ComfyAI Skill for Clawdbot for Openclaw

A local ComfyUI integration for Clawdbot that enables high-quality AI image generation and editing directly within your chat interface.

tullyhu
v1.0.0
Jan 28, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install comfy-ai

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install comfy-ai using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is ComfyAI Skill for Clawdbot?

The ComfyAI Skill for Clawdbot bridges the gap between your local AI art suite and your AI agent. By leveraging your existing ComfyUI setup, this tool allows for seamless text-to-image and image-to-image workflows using specialized models like Flux2. As part of the Openclaw Skills library, it ensures all processing remains local for maximum privacy and performance without relying on external cloud-based generation services.

ComfyAI Skill for Clawdbot Use Cases

  • Generating custom concept art or illustrations from simple text prompts.
  • Applying AI-driven edits to existing images using reference photos and specific instructions.
  • Automating asset creation for design projects directly through chat commands.
  • Maintaining complete data privacy by processing all AI image generation on local hardware.

How ComfyAI Skill for Clawdbot Works

  1. Detects user intent for image generation or editing within the Clawdbot interface.
  2. For image-to-image tasks, the skill automatically copies uploaded files to the local input directory at ~/clawd/skills/comfy-ai/input/.
  3. Triggers the specified JSON workflow on the local ComfyUI instance via API calls.
  4. Processes the prompt through the Flux2-Klein-4B model with integrated VAE and CLIP components.
  5. Retrieves the generated output from the output folder and returns it as a direct media attachment in the chat.

ComfyAI Skill for Clawdbot Setup

Ensure ComfyUI is running locally at http://192.168.31.7:8000. Install the required system dependencies:

# Install required CLI tools
brew install jq curl python3

Download the required workflow JSON and place it in the following directory to register it with your Openclaw Skills environment: ~/clawd/skills/comfy-ai/image_flux2_klein_image_edit_4b_distilled.json.

ComfyAI Skill for Clawdbot Data Schema & Taxonomy

Component Path / Details
Input Assets ~/clawd/skills/comfy-ai/input/
Generated Output ~/clawd/skills/comfy-ai/output/
Workflow Configuration image_flux2_klein_image_edit_4b_distilled.json
Model Architecture Flux2-Klein-4B Distilled
Connectivity Localhost HTTP API (Port 8000)

ComfyAI Skill for Clawdbot Advanced Features

  • High-performance Flux2-Klein-4B model optimization for fast, distilled image generation.
  • Automated latent space management for precise img2img editing and reference matching.
  • Privacy-first architecture ensuring zero data leakage to external providers.
  • Flexible workflow support allowing for complex multi-node AI image pipelines within Openclaw Skills.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*