Commit Graph

6888 Commits

Author SHA1 Message Date
catboxanon
83e8c32276 Fix save_samples being checked early when saving masked composite 2023-12-02 13:30:53 -05:00
drhead
81c4ddf6eb
fix linting 2023-12-02 13:11:00 -05:00
drhead
309a606c2f
ensure that original alpha bar always exists 2023-12-02 13:07:45 -05:00
AUTOMATIC1111
ac02216e54 alternate implementation for unet forward replacement that does not depend on hijack being applied 2023-12-02 19:35:47 +03:00
AUTOMATIC1111
af5f0734c9
Merge pull request #14171 from Nuullll/ipex
Initial IPEX support for Intel Arc GPU
2023-12-02 19:22:32 +03:00
AUTOMATIC1111
a5f61aa8c5 potential fix for #14172 2023-12-02 18:03:34 +03:00
AUTOMATIC1111
11d23e8ca5 remove Train/Preprocessing tab and put all its functionality into extras batch images mode 2023-12-02 18:01:11 +03:00
Kohaku-Blueleaf
50a21cb09f Ensure the cached weight will not be affected 2023-12-02 22:06:47 +08:00
Nuullll
96871e4f74 Remove webui-ipex-user.bat 2023-12-02 17:11:31 +08:00
AUTOMATIC1111
4a666381bf extras tab batch: actually use original filename
preprocessing upscale: do not do an extra upscale step if it's not needed
2023-12-02 12:11:21 +03:00
Kohaku-Blueleaf
110485d5bb Merge branch 'dev' into test-fp8 2023-12-02 17:00:09 +08:00
Nuullll
87cd07b3af Fix fp64 2023-12-02 15:54:25 +08:00
AUTOMATIC1111
0bb6e00ba3
Merge pull request #13957 from h43lb1t0/extra_network_subdirs
dir buttons start with / so only the correct dir will be shown and no…
2023-12-02 09:59:29 +03:00
AUTOMATIC1111
87d973e389
Merge pull request #14063 from wfjsw/use-ext-name-for-installed
use extension name for determining an extension is installed in the index
2023-12-02 09:58:44 +03:00
AUTOMATIC1111
ef6b8123dc put code that can cause an exception into its own function for #14120 2023-12-02 09:57:39 +03:00
AUTOMATIC1111
5ed7daa3d9
Merge pull request #14120 from AUTOMATIC1111/protect-against-bad-ui-creation-scripts
catch uncaught exception with ui creation scripts
2023-12-02 09:54:21 +03:00
AUTOMATIC1111
ef1723ef41
Merge pull request #14125 from cjj1977/dev
Allow use of mutiple styles csv files
2023-12-02 09:53:27 +03:00
AUTOMATIC1111
7547d7c791
Merge pull request #14126 from aria1th/hypertile-xyz
Support XYZ scripts / split hires path from unet
2023-12-02 09:48:40 +03:00
AUTOMATIC1111
88736b5557
Merge pull request #14131 from read-0nly/patch-1
Update devices.py - Make 'use-cpu all' actually apply to 'all'
2023-12-02 09:46:19 +03:00
AUTOMATIC1111
9eadc4f146
Merge pull request #14121 from AUTOMATIC1111/fix-Auto-focal-point-crop-for-opencv-4.8.x
Fix auto focal point crop for opencv >= 4.8
2023-12-02 09:46:00 +03:00
AUTOMATIC1111
97c8e7e0c7
Merge pull request #14119 from AUTOMATIC1111/add-Block-component-creation-callback
add Block component creation callback
2023-12-02 09:45:03 +03:00
AUTOMATIC1111
e12a26c253
Merge pull request #14046 from hidenorly/AddFP32FallbackSupportOnSdVaeApprox
Add FP32 fallback support on sd_vae_approx
2023-12-02 09:44:00 +03:00
AUTOMATIC1111
600036d158
Merge pull request #14156 from AUTOMATIC1111/metadata-pop-up-size-limit
fix not able to exit metadata popup when pop up is too big
2023-12-02 09:30:27 +03:00
AUTOMATIC1111
4125552752
Merge pull request #14170 from MrCheeze/sd-turbo
Add support for SD 2.1 Turbo
2023-12-02 09:30:07 +03:00
AUTOMATIC1111
e294e46d46 split UI settings page into many 2023-12-02 09:26:38 +03:00
Nuullll
7499148ad4 Disable ipex autocast due to its bad perf 2023-12-02 14:00:46 +08:00
AUTOMATIC1111
b58d061e41 infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page 2023-12-02 08:33:28 +03:00
