Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Upgrade to Gemini 3 Pro, Multi-Image Fusion support, and Pro plan requirements.
What This Skill Does
Generates images through the ZenMux API using the Gemini 3 Pro Image model. Supports text prompts, modifying existing images, and fusing elements from multiple reference images into a single output.
Multi-image fusion lets you combine specific elements from separate reference images in one call, which most single-input image APIs cannot do.
When to use it
- Generate concept art from a text description
- Apply a style or mood change to an existing photo
- Swap costumes or outfits between reference images
- Create character illustrations from descriptive prompts
- Produce variations of a product image with a new background
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: put this character in that costume, providing child.png and costume.jpg
- 1Set ZENMUX_API_KEY environment variable
- 2Run scripts/generate.py with --prompt describing the fusion task
- 3Pass both image paths via --images child.png costume.jpg
- 4Model processes the reference images and merges the specified elements
generated_image.png containing the character wearing the costume from the reference
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.