The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Pytorch stable 2.7 is out and support cu128 (#7749)
comfyanonymous21a11ef817e3
diff --git a/README.md b/README.mdindex cf6df7e55..62800bb4f 100644--- a/README.md+++ b/README.md@@ -216,9 +216,9 @@ Additional discussion and help can be found [here](https://github.com/comfyanonyNvidia users should install stable pytorch using this command:-```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu126```+```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu128```-This is the command to install pytorch nightly instead which supports the new blackwell 50xx series GPUs and might have performance improvements.+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/cu128```