Official Verified media Safety 4/5

comfyui

Generate high-quality images using a local ComfyUI instance. Use when the user wants private, powerful image generation via their own hardware and custom workflows. Requires a running ComfyUI server accessible on the local network.

Why use this skill?

Integrate OpenClaw with ComfyUI to generate high-quality images locally. Control your models, use custom workflows, and maintain data privacy.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/dihan/comfy-ui

Download Source Code (.zip)

What This Skill Does

The ComfyUI skill enables the OpenClaw agent to leverage your local hardware for high-fidelity image generation. By acting as an interface between OpenClaw and a local ComfyUI server instance, this skill allows for powerful, private, and customizable AI-assisted image creation. Instead of relying on centralized, restrictive, or expensive cloud-based APIs, you maintain full control over your models, LoRAs, and sampling configurations.

Installation

To begin, ensure you have a running ComfyUI instance on your network. Verify that 'Enable Dev mode' is active in your ComfyUI settings. Install the skill directly via the OpenClaw CLI using the following command:

clawhub install openclaw/skills/skills/dihan/comfy-ui

Once installed, set your COMFYUI_SERVER_ADDRESS environment variable to match your instance, such as http://192.168.1.119:8189. The skill relies on an internal script located in the skill directory to manage WebSockets and API requests.

Use Cases

This skill is perfect for power users who require consistent artistic styles, need to adhere to strict privacy standards, or utilize custom Stable Diffusion XL workflows. It is ideal for creative professionals generating assets, prototyping AI design concepts, or automating batch image production tasks while ensuring all sensitive or private data never leaves your local network.

Example Prompts

"OpenClaw, generate a high-quality portrait of a cyberpunk explorer in a neon-lit alleyway using my custom SDXL workflow."
"Create an image of a serene mountain landscape at sunrise, and save it to the image-gens folder."
"Run a new image generation for a futuristic architecture concept using the workflow located at /workflows/arch_design.json with the prompt 'glass skyscraper in a jungle'."

Tips & Limitations

Workflow Customization: While the skill defaults to a high-quality Juggernaut XL setup, you can inject your own complex JSON workflows. Note that parameter-heavy tasks like LoRA weight adjustments should be configured within the JSON file directly, as the current script does not support CLI-based weight overrides.
File Management: Images are automatically saved to the image-gens/ directory. Keep an eye on your disk space as high-resolution generations can grow significantly in size over time.
Security: Since this skill communicates via HTTP/WebSocket on your local network, ensure your local firewall settings allow the agent to reach the specific ComfyUI port.
Naming: Be aware that outputs may generate with generic temporary filenames; implement a periodic file organization routine if you use the tool heavily.

Read Full Documentation on GitHub

Metadata

Author@dihan

Stars2387

Updated2026-03-09

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-dihan-comfy-ui": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#image-generation#comfyui#stablediffusion#local-ai#creative

Safety Score: 4/5

Flags: network-access, file-write, file-read, code-execution

Related Skills

comfyui-local

dihan 2190