The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Add another ROCm tip.
comfyanonymous3bed56bb1399
diff --git a/README.md b/README.mdindex f88d63f24..bf7803bab 100644--- a/README.md+++ b/README.md@@ -219,6 +219,8 @@ You can enable experimental memory efficient attention on pytorch 2.5 in ComfyUI```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```+You can also try setting this env variable `PYTORCH_TUNABLEOP_ENABLED=1` which might speed things up at the cost of a very slow initial run.+# NotesOnly parts of the graph that have an output with all the correct inputs will be executed.