280ed8f00f
Update sd_hijack_optimizations.py
2023-03-24 16:29:16 +04:00
c84c9df737
Update sd_hijack_optimizations.py
2023-03-21 14:50:22 +04:00
8d7fa2f67c
sdp_attnblock_forward hijack
2023-03-10 22:48:41 +05:00
37acba2633
argument to disable memory efficient for sdp
2023-03-10 12:19:36 +05:00
fec0a89511
scaled dot product attention
2023-03-07 00:33:13 +05:00
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
59146621e2
better support for xformers flash attention on older versions of torch
2023-01-23 16:40:20 +03:00
3262e825cc
add --xformers-flash-attention option & impl
2023-01-21 17:42:04 +09:00
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
c18add68ef
Added license
2023-01-06 16:42:47 -05:00
b95a4c0ce5
Change sub-quad chunk threshold to use percentage
2023-01-06 01:01:51 -05:00
d782a95967
Add Birch-san's sub-quadratic attention implementation
2023-01-06 00:14:13 -05:00
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
505ec7e4d9
cleanup some unneeded imports for hijack files
2022-12-10 09:17:39 +03:00
7dbfd8a7d8
do not replace entire unet for the resolution hack
2022-12-10 09:14:45 +03:00
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
2fd7935ef4
Remove wrong self reference in CUDA support for invokeai
2022-10-19 09:35:53 +03:00
c71008c741
Update sd_hijack_optimizations.py
2022-10-18 11:53:04 +03:00
84823275e8
readd xformers attnblock
2022-10-18 11:53:04 +03:00
2043c4a231
delete xformers attnblock
2022-10-18 11:53:04 +03:00
861db783c7
Use apply_hypernetwork function
2022-10-11 17:24:00 +03:00
574c8e554a
Add InvokeAI and lstein to credits, add back CUDA support
2022-10-11 17:24:00 +03:00
98fd5cde72
Add check for psutil
2022-10-11 17:24:00 +03:00
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
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
530103b586
fixes related to merge
2022-10-11 14:53:02 +03:00
948533950c
replace duplicate code with a function
2022-10-11 11:10:17 +03:00
3e7a981194
remove functorch
2022-10-10 19:54:07 +03:00
122d42687b
Fix VRAM Issue by only loading in hypernetwork when selected in settings
2022-10-09 11:08:11 +03:00
e6e42f98df
make --force-enable-xformers work without needing --xformers
2022-10-08 22:12:23 +03:00
f9c5da1592
add fallback for xformers_attnblock_forward
2022-10-08 19:05:19 +03:00
dc1117233e
simplify xfrmers options: --xformers to enable and that's it
2022-10-08 17:02:18 +03:00
7ff1170a2e
emergency fix for xformers (continue + shared)
2022-10-08 16:33:39 +03:00
48feae37ff
Merge pull request #1851 from C43H66N12O12S2/flash
...
xformers attention
2022-10-08 16:29:59 +03:00
69d0053583
update sd_hijack_opt to respect new env variables
2022-10-08 16:21:40 +03:00
76a616fa6b
Update sd_hijack_optimizations.py
2022-10-08 11:55:38 +03:00
5d54f35c58
add xformers attnblock and hypernetwork support
2022-10-08 11:55:02 +03:00
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
c9cc65b201
switch to the proper way of calling xformers
2022-10-08 04:09:18 +03:00
bad7cb29ce
added support for hypernetworks (???)
2022-10-07 10:17:52 +03:00
f174fb2922
add xformers attention
2022-10-07 05:21:49 +03:00
ad0cc85d1f
Merge branch 'master' into stable
2022-10-02 18:31:19 -03:00
820f1dc96b
initial support for training textual inversion
2022-10-02 15:03:39 +03:00
FNSpd