Date Updated: 19 February 2025
– Windows 10 (version 1903 or later) or Windows 11
– 64-bit processor
– Virtualization enabled in BIOS/UEFI
– NVIDIA GPU
1 . Enable required Windows features:
– Windows Subsystem for Linux
– Virtual Machine Platform
– Restart your computer after enabling these features
2 . Install WSL and Ubuntu:
https://learn.microsoft.com/en-us/windows/wsl/install-manual# Check current WSL installations
wsl -l -v
# Install WSL (Windows 11)
wsl --install
# Set WSL 2 as default
wsl --set-default-version 2
# Verify Ubuntu is on WSL 2
wsl -l -v
# If needed, upgrade Ubuntu to WSL 2
wsl --set-version ubuntu 21 . Update system packages:
sudo apt update
sudo apt upgrade
sudo apt install -y build-essential2 . Install CUDA 12.1:
wget https://developer.download.nvidia.com/compute/cuda/12.1.0/local_installers/cuda_12.1.0_530.30.02_linux.run
sudo apt install gcc-11 g++-11
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-11 100
gcc --version
g++ --version
sudo sh cuda_12.1.0_530.30.02_linux.run# (Optional) If you want to download other cuda versions check the link below:
https://developer.nvidia.com/cuda-toolkit-archive3 . Configure CUDA environment:
nano ~/.bashrc
export PATH=/usr/local/cuda-12.1/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-12.1/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
# Apply changes
source ~/.bashrc
# Verify CUDA installation
nvcc --version4 . cuDNN:
https://developer.nvidia.com/cudnn# Commands for Cuda 12.1 on Ubuntu 24.04
wget https://developer.download.nvidia.com/compute/cudnn/9.7.1/local_installers/cudnn-local-repo-ubuntu2404-9.7.1_1.0-1_amd64.deb
sudo dpkg -i cudnn-local-repo-ubuntu2404-9.7.1_1.0-1_amd64.deb
sudo cp /var/cudnn-local-repo-ubuntu2404-9.7.1/cudnn-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cudnn
sudo apt-get -y install cudnn-cuda-12
wget https://repo.anaconda.com/miniconda/Miniconda3-py311_24.4.0-0-Linux-x86_64.sh
bash Miniconda3-py311_24.4.0-0-Linux-x86_64.sh
source ~/.bashrc
# All Conda Versions
https://repo.anaconda.com/miniconda/
mkdir comfy
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI/custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager.git
git clone https://github.com/pzc163/Comfyui-CatVTON.git
cd ..
make sure you’re in ComfyUI main folder ~/comfy/ComfyUI
conda create --name comfyui python=3.11
conda activate comfyui
conda install pytorch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 pytorch-cuda=12.1 -c pytorch -c nvidia
pip install -r requirements.txtpip install git+https://github.com/facebookresearch/detectron2.git@v0.6
pip install git+https://github.com/facebookresearch/detectron2.git@v0.6#subdirectory=projects/DensePosepip install accelerate
pip install black
pip install cloudpickle
pip install diffusers
pip install future
pip install fvcore
pip install huggingface_hub
pip install hydra-core
pip install matplotlib
pip install numpy
pip install omegaconf
pip install pycocotools
pip install pydot
pip install setuptools
pip install scikit-image
pip install tabulate
pip install tensorboard
pip install termcolor
pip install yacs
pip install ninja==1.11.1.1
pip install iopath==0.1.9
pip install opencv-python-headless>=4.5.3.56
pip install av>=8.0.3
pip install setuptools==58.2.0
pip install Pillow==9.5.0Important Note: When using these commands, make sure your conda environment name matches exactly. The default path ~/miniconda3/envs/comfyui/lib assumes you’ve named your environment “comfyui” and installed Miniconda in the default location. If you used a different name or location, adjust the paths accordingly.
sudo apt update
sudo apt install --only-upgrade libstdc++6
rm -rf ~/.cache/torch_extensions/
cd ~/miniconda3/envs/comfyui/lib
ln -sf /usr/lib/x86_64-linux-gnu/libstdc++.so.6 libstdc++.so.6conda activate comfyui
cd /path/to/ComfyUI
python main.py– First run will download required models automatically
– Access the interface through your web browser
– CatVTON workflow can be found in ComfyUI/custom_nodes/ComfyUI-CatVTON/workflowÂ
– If you encounter issues after installing other custom nodes, reactivate the conda environment and reinstall CatVTON dependencies
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.
