Commit Graph

43 Commits

Author SHA1 Message Date
FNSpd
280ed8f00f
Update sd_hijack_optimizations.py 2023-03-24 16:29:16 +04:00
FNSpd
c84c9df737
Update sd_hijack_optimizations.py 2023-03-21 14:50:22 +04:00
Pam
8d7fa2f67c sdp_attnblock_forward hijack 2023-03-10 22:48:41 +05:00
Pam
37acba2633 argument to disable memory efficient for sdp 2023-03-10 12:19:36 +05:00
Pam
fec0a89511 scaled dot product attention 2023-03-07 00:33:13 +05:00
brkirch
e3b53fd295 Add UI setting for upcasting attention to float32
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers.

In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
2023-01-25 01:13:04 -05:00
AUTOMATIC
59146621e2 better support for xformers flash attention on older versions of torch 2023-01-23 16:40:20 +03:00
Takuma Mori
3262e825cc add --xformers-flash-attention option & impl 2023-01-21 17:42:04 +09:00
AUTOMATIC
40ff6db532 extra networks UI
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-21 08:36:07 +03:00
brkirch
c18add68ef Added license 2023-01-06 16:42:47 -05:00
brkirch
b95a4c0ce5 Change sub-quad chunk threshold to use percentage 2023-01-06 01:01:51 -05:00
brkirch
d782a95967 Add Birch-san's sub-quadratic attention implementation 2023-01-06 00:14:13 -05:00
brkirch
35b1775b32 Use other MPS optimization for large q.shape[0] * q.shape[1]
Check if q.shape[0] * q.shape[1] is 2**18 or larger and use the lower memory usage MPS optimization if it is. This should prevent most crashes that were occurring at certain resolutions (e.g. 1024x1024, 2048x512, 512x2048).

Also included is a change to check slice_size and prevent it from being divisible by 4096 which also results in a crash. Otherwise a crash can occur at 1024x512 or 512x1024 resolution.
2022-12-20 21:30:00 -05:00
AUTOMATIC
505ec7e4d9 cleanup some unneeded imports for hijack files 2022-12-10 09:17:39 +03:00
AUTOMATIC
7dbfd8a7d8 do not replace entire unet for the resolution hack 2022-12-10 09:14:45 +03:00
Billy Cao
adb6cb7619 Patch UNet Forward to support resolutions that are not multiples of 64
Also modifed the UI to no longer step in 64
2022-11-23 18:11:24 +08:00
Cheka
2fd7935ef4 Remove wrong self reference in CUDA support for invokeai 2022-10-19 09:35:53 +03:00
C43H66N12O12S2
c71008c741 Update sd_hijack_optimizations.py 2022-10-18 11:53:04 +03:00
C43H66N12O12S2
84823275e8 readd xformers attnblock 2022-10-18 11:53:04 +03:00
C43H66N12O12S2
2043c4a231 delete xformers attnblock 2022-10-18 11:53:04 +03:00
brkirch
861db783c7 Use apply_hypernetwork function 2022-10-11 17:24:00 +03:00
brkirch
574c8e554a Add InvokeAI and lstein to credits, add back CUDA support 2022-10-11 17:24:00 +03:00
brkirch
98fd5cde72 Add check for psutil 2022-10-11 17:24:00 +03:00
brkirch
c0484f1b98 Add cross-attention optimization from InvokeAI
* Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS)
* Add command line option for it
* Make it default when CUDA is unavailable
2022-10-11 17:24:00 +03:00
AUTOMATIC
873efeed49 rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have 2022-10-11 15:51:30 +03:00
AUTOMATIC
530103b586 fixes related to merge 2022-10-11 14:53:02 +03:00
AUTOMATIC
948533950c replace duplicate code with a function 2022-10-11 11:10:17 +03:00
C43H66N12O12S2
3e7a981194 remove functorch 2022-10-10 19:54:07 +03:00
Fampai
122d42687b Fix VRAM Issue by only loading in hypernetwork when selected in settings 2022-10-09 11:08:11 +03:00
AUTOMATIC
e6e42f98df make --force-enable-xformers work without needing --xformers 2022-10-08 22:12:23 +03:00
AUTOMATIC
f9c5da1592 add fallback for xformers_attnblock_forward 2022-10-08 19:05:19 +03:00
AUTOMATIC
dc1117233e simplify xfrmers options: --xformers to enable and that's it 2022-10-08 17:02:18 +03:00
AUTOMATIC
7ff1170a2e emergency fix for xformers (continue + shared) 2022-10-08 16:33:39 +03:00
AUTOMATIC1111
48feae37ff
Merge pull request #1851 from C43H66N12O12S2/flash
xformers attention
2022-10-08 16:29:59 +03:00
C43H66N12O12S2
69d0053583
update sd_hijack_opt to respect new env variables 2022-10-08 16:21:40 +03:00
C43H66N12O12S2
76a616fa6b
Update sd_hijack_optimizations.py 2022-10-08 11:55:38 +03:00
C43H66N12O12S2
5d54f35c58
add xformers attnblock and hypernetwork support 2022-10-08 11:55:02 +03:00
brkirch
f2055cb1d4 Add hypernetwork support to split cross attention v1
* Add hypernetwork support to split_cross_attention_forward_v1
* Fix device check in esrgan_model.py to use devices.device_esrgan instead of shared.device
2022-10-08 09:39:17 +03:00
C43H66N12O12S2
c9cc65b201
switch to the proper way of calling xformers 2022-10-08 04:09:18 +03:00
AUTOMATIC
bad7cb29ce added support for hypernetworks (???) 2022-10-07 10:17:52 +03:00
C43H66N12O12S2
f174fb2922
add xformers attention 2022-10-07 05:21:49 +03:00
Jairo Correa
ad0cc85d1f Merge branch 'master' into stable 2022-10-02 18:31:19 -03:00
AUTOMATIC
820f1dc96b initial support for training textual inversion 2022-10-02 15:03:39 +03:00