A powerful local AI image generation skill leveraging ComfyUI for high-speed text-to-image creation and automated grid layouts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install comfyui-image-generator
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install comfyui-image-generator 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 ComfyUI Image Generator?
The ComfyUI Image Generator is a sophisticated tool designed for local AI image creation within the Openclaw Skills ecosystem. It enables users to transform text prompts into high-quality visual assets using a optimized ComfyUI backend. By leveraging GGUF-based models like z-image-turbo, this skill provides a high-performance alternative to cloud-based generators, ensuring data privacy and reducing latency for developers and creative professionals.
This skill is specifically engineered to handle both individual image requests and complex grid-based generations (4, 9, or 16 tiles). It seamlessly bridges the gap between local processing power and cloud accessibility by automatically syncing generated outputs to remote storage, making it a cornerstone for automated creative workflows.
ComfyUI Image Generator Use Cases
- Rapidly generate concept art or UI assets directly from a terminal or agent interface using Openclaw Skills.
- Create character sheets or variation grids (up to 16 images) for creative brainstorming sessions.
- Automate the production of localized visual content without relying on expensive third-party API credits.
- Build integrated media pipelines where generated images are automatically archived to Google Drive for team review.
How ComfyUI Image Generator Works
- The user inputs a descriptive prompt along with optional parameters such as file prefixes, grid counts, or specific seeds.
- The skill executes a specialized bash script that interfaces with the local ComfyUI API.
- A pre-configured node structure (including UnetLoaderGGUF and KSampler) processes the request using the z-image-turbo model.
- The system monitors the generation process with a high-timeout threshold to ensure completion of complex tasks.
- Once generated, the image is saved to a local directory and a copy is uploaded to the user's Google Drive 'Generated Images' folder.
ComfyUI Image Generator Setup
To utilize this within the Openclaw Skills framework, ensure your local ComfyUI instance is active and the required GGUF models are placed in your models directory.
# Generate a single image
bash /path/to/comfyui_image_generator/generate_image.sh "your prompt here"
# Generate a 4-image grid
bash /path/to/comfyui_image_generator/generate_grid.sh "your prompt" "output_prefix" 4
ComfyUI Image Generator Data Schema & Taxonomy
| Data Component | Specification |
|---|---|
| Resolution | Default 512x512 (optimized for speed) |
| Local Storage | /Users/pc8521/Documents/ComfyUI/output/ |
| Cloud Storage | Google Drive /Generated Images/ |
| Node Pipeline | GGUF Unet, CLIP, VAE, and KSampler (Euler) |
| File Naming | [Prefix][Timestamp][Seed].png |
ComfyUI Image Generator Advanced Features
- Support for multi-grid generation (4, 9, and 16 tiles) to compare variations in a single execution.
- Integrated GGUF support for running high-quality models like Qwen3-4B on consumer-grade hardware.
- Automated cloud synchronization that triggers immediately after image rendering is complete.
- Silent execution mode with all progress redirected to background logs to avoid CLI clutter.
- Extended timeout protection (900s) to prevent script termination during intensive 16-grid generation tasks within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Google Free Media Generator
A browser-based automation skill for generating high-quality AI images and videos via Google Gemini and Google Flow without incurring API costs.
F5-TTS Mining Rig Monitor
A specialized monitoring tool for tracking F5-TTS training progress on multi-GPU mining rigs via non-intrusive SSH commands.
F5-Telegram-Notify
A specialized notification utility to track F5-TTS model training status and results via Telegram alerts.
Browser Download
Enables AI agents to programmatically identify and download files from web pages using the browser tool.
Bilibili Analytics
A professional data extraction and analysis tool for Bilibili search results, generating structured reports on trends and engagement.
Feishu Mention Bot
A specialized tool for programmatically @mentioning robots within Feishu group chats to trigger automated workflows and inter-agent communication.
Featured*
