基于Anaconda如何安装ComfyUI

基于conda安装ComfyUI

并且基于同一个虚拟环境（SDW)安装。

然后可以直接参考github中ComfyUI Readme的方法安装。

Manual Install (Windows, Linux)

Git clone this repo.

Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints

Put your VAE in: models/vae

NVIDIA

Nvidia users should install stable pytorch using this command:

pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121

This is the command to install pytorch nightly instead which might have performance improvements:

pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121

Troubleshooting

If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with:

pip uninstall torch

And install it again with the command above.

Dependencies

Install the dependencies by opening your terminal inside the ComfyUI folder and:

pip install -r requirements.txt

After this you should have everything installed and can proceed to running ComfyUI.

直接选择一个路径文件夹，鼠标右键下拉选中Git Bash，

输入或者复制：git clone https://github.com/comfyanonymous/ComfyUI.git

然后启动Anaconda Prompt 激活SDW 虚拟环境，安装Requirements，

等待安装完成，可以启动comfyUI了，以后就可以按照如下方式启动：

当看到这个链接，可以Ctrl+左键在浏览器中打开了，或者复制粘贴也可以。