mirror of https://github.com/lllyasviel/stable-diffusion-webui-forge.git synced 2026-06-13 21:01:06 +08:00

History

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
..
diffusion_engine	add a way to save models	2024-08-19 06:30:49 -07:00
huggingface	upload Schnell support files	2024-08-11 17:31:12 -07:00
misc	Update sub_quadratic_attention.py	2024-08-03 15:19:45 -07:00
modules	multiple lora implementation sources	2024-08-13 07:13:32 -07:00
nn	fix for XPU (#1997 )	2024-10-06 14:33:47 +01:00
patcher	fix	2024-09-08 17:24:53 -07:00
sampling	Rephrase low GPU warning (#1761 )	2024-09-09 14:30:22 -03:00
text_processing	(T5) pad chunks to length of largest chunk (#1990 )	2024-10-07 11:37:06 +01:00
args.py	add low vram warning	2024-08-19 11:08:01 -07:00
attention.py	disable xformers for t5	2024-08-15 00:55:49 -07:00
loader.py	use safer codes	2024-08-31 10:55:19 -07:00
memory_management.py	move codes	2024-08-31 11:31:02 -07:00
operations_bnb.py	maintain loading related	2024-08-29 19:05:48 -07:00
operations_gguf.py	Speed up quant model loading and inference ...	2024-08-30 00:49:05 -07:00
operations.py	Maintain patching related	2024-08-30 15:18:21 -07:00
README.md	rename	2024-07-29 11:29:29 -06:00
shared.py	add a way to exchange variables between modules	2024-09-08 20:22:04 -07:00
state_dict.py	Load Model only when click Generate	2024-08-08 14:51:13 -07:00
stream.py	revise stream logics	2024-08-08 18:45:36 -07:00
utils.py	Maintain patching related	2024-08-30 15:18:21 -07:00

README.md

WIP Backend for Forge