Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Updated skill metadata to specify required environment variable logic: `MULEROUTER_API_KEY` and one of `MULEROUTER_BASE_URL` or `MULEROUTER_SITE` are now enforced with clearer definitions. - Added `env_one_of` and `install` fields to skill metadata for improved environment and dependency management. - Expanded the file whitelist in metadata to explicitly include `pyproject.toml`. - No changes to underlying functionality or APIs—documentation and metadata improvements only.
What This Skill Does
Generates images and videos through MuleRouter or MuleRun multimodal APIs. Supports text-to-image, text-to-video, image-to-video, and video editing operations including keyframe interpolation. Works with models like Wan2.6, Veo3, Midjourney, and Sora2.
Provides a single CLI interface to multiple state-of-the-art image and video generation models without managing separate API integrations for each.
When to use it
- Convert a product photo into a short animated video
- Generate concept art from a text description
- Animate a static illustration with a camera movement prompt
- Edit existing video footage using keyframe interpolation
- Batch-generate image variations from a single prompt
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate a video of a cat walking through a garden
- 1Check MULEROUTER_API_KEY and MULEROUTER_BASE_URL or MULEROUTER_SITE are set
- 2Run uv sync to install dependencies
- 3Run uv run python scripts/list_models.py to list available text-to-video models
- 4Run uv run python models/alibaba/wan2.6-t2v/generation.py --list-params to review options
- 5Run uv run python models/alibaba/wan2.6-t2v/generation.py --prompt "A cat walking through a garden"
API returns a URL to the generated video file
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.