18 Commits

Author	SHA1	Message	Date
layerdiffusion	a05a06b337	make results more consistent to A1111	2024-08-08 01:53:03 -07:00
layerdiffusion	e396307e9d	hard code clip token device ... #950	2024-08-08 01:36:01 -07:00
layerdiffusion	78c65708ea	fix t5	2024-08-07 21:55:00 -07:00
layerdiffusion	463cff0d89	fix t5	2024-08-07 21:10:23 -07:00
lllyasviel	14a759b5ca	revise kernel	2024-08-07 13:28:12 -07:00
layerdiffusion	64baac36b6	improve clip cast	2024-08-06 21:09:40 -07:00
layerdiffusion	0863765173	rework sd1.5 and sdxl from scratch	2024-08-05 03:08:17 -07:00
layerdiffusion	e28e11fa97	allow clip to skip TI	2024-08-04 19:28:53 -07:00
layerdiffusion	0d81ccb387	print to make sure that everything works well	2024-08-04 19:03:12 -07:00
layerdiffusion	9679232d29	fix TI embedding info text ... original webui is also broken but forge is fixed now	2024-08-04 18:49:35 -07:00
layerdiffusion	a72154405e	Text Processing Engine is Finished ... 100% reproduce all previous results, including TI embeddings, LoRAs in CLIP, emphasize settings, BREAK, timestep swap scheduling, AB mixture, advanced uncond, etc Backend is 85% finished	2024-08-04 18:42:51 -07:00
layerdiffusion	2791203d5b	move file	2024-08-04 13:49:58 -07:00
layerdiffusion	1e23bf07ca	add transformer encode	2024-08-04 13:45:32 -07:00
layerdiffusion	8c118df739	emphasis	2024-08-04 13:19:32 -07:00
layerdiffusion	cb9b155645	add embedding layer impl	2024-08-04 13:10:08 -07:00
layerdiffusion	21c8608373	Implement A1111 Text Processing from Scratch ... Thanks god	2024-08-04 12:43:31 -07:00
layerdiffusion	2e4adf19b6	Create emphasis.py	2024-08-04 12:21:57 -07:00
layerdiffusion	42ef31f106	textual inversion from scratch	2024-08-04 12:07:11 -07:00