d0e85873ac
check for OS and env variable
2022-10-08 16:13:26 +03:00
4201fd14f5
install xformers
2022-10-08 14:42:34 +03:00
f5490674a8
fix bad output for error when updating a git repo
2022-10-06 17:41:49 +03:00
a971e4a767
update k-diff once again
2022-10-06 13:42:21 +03:00
c30c06db20
update k-diffusion
2022-10-06 13:42:21 +03:00
6e7057b31b
support for downloading new commit hash for git repos
2022-10-06 12:08:58 +03:00
53a3dc601f
move CLIP out of requirements and into launcher to make it possible to launch the program offline
2022-10-02 18:21:56 +03:00
d1f098540a
remove unwanted formatting/functionality from the PR
2022-09-30 11:42:40 +03:00
d73741794d
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-29 19:59:36 -05:00
0dce0df1ee
Holy $hit.
...
Yep.
Fix gfpgan_model_arch requirement(s).
Add Upscaler base class, move from images.
Add a lot of methods to Upscaler.
Re-work all the child upscalers to be proper classes.
Add BSRGAN scaler.
Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff.
Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated.
Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size.
Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size.
Add typehints for IDE sanity.
PEP-8 improvements.
Moar.
2022-09-29 17:46:23 -05:00
dc1ee79e96
added --exit for notebooks
2022-09-29 18:33:29 +03:00
b6f80bdcc2
update k-diffusion
2022-09-29 13:52:51 +03:00
a703f56d73
clone k-diffusion instead of installing it via pip, and do not install its requirements.txt
2022-09-28 21:38:26 +03:00
d64b451681
added support for automatically installing latest k-diffusion
...
added eta parameter to parameters output for generated images
split eta settings into ancestral and ddim (because they have different default values)
2022-09-28 18:09:06 +03:00
5eb9d1aeac
change the version of k-diffusion. It still won't be installed unless you are installing from scratch, though.
2022-09-28 15:53:01 +03:00
b8bb14960a
Fix variable name typo in error message for launch.py
...
COMMANDINE_ARGS -> COMMANDLINE_ARGS
2022-09-27 17:47:07 +03:00
5a1951f175
Update launch.py
2022-09-21 16:50:30 +03:00
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling ( #763 )
...
* Add LDSR Upscaling
2022-09-21 16:06:37 +03:00
d6e8d85e30
removed TORCH_COMMAND section from webui.sh and
...
added correct torchvision version to default torch install command
2022-09-21 16:04:13 +03:00
45c46f4cb3
oops
2022-09-21 10:32:58 +03:00
a8ff013963
added --skip-torch-cuda-test to launcher for #746
2022-09-21 10:25:45 +03:00
c2775528c9
added __name__ == __main__ to launch.py so it can be imported without launching the webUI
2022-09-20 17:23:26 +03:00
918a092ed4
emergency fix for running in dir with spaces
2022-09-13 17:32:40 +03:00
33e6b6e9a6
moved most of functionality from webui.bat into cross-platform launch.py
...
moved stable diffusion dependencies into requirements.txt
added checkout with specific commit hashes to all external repos
2022-09-13 16:48:18 +03:00
C43H66N12O12S2