4712 Commits

Author	SHA1	Message	Date
layerdiffusion	22a19943d2	fix lcm	2024-08-18 19:23:12 -07:00
DenOfEquity	93bfd7f85b	invalidate cond cache if distilled CFG changed (#1240) ... * Update processing.py add distilled_cfg_scale to params that invalidate cond cache * Update ui.py distilled CFG and CFG step size 0.1 (from 0.5)	2024-08-17 19:34:11 -07:00
layerdiffusion	0f266c48bd	make clear_prompt_cache a function	2024-08-17 19:00:13 -07:00
lllyasviel	93b40f355e	Forge Space and BiRefNet	2024-08-17 08:29:08 -07:00
layerdiffusion	1bd6cf0e0c	Support LoRAs for Q8/Q5/Q4 GGUF Models ... what a crazy night of math	2024-08-15 05:34:46 -07:00
layerdiffusion	447f261154	fix	2024-08-15 01:56:21 -07:00
layerdiffusion	3acb50c40e	integrate llama3's GGUF	2024-08-15 01:45:29 -07:00
layerdiffusion	d8b83a9501	gguf preview	2024-08-15 00:03:32 -07:00
David Martin Rius	dad6e9ad02	Fix type error in BLIP model generation by converting configuration values to integers. (#1113) ... - Cast `num_beams` and `min_length` to integers in `interrogate.py` when passing them to the BLIP model's `generate` function. - Resolves issues with type mismatches that caused crashes during the interrogation process.	2024-08-14 17:37:12 -07:00
David Martin Rius	4eadf1b5e6	Fix validation error by updating SDModelItem config field to be optional. Changed config field in SDModelItem model to Optional[str] with default value None. (#1096)	2024-08-14 17:35:17 -07:00
layerdiffusion	b09c24ef51	add fp16_fix	2024-08-14 17:10:03 -07:00
layerdiffusion	bb58520a4c	completely solve 'NoneType' object is not iterable	2024-08-13 15:36:18 -07:00
lllyasviel	61f83dd610	support all flux models	2024-08-13 05:42:17 -07:00
layerdiffusion	d08c9c809c	cleanup codes	2024-08-11 22:07:54 -07:00
layerdiffusion	cd8a181438	make flux inpaint and soft inpaint works	2024-08-11 18:18:16 -07:00
layerdiffusion	36250c78f5	fix flux img2img and highres.fix math	2024-08-11 18:07:50 -07:00
layerdiffusion	19b41b9438	Add option to experiment with results from other impl ... Setting -> Compatibility -> Try to reproduce the results from external software	2024-08-11 17:02:50 -07:00
layerdiffusion	08958f84c0	do not raise	2024-08-11 16:21:52 -07:00
layerdiffusion	fec56de319	show xformers on UI	2024-08-11 15:58:30 -07:00
layerdiffusion	8af421d53a	remove old codes	2024-08-11 15:55:07 -07:00
layerdiffusion	261b7e7b8b	update version check ... but they are not used - weird a1111	2024-08-11 15:48:47 -07:00
layerdiffusion	9001968898	Change default combination to a relatively safe one	2024-08-11 14:26:34 -07:00
layerdiffusion	86ee2d9462	improve hints	2024-08-11 02:00:53 -07:00
lllyasviel	cfa5242a75	forge 2.0.0 ... see also discussions	2024-08-10 19:24:19 -07:00
layerdiffusion	593455c4de	global unload after env var change	2024-08-08 22:34:55 -07:00
layerdiffusion	d3b81924df	make none default to clip	2024-08-08 18:12:06 -07:00
layerdiffusion	cebd828df2	backward compatibility	2024-08-08 17:39:01 -07:00
layerdiffusion	20e1ba4a82	fix	2024-08-08 15:08:20 -07:00
lllyasviel	6921420b3f	Load Model only when click Generate ... #964	2024-08-08 14:51:13 -07:00
layerdiffusion	ce3f0f86b4	prompt-all-in-one now works ... fix for webui backward compatibility	2024-08-08 13:46:42 -07:00
layerdiffusion	1802850eb1	disable negative prompt UI when CFG==1	2024-08-08 02:24:04 -07:00
layerdiffusion	a189f3e53e	distilled cfg scale info text	2024-08-08 01:22:27 -07:00
layerdiffusion	572a3c3d8b	distilled cfg scale	2024-08-08 00:57:40 -07:00
layerdiffusion	653be0a3ad	comments	2024-08-08 00:20:15 -07:00
layerdiffusion	396d9f378d	we do not need to waste 10 seconds on T5 when CFG=1	2024-08-08 00:19:16 -07:00
layerdiffusion	692a0b2422	remove confusing codes that actually do nothing	2024-08-07 19:01:19 -07:00
layerdiffusion	5591b701c1	link k-diffusion to backend	2024-08-07 18:44:53 -07:00
layerdiffusion	69b1827ed5	revise preview logics	2024-08-07 18:00:58 -07:00
lllyasviel	a6baf4a4b5	revise kernel ... and add unused files	2024-08-07 16:51:24 -07:00
lllyasviel	a07c758658	intergrate k-diffusion	2024-08-07 15:05:42 -07:00
lllyasviel	14a759b5ca	revise kernel	2024-08-07 13:28:12 -07:00
layerdiffusion	0128ae6041	fix hr fix prompt	2024-08-06 20:36:33 -07:00
layerdiffusion	1be7f9ea6f	fix vae	2024-08-06 20:31:13 -07:00
layerdiffusion	b57573c8da	Implement many kernels from scratch	2024-08-06 20:19:03 -07:00
layerdiffusion	4c8331b806	Update launch_utils.py	2024-08-06 18:08:59 -07:00
lllyasviel	71c94799d1	diffusion in fp8 landed	2024-08-06 16:47:39 -07:00
layerdiffusion	5f908c2bf3	add forge opts section	2024-08-06 15:11:40 -07:00
layerdiffusion	fd283ce2de	remove unused	2024-08-06 14:45:08 -07:00
layerdiffusion	6d789653b9	better model load logic	2024-08-06 14:34:57 -07:00
layerdiffusion	c1b23bd494	rework and speed up model loading	2024-08-06 14:23:21 -07:00