12 Commits

Author	SHA1	Message	Date
Haoming	fce4a3c03a	lint	2025-10-18 15:33:27 +08:00
Haoming	91288c7e99	yeet	2025-09-10 16:43:28 +08:00
Haoming	00e4c496e7	T5	2025-09-09 16:20:29 +08:00
Haoming	56cb5d0b59	yeet	2025-09-09 14:16:30 +08:00
Haoming	355e7dfcc3	lint	2025-07-28 16:42:20 +08:00
DenOfEquity	2051c4100b	Apply emphasis mode changes immediately (#2423) ... Previously emphasis mode changes applied only on model load. Also added handling for mode 'None' (literal interpretation), which previously gave results identical to mode 'Ignore'.	2024-12-08 19:25:39 +00:00
DenOfEquity	cc378589a4	(T5) pad chunks to length of largest chunk (#1990) ... When the prompt is chunked using the BREAK keyword, chunks will be padded to the minimum size of 256 tokens - but chunks can be longer. torch.stack then fails if all chunks are not the same size, so find the largest and pad all to match. #1988 (doesn't quite ID the real issue, prompts longer than 255 tokens work fine)	2024-10-07 11:37:06 +01:00
lllyasviel	cfa5242a75	forge 2.0.0 ... see also discussions	2024-08-10 19:24:19 -07:00
layerdiffusion	a05a06b337	make results more consistent to A1111	2024-08-08 01:53:03 -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