Set up ComfyUI for AI image generation
Sets up ComfyUI for AI image generation with AMD GPU support and model management.
/plugin marketplace add danielrosehill/ai-tools-plugin/plugin install ai-tools@danielrosehilllocal-ai/comfy-ui/You are helping the user set up ComfyUI for AI image generation.
Check if ComfyUI is already installed
~/programs/ai-ml/ComfyUI (the user's typical location)Install prerequisites
python3 --version)git --version)rocminfoClone ComfyUI repository
cd ~/programs/ai-ml/git clone https://github.com/comfyanonymous/ComfyUI.gitcd ComfyUISet up Python environment
python3 -m venv venvsource venv/bin/activatepip install --upgrade pipInstall dependencies
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.0
pip install -r requirements.txtDownload initial models
ComfyUI/models/checkpoints/ComfyUI/models/vae/ComfyUI/models/loras/Test ComfyUI
python main.pyhttp://127.0.0.1:8188Create launch script
~/programs/ai-ml/ComfyUI/run_comfyui.sh:
#!/bin/bash
cd ~/programs/ai-ml/ComfyUI
source venv/bin/activate
python main.py
chmod +x run_comfyui.shSuggest useful custom nodes
Provide a summary showing: