Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Connects to a local ComfyUI instance to generate images from text prompts or edit uploaded images using a reference workflow. All processing runs on the user's machine using the Flux2-Klein-4B model with VAE and CLIP. Returns generated images directly as chat attachments.
All image generation and editing happens locally, so no prompts or images are sent to external services.
When to use it
- Generating concept art from a text description
- Editing a product photo with a new visual style
- Adding effects or branding elements to an uploaded image
- Drafting visual mockups without leaving the chat interface
- Prototyping image variations from a reference photo
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Edit this image [uploads handbag_white.png] to add neon glow and a logo
- 1Detects uploaded image in the message
- 2Copies image to ~/clawd/skills/comfy-ai/input/
- 3Loads the img2img workflow JSON
- 4Sends request to local ComfyUI at http://192.168.31.7:8000
- 5Retrieves generated image from the output folder
Edited image returned as a media attachment in chat
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.