comfy-ui
dihan 作
DevOps & Cloud概要
Generate high-quality images using a local ComfyUI instance.
説明
このスキルでできること
Connects OpenClaw to a locally running ComfyUI instance for image generation. Uses an SDXL workflow by default (Juggernaut XL) and supports custom API JSON workflows. Images are saved locally and generation happens entirely on your own hardware.
All generation runs on your own machine, so prompts and images never leave your network and there are no per-image API costs.
使いどころ
- Generating images privately without sending prompts to cloud services
- Running custom LoRA or fine-tuned model workflows from a home server
- Batch-generating concept art using saved workflow JSON files
- Automating image creation as part of a local agent pipeline
- Producing high-resolution SDXL outputs on dedicated GPU hardware
ワークフロー例
User asks: Generate an image of a misty mountain at dawn
- 1
Reads COMFYUI_SERVER_ADDRESS from environment
- 2
Calls comfy_gen.py with the prompt and server address
- 3
Script connects to ComfyUI via WebSocket/HTTP and queues the prompt
- 4
Waits for generation to complete and downloads the resulting image
- 5
Saves image to image-gens/ folder and returns the file path
Generated image saved locally, file path returned to user
要件
- COMFYUI_SERVER_ADDRESS environment variable (e.g. http://192.168.1.119:8189)
- ComfyUI installed and running locally with Dev mode enabled
インストール
clawhub install dihan/comfy-uiCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。