Back to Registry View Author Profile
Official Verified
Comfy Ai
Skill by tullyhu
skill-install — Terminal
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/tullyhu/comfy-aiOr
ComfyAI Skill for Clawdbot
Description
Integrates with local ComfyUI instance at http://192.168.31.7:8000 to generate images from text (txt2img) and edit images using uploaded references (img2img). Uses the workflow: ~/clawd/skills/comfy-ai/image_flux2_klein_image_edit_4b_distilled.json.
Capabilities
- ✅ Text-to-image: Generate images from text prompts only
- ✅ Image-to-image: Edit uploaded image using a text prompt and reference image
- ✅ Returns generated image as media attachment directly to chat
Requirements
- ComfyUI running at
http://192.168.31.7:8000 - Workflow file located at
~/clawd/skills/comfy-ai/image_flux2_klein_image_edit_4b_distilled.json curl,jq, andpython3installed (standard on macOS)
Usage Examples
"Generate a cyberpunk cat wearing sunglasses"
"Edit this image: [upload handbag_white.png] with prompt 'add neon glow and logo from reference'
How It Works
- For text-only: Uses the workflow’s empty latent + positive prompt
- For image edit: Automatically detects uploaded image → copies it to
~/clawd/skills/comfy-ai/input/→ triggers img2img - Generated images are saved to
~/clawd/skills/comfy-ai/output/and returned as media attachment - Uses Flux2-Klein-4B model with VAE and CLIP from your workflow
Security Note
All processing happens locally. No data leaves your machine.
Metadata
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-tullyhu-comfy-ai": {
"enabled": true,
"auto_update": true
}
}
}Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.