Commit Graph

24 Commits

Author SHA1 Message Date
comfyanonymous
c60864b5e4 Refactor the attention functions.
There's no reason for the whole CrossAttention object to be repeated when
only the operation in the middle changes.
2023-10-11 20:38:48 -04:00
comfyanonymous
ef0c0892f6 Add a force argument to soft_empty_cache to force a cache empty. 2023-09-04 00:58:18 -04:00
comfyanonymous
2ab478346d Remove optimization that caused border. 2023-08-29 11:21:36 -04:00
comfyanonymous
6932eda1fb Fallback to slice attention if xformers doesn't support the operation. 2023-08-27 22:24:42 -04:00
comfyanonymous
1b9a6a9599 Make --bf16-vae work on torch 2.0 2023-08-27 21:33:53 -04:00
comfyanonymous
71ffc7b350 Faster VAE loading. 2023-07-29 16:28:30 -04:00
comfyanonymous
51da619d73 Remove useless code. 2023-06-23 12:35:26 -04:00
comfyanonymous
c0a5444d1b Make scaled_dot_product switch to sliced attention on OOM. 2023-05-20 16:01:02 -04:00
comfyanonymous
e33cb62d1b Simplify and improve some vae attention code. 2023-05-20 15:07:21 -04:00
comfyanonymous
2edaaba3c2 Fix imports. 2023-05-04 18:10:29 -04:00
comfyanonymous
4df70d0f62 Fix model_management import so it doesn't get executed twice. 2023-04-15 19:04:33 -04:00
comfyanonymous
7597a5d83e Disable xformers in VAE when xformers == 0.0.18 2023-04-04 22:22:02 -04:00
comfyanonymous
7cae5f5769 Try again with vae tiled decoding if regular fails because of OOM. 2023-03-22 14:49:00 -04:00
comfyanonymous
13ec5cd3c2 Try to improve VAEEncode memory usage a bit. 2023-03-22 02:45:18 -04:00
comfyanonymous
1de721b33c Add pytorch attention support to VAE. 2023-03-13 12:45:54 -04:00
comfyanonymous
72b42ab260 --disable-xformers should not even try to import xformers. 2023-03-13 11:36:48 -04:00
comfyanonymous
7c95e1a03b Xformers is now properly disabled when --cpu used.
Added --windows-standalone-build option, currently it only opens
makes the code open up comfyui in the browser.
2023-03-12 15:44:16 -04:00
comfyanonymous
bbdc5924b4 Try to fix memory issue. 2023-03-11 15:15:13 -05:00
comfyanonymous
f8f2ea3bb1 Make VAE use common function to get free memory. 2023-03-05 14:20:07 -05:00
comfyanonymous
509c7dfc6d Use real softmax in split op to fix issue with some images. 2023-02-10 03:13:49 -05:00
comfyanonymous
773cdabfce Same thing but for the other places where it's used. 2023-02-09 12:43:29 -05:00
comfyanonymous
e8c499ddd4 Split optimization for VAE attention block. 2023-02-08 22:04:20 -05:00
comfyanonymous
5b4e312749 Use inplace operations for less OOM issues. 2023-02-08 22:04:13 -05:00
comfyanonymous
220afe3310 Initial commit. 2023-01-16 22:37:14 -05:00