The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
The new smart memory management makes this unnecessary.
comfyanonymousf72780a7e363
diff --git a/comfy/model_management.py b/comfy/model_management.pyindex 0e86df411..016434492 100644--- a/comfy/model_management.py+++ b/comfy/model_management.py@@ -111,9 +111,6 @@ if not args.normalvram and not args.cpu:if lowvram_available and total_vram <= 4096:print("Trying to enable lowvram mode because your GPU seems to have 4GB or less. If you don't want this use: --normalvram")set_vram_to = VRAMState.LOW_VRAM- elif total_vram > total_ram * 1.1 and total_vram > 14336:- print("Enabling highvram mode because your GPU has more vram than your computer has ram. If you don't want this use: --normalvram")- vram_state = VRAMState.HIGH_VRAMtry:OOM_EXCEPTION = torch.cuda.OutOfMemoryError