989 Commits

Author	SHA1	Message	Date
Vladimir Mandic	5ed58ac7cc	end-to-end update flux, see changelog and wiki	2024-08-28 08:04:24 -04:00
Disty0	3a97db1f8a	Fix setting no-half-vae	2024-08-22 00:16:00 +03:00
Disty0	6a58d5210b	Make eval use apply_compile_to_model	2024-08-19 20:06:51 +03:00
Disty0	cc89ed84f9	Rename cpu offload to model offload	2024-08-19 18:48:09 +03:00
Disty0	a3f26c9df0	Convert Dynamic Attention SDP to a global SDP option	2024-08-18 01:44:27 +03:00
Disty0	5c857e8aaf	Add check for Flux attention processor	2024-08-18 00:35:10 +03:00
Disty0	bce3c7eabf	Fix --Xvram flags not activating offload	2024-08-18 00:23:15 +03:00
Disty0	5a75b120ae	Fix Lora with Balanced Offlaod	2024-08-16 21:22:41 +03:00
Disty0	7a6b45b410	Balanced offload move device map calcs	2024-08-16 02:49:42 +03:00
Disty0	8699e0cacb	Add gc to balanced offload	2024-08-14 17:37:07 +03:00
Disty0	7edc864014	Add module name to disk offload path	2024-08-14 12:21:54 +03:00
Disty0	8619a7f35c	Better balanced offload	2024-08-14 11:53:35 +03:00
Disty0	a73716bf89	Add meta to device check	2024-08-13 23:35:56 +03:00
Disty0	97a5faed4c	Fix qint4	2024-08-13 23:24:42 +03:00
Disty0	6a1af56834	FLUX quant loading support	2024-08-11 23:54:05 +03:00
Disty0	fb89e26b54	Auto detect memory size ffor balaced offload	2024-08-11 19:01:49 +03:00
Disty0	4ba173280b	Check device index for balanced offload	2024-08-11 17:35:07 +03:00
Disty0	e3b087b6c0	Add balanced offload mode and make offload modes a single choice list	2024-08-11 17:27:30 +03:00
Seunghoon Lee	a9f27991a3	enable diffusers_move_unet for Flux	2024-08-09 16:12:01 +09:00
Disty0	1cf87ef409	Change cascade load order	2024-08-07 05:03:26 +03:00
Disty0	9818950991	Cascade fixes	2024-08-07 04:54:41 +03:00
Disty0	6c75bcca0a	Optimum Quanto support	2024-07-30 17:35:56 +03:00
Vladimir Mandic	9e6fb5249c	add auraflow	2024-07-12 08:43:30 -04:00
Vladimir Mandic	dddf0f2aeb	draft kwai kolors	2024-07-07 12:44:38 -04:00
Vladimir Mandic	32dc4b3ab4	draft lumina work	2024-07-05 20:06:06 -04:00
Disty0	e5bd949b93	Don't force vae config on huggingface models	2024-07-03 19:00:50 +03:00
Vladimir Mandic	576d9aae73	autodetect sd3-t5-fp16	2024-06-28 09:27:36 -04:00
Vladimir Mandic	16ab1a0af7	lint updates	2024-06-26 08:58:22 -04:00
Vladimir Mandic	2f9f2c5c52	fix inpaint pipeline missing requires_aesthetics_score	2024-06-22 18:00:01 -04:00
Vladimir Mandic	01ca2d40fb	cleanup	2024-06-22 08:43:06 -04:00
Vladimir Mandic	e4a8919ca1	one more fix for requires_aesthetics_score	2024-06-22 08:35:18 -04:00
Disty0	bbaec29720	Cleanup	2024-06-21 21:07:15 +03:00
Vladimir Mandic	0f459411e4	extra check	2024-06-21 12:59:35 -04:00
Disty0	77657611c0	Fix Diffusers requires_aesthetics_score	2024-06-21 19:30:20 +03:00
Disty0	8eb26b202c	Update changelog	2024-06-21 18:21:48 +03:00
Disty0	43a54317ee	Fix face hires with lowvram	2024-06-21 18:09:56 +03:00
Vladimir Mandic	a1beb777fc	update notes	2024-06-21 08:35:37 -04:00
Vladimir Mandic	6b6170bfaa	Merge branch 'dev' into SD3-parsing	2024-06-21 08:16:44 -04:00
Vladimir Mandic	e51599cc6f	disable model load fallback on unknown model	2024-06-20 18:21:42 -04:00
Vladimir Mandic	1a6d313340	cleanup	2024-06-20 13:46:31 -04:00
AI-Casanova	1fcd378bd1	Merge branch 'dev' into SD3-parsing	2024-06-19 23:47:17 -05:00
AI-Casanova	e3009753e3	Finish SD3 Prompt Parsing, reconfigure Compel Hijack	2024-06-19 23:41:11 -05:00
Disty0	bf9565cb46	NNCF compression support on CPU and add INT8 option for T5	2024-06-19 21:23:47 +03:00
Vladimir Mandic	2a27cd916d	pixart sigma improvements	2024-06-18 13:21:13 -04:00
Vladimir Mandic	bbaa03a466	add 4bit t5	2024-06-17 09:39:30 -04:00
Vladimir Mandic	9644063cd6	add generic t5 loader	2024-06-16 11:38:29 -04:00
Vladimir Mandic	a726acbcc6	fix HunyuanDiT	2024-06-15 17:08:33 -04:00
Vladimir Mandic	5feaed0c6a	unify hf-login	2024-06-15 16:47:03 -04:00
Vladimir Mandic	3f1c236ce4	force apply vae config on model load	2024-06-13 20:13:18 -04:00
Vladimir Mandic	d7983eece7	sd3 add transformer attention method	2024-06-13 13:28:24 -04:00