The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Better memory estimation for ROCm that support mem efficient attention.
comfyanonymous8773ccf74d18
diff --git a/comfy/model_management.py b/comfy/model_management.pyindex f3d90c668..212ce9af2 100644--- a/comfy/model_management.py+++ b/comfy/model_management.py@@ -909,6 +909,8 @@ def pytorch_attention_flash_attention():return Trueif is_ascend_npu():return True+ if is_amd():+ return True #if you have pytorch attention enabled on AMD it probably supports at least mem efficient attentionreturn Falsedef mac_version():