Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates images and videos through the MuleRouter and MuleRun multimodal APIs. Supports text-to-image, text-to-video, image-to-video, and video editing operations including keyframe interpolation. Works with models such as Wan2.6, Veo3, Sora2, and Midjourney.
Provides a single CLI interface to multiple frontier image and video generation models without managing separate API clients for each provider.
When to use it
- Generate a video clip from a text prompt using Wan2.6
- Animate a product photo into a short video
- Create concept art images from descriptive text
- Edit existing video with keyframe interpolation
- Transform a still image into a cinematic zoom shot
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a 5-second video of a cat walking through a garden
- 1Verify MULEROUTER_API_KEY and MULEROUTER_BASE_URL are set
- 2Run uv sync to install dependencies
- 3Run list_models.py to confirm wan2.6-t2v is available
- 4Check model parameters with generation.py --list-params
- 5Execute generation.py --prompt "A cat walking through a garden" and parse the output URL
A video file URL returned by the API, ready for download or further editing
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.