Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added documentation for required environment variable (SILICONFLOW_API_KEY) and config file location (~/.openclaw/openclaw.json) - Expanded configuration section with example OpenClaw JSON format - Added a "Requirements" section detailing API key and config detection - Introduced a "Security Notes" section describing API key usage and data practices
What This Skill Does
Generates videos from text prompts or static images using the SiliconFlow API and Wan2.2 model. Supports both Text-to-Video and Image-to-Video modes at ¥2 per video. API key can be set via environment variable or OpenClaw config.
Wan2.2 (14B params) produces cinematic-quality output accessible via a simple CLI script without managing a local GPU.
When to use it
- Animating a product photo into a short clip
- Generating a cinematic scene from a script line
- Creating social media video content from text descriptions
- Turning concept art into motion video
- Prototyping video ads without a camera
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a video of a sunset over the ocean with waves crashing
- 1Reads SILICONFLOW_API_KEY from environment or ~/.openclaw/openclaw.json
- 2Calls SiliconFlow API with Wan-AI/Wan2.2-T2V-A14B model and the text prompt
- 3Polls the API until the video generation job completes
- 4Downloads the resulting video file
A cinematic video clip of a sunset ocean scene saved locally
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.