From 9e411073e901f766118a7b82f613872fd745ecc2 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 9 Dec 2023 13:41:30 -0500 Subject: [PATCH] Add instructions for those that have python 3.12 --- README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 450a012b..167214c0 100644 --- a/README.md +++ b/README.md @@ -93,23 +93,27 @@ Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints Put your VAE in: models/vae -Note: pytorch does not support python 3.12 yet so make sure your python version is 3.11 or earlier. +Note: pytorch stable does not support python 3.12 yet. If you have python 3.12 you will have to use the nightly version of pytorch. If you run into issues you should try python 3.11 instead. ### AMD GPUs (Linux only) AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version: ```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.6``` -This is the command to install the nightly with ROCm 5.7 that might have some performance improvements: +This is the command to install the nightly with ROCm 5.7 which has a python 3.12 package and might have some performance improvements: ```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm5.7``` ### NVIDIA -Nvidia users should install pytorch using this command: +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 has a python 3.12 package and 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: