Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
An end-to-end workflow for generating AI videos with Seedance 2.0. Covers storyboard creation, reference image generation via Seedream 4.5, video task submission, and result polling. Works in both MCP tool mode and standalone Python script mode with a single API key.
Handles the full storyboard-to-video pipeline in one skill, including reference image generation and async polling, without coordinating separate tools for each step.
When to use it
- Generating a short sci-fi video clip from a text description
- Creating first-and-last-frame controlled video transitions
- Building a storyboard and reference images before video production
- Editing existing images for use as video reference frames
- Automating video generation polling until the final URL is ready
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Make a 15-second cinematic video of an astronaut walking on Mars
- 1Collect video parameters: duration 15s, aspect ratio 16:9, cinematic sci-fi style, no existing assets
- 2Submit text-to-image task to Seedream 4.5 to generate astronaut and Mars scene reference images
- 3Poll for image task completion every 10 seconds until URLs are returned
- 4Compose storyboard prompt referencing generated images and submit Seedance 2.0 video task
- 5Poll for video completion every 30 seconds and return the final video URL to the user
A hosted video URL for the completed AI-generated clip
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.