| Age | Commit message (Collapse) | Author |
|---|
|
preprocessing upscale: do not do an extra upscale step if it's not needed
|
|
dir buttons start with / so only the correct dir will be shown and no…
|
|
use extension name for determining an extension is installed in the index
|
|
|
|
AUTOMATIC1111/protect-against-bad-ui-creation-scripts
catch uncaught exception with ui creation scripts
|
|
Allow use of mutiple styles csv files
|
|
Update devices.py - Make 'use-cpu all' actually apply to 'all'
|
|
AUTOMATIC1111/fix-Auto-focal-point-crop-for-opencv-4.8.x
Fix auto focal point crop for opencv >= 4.8
|
|
AUTOMATIC1111/add-Block-component-creation-callback
add Block component creation callback
|
|
Add FP32 fallback support on sd_vae_approx
|
|
Add support for SD 2.1 Turbo
|
|
|
|
option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page
|
|
on load
|
|
sd_hijack is only partially undone
|
|
|
|
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```
|
|
This reverts commit 58c19545c83fa6925c9ce2216ee64964eb5129ce.
Since the modification is expected to move to mac_specific.py
(https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046#issuecomment-1826731532)
|
|
|
|
autocrop.download_and_cache_models
in opencv >= 4.8 the face detection model was updated
download the base on opencv version
returns the model path or raise exception
|
|
fixes issue where "--use-cpu" all properly makes SD run on CPU but leaves ControlNet (and other extensions, I presume) pointed at GPU, causing a crash in ControlNet caused by a mismatch between devices between SD and CN
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14097
|
|
* https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14122
Fix edge case where style text has multiple {prompt} placeholders
* https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14005
|
|
prevent total webui crash
|
|
|
|
|
|
|
|
improve json readability
|
|
|
|
Update Ruff to 0.1.6
|
|
|
|
Move exception_records related methods to errors.py
|
|
|
|
support HyperTile optimization
|
|
|
|
|
|
|
|
|
|
|
|
|
|
prevents start #14047
|
|
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 submodule may require additional modifications. The following is the example modification on the other submodule.
```repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py
class Upsample(nn.Module):
..snip..
def forward(self, x):
assert x.shape[1] == self.channels
if self.dims == 3:
x = F.interpolate(
x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest"
)
else:
try:
x = F.interpolate(x, scale_factor=2, mode="nearest")
except:
x = F.interpolate(x.to(th.float32), scale_factor=2, mode="nearest").to(x.dtype)
if self.use_conv:
x = self.conv(x)
return x
..snip..
```
You can see the FP32 fallback execution as same as sd_vae_approx.py.
|
|
|
|
AUTOMATIC1111/Option-to-show-batch-img2img-results-in-UI
Option to show batch img2img results in UI
|
|
|
|
implementing script metadata and DAG sorting mechanism
|
|
much and ignores cyclic errors, use classes with named fields instead of dictionaries, eliminate some duplicated code
|
|
GitHub now allows uploading of .json files in issues
|
|
shared.opts.img2img_batch_show_results_limit
limit the number of images return to the UI for batch img2img
default limit 32
0 no images are shown
-1 unlimited, all images are shown
|
|
|
|
Enable prompt hotkeys in style editor
|
