18 Commits

Author	SHA1	Message	Date
wfjsw	cca6102ff3	cleanup	2024-03-09 19:12:42 -10:00
wfjsw	4f0d5a583e	smart lowvram mover	2024-03-09 19:12:42 -10:00
wfjsw	c1702ea498	async weight mover	2024-03-09 19:12:42 -10:00
AUTOMATIC1111	016554e437	add --medvram-sdxl	2023-08-22 18:49:08 +03:00
AUTOMATIC1111	b235022c61	option to keep multiple models in memory	2023-08-01 00:24:48 +03:00
AUTOMATIC1111	2c11e9009e	repair --medvram for SD2.x too after SDXL update	2023-07-24 11:57:59 +03:00
AUTOMATIC1111	9a3f35b028	repair medvram and lowvram	2023-07-14 09:56:01 +03:00
AUTOMATIC1111	da464a3fb3	SDXL support	2023-07-12 23:52:43 +03:00
AUTOMATIC	1ca5e76f7b	fix for conds of second hires fox pass being calculated using first pass's networks, and add an option to revert to old behavior	2023-06-04 13:07:31 +03:00
MrCheeze	8a34671fe9	Add support for the Variations models (unclip-h and unclip-l)	2023-03-25 21:03:07 -04:00
MrCheeze	a1c8ad8828	unload depth model if medvram/lowvram enabled	2022-12-10 11:02:47 -05:00
AUTOMATIC	b5050ad207	make SD2 compatible with --medvram setting	2022-11-26 20:52:16 +03:00
Jairo Correa	af758e97fa	Unload sd_model before loading the other	2022-11-01 04:01:49 -03:00
AUTOMATIC	50b5504401	remove parsing command line from devices.py	2022-10-22 14:04:14 +03:00
AUTOMATIC	9bb20be090	memory optimization for CLIP interrogator ... changed default cfg_scale to a higher value	2022-09-12 11:55:27 +03:00
Abdullah Barhoum	b5d1af11b7	Modular device management	2022-09-11 09:49:43 +03:00
xeonvs	aaeeef82fa	Miss device type for option --medvram	2022-09-07 18:09:30 +02:00
AUTOMATIC	345028099d	split codebase into multiple files; to anyone this affects negatively: sorry	2022-09-03 12:08:45 +03:00