Date Updated: 25 Mars 2025
python 3.11 or 3.11
pyTorch 2.6
1 . Check Python Version
python --version
2 . Fresh ComfyUI Installation Process
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI
Check your Cuda version: nvcc --version
Download Pytorch:
https://pytorch.org/get-started/locally/
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt
3 . Nunchaku Wheels
All Nunchaku Wheels: https://huggingface.co/mit-han-lab/nunchaku/tree/main
for torch 2.6 python 3.11
pip install https://huggingface.co/mit-han-lab/nunchaku/resolve/main/nunchaku-0.1.4%2Btorch2.6-cp311-cp311-win_amd64.whl
for torch 2.6 python 3.11
pip install https://huggingface.co/mit-han-lab/nunchaku/resolve/main/nunchaku-0.1.4%2Btorch2.6-cp312-cp312-win_amd64.whl
4 . Custom Nodes
cd custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager comfyui-manager
cd custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager comfyui-manager
git clone https://github.com/mit-han-lab/ComfyUI-nunchaku
cd ComfyUI-nunchaku
pip install -r requirements.txt
pip install -U "huggingface_hub[cli]"
huggingface-cli download comfyanonymous/flux_text_encoders clip_l.safetensors --local-dir models/text_encoders
huggingface-cli download comfyanonymous/flux_text_encoders t5xxl_fp16.safetensors --local-dir models/text_encoders
huggingface-cli download black-forest-labs/FLUX.1-schnell ae.safetensors --local-dir models/vae
huggingface-cli download mit-han-lab/svdq-int4-flux.1-dev --local-dir models/diffusion_models/svdq-int4-flux.1-dev
huggingface-cli download mit-han-lab/svdq-int4-flux.1-fill-dev --local-dir models/diffusion_models/svdq-int4-flux.1-fill-dev
Send download link to:
Learn to create stunning AI Influencer with ComfyUI. This beginner-friendly course will guide you through every step—from basics to advanced techniques.