ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified ai models Safety 3/5

comfyui-request

Send a workflow request to ComfyUI and return image results.

Why use this skill?

Seamlessly integrate ComfyUI into your OpenClaw agent. Automate image generation, trigger custom workflows, and retrieve assets programmatically.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/xtopher86/comfyui-request
Or

What This Skill Does

The comfyui-request skill serves as a robust bridge between the OpenClaw AI agent and your local or remote ComfyUI instance. ComfyUI is a powerful, node-based GUI for Stable Diffusion, and this skill automates the execution of these complex generative workflows programmatically. Instead of manually interacting with the ComfyUI web interface, the agent can trigger specific image generation tasks directly by sending structured JSON workflow data to your server. It handles the communication process, waits for the generation to complete, and retrieves the resulting media assets, whether as public URLs or base64 encoded strings, making it a powerful tool for visual content automation.

Installation

To integrate this skill into your environment, use the OpenClaw CLI tool. Open your terminal and execute the following command: clawhub install openclaw/skills/skills/xtopher86/comfyui-request Once installed, you must configure your ComfyUI server details. Create a .env file within the skill directory or define environment variables for COMFYUI_HOST and COMFYUI_PORT. If your ComfyUI instance is protected, ensure you populate COMFYUI_USER and COMFYUI_PASS to allow the agent to authenticate correctly.

Use Cases

  • Automated Asset Generation: Generate batches of marketing images or social media banners programmatically during off-peak hours.
  • Dynamic UI Mockups: Create custom product visualizations for end-users based on their specific input parameters.
  • Workflow Chaining: Incorporate image generation as a step in a larger pipeline where an AI agent first processes text data, generates a prompt, and then visualizes the output via ComfyUI.

Example Prompts

  1. "Generate a product showcase image using the workflow in workflow_config.json with the product prompt set to 'a minimalist wooden chair'."
  2. "Run the latest batch of style-transfer workflows on the provided image and save the results."
  3. "Execute the ComfyUI workflow for generating an architectural sketch based on the structural parameters I just uploaded."

Tips & Limitations

  • Payload Size: Large workflows with high-resolution output may take significant time to process; ensure your server has adequate GPU memory.
  • Endpoint Requirements: This skill specifically requires an /run endpoint on your ComfyUI server. You may need custom middleware or a wrapper script if your instance does not natively expose this specific route.
  • Security: Always use Basic Auth if your ComfyUI server is reachable via a network to prevent unauthorized generation resource exhaustion.

Metadata

Author@xtopher86
Stars879
Views0
Updated2026-02-11
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-xtopher86-comfyui-request": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#generative-art#automation#stable-diffusion#comfyui#image-generation
Safety Score: 3/5

Flags: network-access, external-api