端中设置环境变量：
# macOS/Linux
export ARK_API_KEY="你的API密钥"
# 或者添加到 ~/.zshrc 或 ~/.bashrc 以永久生效
echo 'export ARK_API_KEY="你的API密钥"' >> ~/.zshrc
source ~/.zshrc
# Windows PowerShell
$env:ARK_API_KEY="你的API密钥"
# 或者设置系统环境变量以永久生效
[System.Environment]::SetEnvironmentVariable('ARK_API_KEY', '你的API密钥', 'User')
方式二：通过 LobsterAI 启动时注入
LobsterAI 会自动读取系统环境变量，确保在启动 LobsterAI 前已设置 ARK_API_KEY。
如何获取 API Key： 1.
(truncated - see the full file via the links below)
File tree — 4 files
SKILLs/seedance/SKILL.md
SKILLs/seedance/scripts/generate-video.ps1
SKILLs/seedance/scripts/generate-video.sh
SKILLs/seedance/scripts/generate_video.js
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate videos from text descriptions or images using AI”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Create videos from text descriptions or images using ByteDance Seedance models via the Volcengine Ark API. Choose from multiple model variants optimized for speed, quality, or specific use cases like text-to-video or image-to-video generation. A Python CLI tool handles task creation, polling, and downloads automatically.
This skill leverages Seedance 1.0/1.5 models to generate videos from text descriptions, with optional guidance from images, videos, and audio. You can control output parameters like aspect ratio, duration, resolution, and frame count, and optionally generate accompanying audio. Supports multiple input modes including text-only, frame-guided, and multimodal reference workflows.
Generate Video turns text descriptions into short videos, optionally anchored by still images as opening or closing frames. It supports text-to-video generation, image-to-video animation, and frame-to-frame morphing, with configurable resolution, duration, aspect ratio, and reproducible output via seed control.
This skill harnesses Volcengine's Jimeng Video 3.0 Pro API to produce AI-generated videos from text descriptions or input images. Supports multiple generation modes ranging from 720P to 1080P Pro quality, with configurable duration (4–10 seconds), frame rates (24–30 fps), and image-to-video variants including camera movement effects. Requires Volcengine API credentials and handles async task submission with polling.
Seedream harnesses Volcengine's image generation model to create, edit, and fuse images across multiple modes. It supports text-to-image creation, single and multi-image editing, image series generation, and real-time web-search-enhanced creation via the Seedream 5.0 lite model. The skill runs on Node.js with no Python dependency, offering configurable output sizes from 1K to 4K resolution.
Stock Explorer pulls live market data and OHLCV information from Yahoo Finance, then computes technical indicators like RSI, MACD, Bollinger Bands, VWAP, and ATR directly on your machine. Supports US stocks, A-shares, HK stocks, crypto, and forex tickers with commands for quotes, fundamentals, trend charts, and comprehensive analysis reports.
More skills stock-announcements (MIT) · byted-web-search (Apache-2.0) · Seedance Video (NOASSERTION) · Seedance Video Gen (unlicensed)