MrCheeze
6080045b2a Add support for SD 2.1 Turbo, by converting the state dict from SGM to LDM on load 2023-12-01 22:58:05 -05:00
MrCheeze
293f44e6c1 Fix bug where is_using_v_parameterization_for_sd2 fails because the sd_hijack is only partially undone 2023-12-01 22:56:08 -05:00
missionfloyd
01c8f1803a
Close popups with escape key 2023-11-30 22:36:12 -07:00
w-e-w
c2ed413203 add max-heigh/width to global-popup-inner
prevent the pop-up from being too big as to making exiting the pop-up impossible
2023-12-01 02:59:41 +09:00
Nuullll
8b40f475a3 Initial IPEX support 2023-11-30 20:22:46 +08:00
drhead
668ae34e21
remove debug print 2023-11-29 22:48:31 -05:00
catboxanon
de79597ab9 Only apply ztSNR related code if alphas_cumprod exists 2023-11-29 18:33:32 -05:00
catboxanon
ffa7f8201d Lint 2023-11-29 18:10:43 -05:00
catboxanon
ec6ee5c13b Fix infotext for ztSNR 2023-11-29 18:10:27 -05:00
drhead
6d0a8dcd89
Implement zero terminal SNR schedule option 2023-11-29 17:42:07 -05:00
drhead
588a52891d
Add options for zero terminal SNR 2023-11-29 17:40:23 -05:00
drhead
b25c126ccd
Protect alphas_cumprod from downcasting 2023-11-29 17:38:53 -05:00
CodeHatchling
c7a1ff8720 Tweaked default values. 2023-11-28 23:31:10 -07:00
CodeHatchling
284fd8f415 Tweaked UI sliders and labels. 2023-11-28 23:03:50 -07:00
CodeHatchling
c5c7fa06aa Added slider for detail preservation strength, removed largely needless offset parameter, changed labels in UI and for saving to/pasting data from PNG files. 2023-11-28 22:35:07 -07:00
CodeHatchling
debf836fcc Added UI elements to control blending parameters. 2023-11-28 16:15:36 -07:00
CodeHatchling
a6e5846453 Nerfs the aggressive post-processing step of overlaying the original image. 2023-11-28 16:13:42 -07:00
CodeHatchling
e715e46b6a Implements "scheduling" for blending of the original latents and a latent blending formula that preserves details in blend transition areas. 2023-11-28 16:10:22 -07:00
CodeHatchling
bbba133f05 Removed conflicting step that replaces the softly inpainted latents with a naive blend with the original latents. 2023-11-28 15:09:43 -07:00
CodeHatchling
dec791d35d Removed code which forces the inpainting mask to be 0 or 1. Now fractional values (e.g. 0.5) are accepted. 2023-11-28 15:05:01 -07:00
hidenorly
81c00728b8 Fix the Ruff error about unused import 2023-11-29 04:59:35 +09:00
hidenorly
a0096c5897 Add FP32 fallback support on torch.nn.functional.interpolate
This tries to execute interpolate with FP32 if it failed.

Background is that
on some environment such as Mx chip MacOS devices, we get error as follows:

```
"torch/nn/functional.py", line 3931, in interpolate
        return torch._C._nn.upsample_nearest2d(input, output_size, scale_factors)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half'
```

In this case, ```--no-half``` doesn't help to solve. Therefore this commits add the FP32 fallback execution to solve it.

Note that the ```upsample_nearest2d``` is called from ```torch.nn.functional.interpolate```.
And the fallback for torch.nn.functional.interpolate is necessary at
```modules/sd_vae_approx.py``` 's ```VAEApprox.forward```
```repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py``` 's ```Upsample.forward```
2023-11-29 04:45:04 +09:00
hidenorly
39eae9f009 Revert "Add FP32 fallback support on sd_vae_approx"
This reverts commit 58c19545c8.
Since the modification is expected to move to mac_specific.py
(https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046#issuecomment-1826731532)
2023-11-29 04:07:48 +09:00