13 Commits

Author	SHA1	Message	Date
comfyanonymous	3b9a2f504d	Move code to empty gpu cache to model_management.py	2023-04-15 11:19:07 -04:00
藍+85CD	47e0c9415a	Support releases all unoccupied cached memory from XPU	2023-04-15 15:50:51 +08:00
pythongosssss	8a1dcd1adf	Allows nodes to return ui data and output data ... Fire executed event on node when message received	2023-03-29 18:53:24 +01:00
Davemane42	7f2e0d1d1a	add unique_id to nodes hidden inputs ... @classmethod def INPUT_TYPES(cls): return { "hidden": {"unique_id": "UNIQUE_ID"}, }	2023-03-28 02:52:12 -04:00
comfyanonymous	7800fecf22	Fix errors appearing more than once.	2023-03-27 02:16:58 -04:00
comfyanonymous	35a3b7de52	Fix IS_CHANGED not working on nodes with an input from another node.	2023-03-27 01:56:22 -04:00
comfyanonymous	1634d030fb	Use inference_mode instead of no_grad.	2023-03-22 03:48:26 -04:00
pythongosssss	e69202b33e	Updated to reuse session id if available	2023-03-07 13:24:15 +00:00
comfyanonymous	40fe09c7b8	Add a button to interrupt processing to the ui.	2023-03-02 15:24:51 -05:00
comfyanonymous	b59b82a73b	Add a way to interrupt current processing in the backend.	2023-03-02 14:42:03 -05:00
comfyanonymous	392364779f	Only clear cuda cache on CUDA since it causes slowdowns on ROCm.	2023-02-28 13:39:30 -05:00
comfyanonymous	fc9323caf2	Try to clear more memory at the end of each prompt execution.	2023-02-28 11:56:33 -05:00
comfyanonymous	f05d2bab79	Move some stuff from main.py to execution.py	2023-02-27 19:44:58 -05:00