2.3 KiB
Manual Install on Linux with NVIDIA GPU
Clone the repo
git clone git@github.com:comfyanonymous/ComfyUI.git
Install dependencies
Make sure you have cuda12+ installed.
Follow instruction on NVIDIA's website
wget https://developer.download.nvidia.com/compute/cuda/12.6.1/local_installers/cuda-repo-debian11-12-6-local_12.6.1-560.35.03-1_amd64.deb
sudo dpkg -i cuda-repo-debian11-12-6-local_12.6.1-560.35.03-1_amd64.deb
sudo cp /var/cuda-repo-debian11-12-6-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo add-apt-repository contrib
sudo apt-get update
sudo apt-get -y install cuda-toolkit-12-6
And install the driver
sudo apt-get install -y cuda-drivers
Install Miniconda. This will help you install the correct versions of Python and other libraries needed by ComfyUI.
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm ~/miniconda3/miniconda.sh
Create an environment with Conda.
conda create -n comfyenv
And activate it
conda activate comfyenv
Install python dependencies
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
https://docs.comfy.org/get_started/introduction
https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors
https://github.com/Fannovel16/comfyui_controlnet_aux
https://github.com/ltdrdata/ComfyUI-Manager
https://comfyanonymous.github.io/ComfyUI_examples/controlnet/
https://github.com/WASasquatch/comfyui-plugins
https://github.com/JasonS09/comfy_controlnet_preprocessors
https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/tree/main
https://huggingface.co/Comfy-Org/flux1-schnell/tree/main
https://huggingface.co/gradjitta/flux.1-schnell-nf4/tree/main
https://huggingface.co/monster-labs/control_v1p_sd15_qrcode_monster/tree/main
https://www.youtube.com/watch?v=7PpYsaAoYF8
Create Consistent, Editable AI Characters & Backgrounds for your Projects! https://www.patreon.com/posts/new-video-create-103261741