This skill allows OpenClaw to generate images by connecting to a ComfyUI instance running on the local network.
COMFYUI_SERVER_ADDRESS environment variable to your PC's IP and port (e.g., http://192.168.1.119:8189).Run the internal generation script with a prompt:
python3 {skillDir}/scripts/comfy_gen.py "your image prompt" $COMFYUI_SERVER_ADDRESS
Place your API JSON workflows in the workflows/ folder, then specify the path:
python3 {skillDir}/scripts/comfy_gen.py "your prompt" $COMFYUI_SERVER_ADDRESS --workflow {skillDir}/workflows/my_workflow.json
image-gens/ and can be configured to sync to local document folders.workflows/ folder. The script will automatically try to inject your prompt and a random seed into the workflow nodes.The skill uses a Python helper (scripts/comfy_gen.py) to handle the WebSocket/HTTP handshake with the ComfyUI API, queue the prompt, and download the resulting image.
comfy_gen.py script after the prompt, not just as an environment variable.python3 ... "Your prompt" http://192.168.1.119:8189 ...--workflow '/path/to/your/workflow file name.json'comfy_gen.py script does not appear to have a direct parameter for controlling Lora weights (e.g., setting 'l1lly' Lora to 0.90). This might need to be configured within the workflow JSON itself, or require modifications to the script or workflow.ComfyUI_temp_...png) rather than more descriptive ones by default.共 1 个版本