Setup & Installation
openclaw skills install @xtopher86/comfyui-request
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install comfyui-request
What This Skill Does
Sends a JSON workflow to a running ComfyUI server and returns the generated image as a URL or base64 string. Connects over HTTP using configurable host, port, and optional basic auth credentials.
Lets agents drive ComfyUI image generation without manual UI interaction, making it composable with other automated steps.
When to use it
- Triggering image generation from an AI agent conversation
- Automating batch image workflows without opening the ComfyUI UI
- Integrating ComfyUI output into a larger multi-step pipeline
- Testing workflow JSON changes programmatically
- Retrieving generated images for downstream processing or storage
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Run this ComfyUI workflow and give me the output image
AGENT
- 1Load the workflow JSON object
- 2POST the workflow to the ComfyUI /run endpoint at the configured host and port
- 3Receive the JSON response from the server
- 4Extract the image field containing the URL or base64 string
OUTPUT
Image URL or base64 string ready for display or further processing
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
ComfyUI server installed and running with the /run endpoint exposedCOMFYUI_USER and COMFYUI_PASS credentials if the server requires basic auth