OpenClaw ComfyUI

What this skill does

The core script skills/comfyui/comfy_client.py handles prompt injection, image uploads, and result polling; the host address is configured in TOOLS.md (example 192.168.1.38:8190), workflow templates live in skills/comfyui/workflows/, and outputs go to outputs/comfy/ relative to the workspace root. Invocation is python3 skills/comfyui/comfy_client.py <template_id> "<prompt>" [input_image_path] [orientation]: gen_z runs text-to-image with image_z_image_turbo.json, and qwen_edit runs image-to-image/editing with qwen_image_edit_2511.json including automatic image upload; orientation is portrait (720x1280) or landscape (1280x720), defaulting to portrait. To extend, drop an API-formatted JSON workflow into the workflows directory and register a new ID in WORKFLOW_MAP, adjusting the injection logic in main() if the workflow uses unique node types. Token-saving strategy: reference workflows by template_id instead of sending full JSON in chat, prefer the file path from metadata over analyzing image content via vision, and deliver images directly via messaging plugins (e.g., Telegram) or local open to avoid bloating the context window with base64 data. The skill card warns that a ComfyUI server can influence downloaded filenames and cause local writes without safe path checks — constrain downloads to an approved output directory, normalize filenames, and reject path traversal; media uploaded for editing leaves the local workspace for the configured ComfyUI server, and remote or shared endpoints increase exposure.

Profile published 2026-10-27

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Monthly Trend

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

# ComfyUI-OpenClaw Skill 🎨✨

A professional, token-saving agent skill for connecting and controlling ComfyUI via API. Designed for high efficiency, automatic asset handling, and seamless integration with OpenClaw.

## 🏗️ Skill Structure
- **Host Address:** `192.168.1.38:8190` (Configured in `TOOLS.md`)
- **Workflow Directory:** `skills/comfyui/workflows/` (Self-contained within the skill folder)
- **Output Directory:** `outputs/comfy/` (Relative to workspace root)
- **Core Script:** `skills/comfyui/comfy_client.py` (Handles prompt injection, image uploads, and result polling)

## 🛠️ Tools (CLI)
Invoke via the `exec` command:
`python3 skills/comfyui/comfy_client.py <template_id> "<prompt>" [input_image_path/orientation] [orientation]`

### Parameters:
- **template_id:**
    1. `gen_z`: Text-to-Image (uses `image_z_image_turbo.json`)
    2. `qwen_edit`: Image-to-Image / Editing (uses `qwen_image_edit_2511.json`) - *Supports automatic image upload.*
- **prompt:** The description of the image to generate or edits to perform.
- **input_image_path:** (Optional) Local path for image-to-image tasks.
- **orientation:** (Optional) Set to `portrait` (720x1280) or `landscape` (1280x720). Defaults to `portrait`.

## 💡 How to Add New Workflows
You can expand this skill easily:
1. Place your new API-formatted JSON workflow in `skills/comfyui/workflows/`.
2. Update the `WORKFLOW_MAP` dictionary in `skills/comfyui/comfy_client.py` with a new ID and the file path.
3. (Optional) If the workflow uses unique node types, adjust the injection logic in the script's `main()` function.

## 🚀 Token-Saving Strategy
- **Template Mapping:** Never send full workflow JSONs in the chat. Refer to them by `template_id`.
- **Vision-Saving Strategy:** To minimize token usage, the agent should prioritize using the **file path from metadata** instead of analyzing image content via vision capabilities unless explicitly asked to describe or analyze the image.
- **Direct Delivery:** Deliver images directly to users via messaging plugins (e.g., Telegram) or local file openers (`open`) to avoid bloating the LLM's context window with base64 data.

Popular in Design & Media