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.
Why use this skill?
Generate professional-grade AI videos using ByteDance Seedance models. Supports text-to-video, image-to-video, and audio generation via OpenClaw.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jackycser/seedance-video-generationWhat This Skill Does
The seedance-video skill is a powerful interface for ByteDance’s advanced generative AI video models. It enables users to transform text, single images, or multi-frame sequences into high-quality video content directly from the command line. By leveraging the Volcengine Ark API, it supports multiple model variations, ranging from the flagship Seedance 1.5 Pro—which includes integrated audio synthesis—to cost-effective Lite versions for specialized image-to-video tasks. The skill streamlines the complex video generation workflow by handling API authentication, image base64 encoding, task polling, and automatic media downloads.
Installation
To begin, ensure you have the OpenClaw environment set up. Install the skill using the following command:
clawhub install openclaw/skills/skills/jackycser/seedance-video-generation
Once installed, you must configure your API credentials to communicate with the Volcengine backend. Open your environment configuration file and add your unique key:
export ARK_API_KEY="your-api-key-here"
The skill includes a robust Python CLI tool located at ~/.claude/skills/seedance-video/seedance.py, which is the recommended method for interaction as it manages retries and file processing natively.
Use Cases
This tool is ideal for content creators, developers, and designers needing rapid video prototyping. Common workflows include:
- Creative Storyboarding: Generating motion clips from static concept art.
- Social Media Content: Quickly creating dynamic visual backgrounds or short-form video snippets.
- Audio-Visual Production: Utilizing the 1.5 Pro model to generate video content synchronized with generated audio.
- Draft-to-Final Workflow: Using draft mode to iterate on visual compositions quickly before committing to a full-resolution, high-fidelity render.
Example Prompts
- "Use the seedance-video skill to generate a 10-second video of a cyberpunk city street with neon lights reflecting in puddles, using a 16:9 aspect ratio."
- "Take this image file at ./portrait.jpg and generate a video where the subject slowly turns their head toward the camera using the latest pro model."
- "Check the status of my previous video generation task with ID 'task_abc_123' and download the result if it is completed."
Tips & Limitations
- Model Selection: Always check the model capabilities table. If you require audio, ensure you use the 1.5 Pro model.
- Resource Management: Video generation can be compute-intensive. Use 'draft' mode for rapid iteration to save API quota.
- Input Requirements: When using image-to-video, ensure your source images are clear and well-lit for optimal consistency. The CLI tool will automatically convert local paths to the required base64 format.
- Versioning: Stay updated with the model IDs provided in the documentation, as ByteDance frequently releases improved versions.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-jackycser-seedance-video-generation": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api