The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Please try native formats instead of disabling dynamic vram. (#14577)
comfyanonymous833bfb572e85
diff --git a/main.py b/main.pyindex ad5c11e16..aa4ee2adb 100644--- a/main.py+++ b/main.py@@ -557,8 +557,13 @@ if __name__ == "__main__":logging.warning("WARNING: You are using a python version older than 3.10, please upgrade to a newer one. 3.12 and above is recommended.")if args.disable_dynamic_vram:- logging.warning("Dynamic vram disabled with argument. If you have any issues with dynamic vram enabled please give us a detailed reports as this argument will be removed soon.")-+ logging.warning(+ "Dynamic vram disabled with argument. If you have any issues with "+ "dynamic vram enabled please give us a detailed reports as this "+ "argument will be removed soon. If you use gguf we recommend keeping "+ "dynamic vram enabled and using native ComfyUI model formats instead. "+ "ComfyUI native formats like fp8 will be faster even if they are larger than your memory."+ )event_loop, _, start_all_func = start_comfyui()try:x = start_all_func()