f8884bc051
fix hip detection
2023-05-25 09:13:57 -04:00
9e66d88e21
add mps defaults
2023-05-24 15:21:49 -04:00
684851ae34
set default optimizer
2023-05-24 13:50:01 -04:00
0acc7d3b86
fix redirector
2023-05-24 08:49:33 -04:00
ea0780339a
fixes
2023-05-21 08:17:36 -04:00
9033499e08
add manual seed
2023-05-19 08:34:43 -04:00
0ccda9bc8b
jumbo patch
2023-05-17 14:15:55 -04:00
5250ba4be3
force no-half with directml
2023-05-16 21:20:36 -04:00
8350b93a5c
add force latent sampler
2023-05-15 09:32:20 -04:00
5134471bc8
dml autocast
2023-05-14 13:24:59 -04:00
618a1703ae
update cudnn benchmark setting
2023-05-14 12:28:37 -04:00
760f5fb89a
add extra debug messages
2023-05-14 12:26:15 -04:00
a652270999
fix
2023-05-13 12:26:00 -04:00
a2923064a5
update cudnn
2023-05-13 11:52:31 -04:00
d96ab6a1ae
update directml
2023-05-13 11:21:11 -04:00
a2485cf7ef
update
2023-05-12 21:12:24 -04:00
1921504e64
enable dynamo compile
2023-05-12 15:58:00 -04:00
daf90cb6b4
add performance note
2023-05-12 14:23:51 -04:00
62dda471a3
process images in threads
2023-05-12 14:21:26 -04:00
1943bfea88
use cudnn workaround
2023-05-11 22:24:12 -04:00
e038bf1549
aggressive gc
2023-05-10 16:03:55 -04:00
41182009cb
switch some cmdopts to opts
2023-05-08 09:27:50 -04:00
1360c6422a
add fp16 test
2023-05-08 09:27:50 -04:00
8171d57c36
Remove unnecessary IPEX imports
2023-05-04 02:34:34 +03:00
5d8c787a7b
restart server redesign
2023-05-03 17:20:22 -04:00
53f3567224
Use cmd_args parser instead of launch.py
2023-05-03 21:25:23 +03:00
7577a09528
Add IPEX Optimizers and use XPU instead of CPU when using IPEX
2023-05-03 18:12:38 +03:00
de8d0bef9f
More patches and Import IPEX after Torch
2023-04-30 18:19:37 +03:00
a720a670e8
More patches and less import shared
2023-04-30 16:01:17 +03:00
b075d3c8fd
Intel ARC Support
2023-04-30 15:13:56 +03:00
d2d5011bd3
Implement memory estimation for AMDGPUs.
...
Stable.
2023-04-26 17:44:32 +09:00
a49a8f8b46
First DirectML implementation.
...
Unstable and not tested.
2023-04-25 01:43:19 +09:00
61e9a1970c
add exception around torch properties
2023-04-22 08:35:17 -04:00
cf277e7326
fix dtype logic
2023-04-21 15:04:05 -04:00
57204b3d70
disable xformers/sdp if cannot be used
2023-04-21 11:32:19 -04:00
7939a1649d
parse model preload
2023-04-20 23:19:25 -04:00
0e7144186d
jump patch
2023-04-20 11:20:27 -04:00
e14cba0771
add lycoris folder
2023-04-15 12:25:59 -04:00
81b8294e93
switch cmdflags to settings
2023-04-12 10:40:11 -04:00
1b8af15f13
Refactor Mac specific code to a separate file
...
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.
2023-02-01 14:05:56 -05:00
2217331cd1
Refactor MPS fixes to CondFunc
2023-02-01 06:36:22 -05:00
7738c057ce
MPS fix is still needed :(
...
Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS
2023-02-01 05:23:58 -05:00
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings
...
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28 18:44:36 +03:00
f9edd578e9
Remove MPS fix no longer needed for PyTorch
...
The torch.narrow fix was required for nightly PyTorch builds for a while to prevent a hard crash, but newer nightly builds don't have this issue.
2023-01-28 04:16:27 -05:00
ada17dbd7c
Refactor conditional casting, fix upscalers
2023-01-28 04:16:25 -05:00
9beb794e0b
clarify the option to disable NaN check.
2023-01-27 13:08:00 +03:00
d2ac95fa7b
remove the need to place configs near models
2023-01-27 11:28:12 +03:00
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
84d9ce30cb
Add option for float32 sampling with float16 UNet
...
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half().
2023-01-25 01:13:02 -05:00
aa60fc6660
Merge pull request #6922 from brkirch/cumsum-fix
...
Improve cumsum fix for MPS
2023-01-19 13:18:34 +03:00
Vladimir Mandic
Disty0
Seunghoon Lee
brkirch
AUTOMATIC1111