| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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)
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
| | |
| |
| |
| |
| |
| |
| |
| | |
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
|
| |\ \ |
|
| | | |
| | |
| | |
| | | |
much and ignores cyclic errors, use classes with named fields instead of dictionaries, eliminate some duplicated code
|
| |\| |
| | |
| | | |
implementing script metadata and DAG sorting mechanism
|
| | | | |
|
| | | | |
|
| | | | |
|
| | | | |
|
| | | | |
|
| | | | |
|
| | | | |
|
| | |/ |
|
| |\ \
| | |
| | | |
save sysinfo as .json
|
| |/ /
| |
| |
| | |
GitHub now allows uploading of .json files in issues
|
| |\ \
| | |
| | | |
Enable prompt hotkeys in style editor
|
| | | | |
|
| |\ \ \
| | | |
| | | |
| | | |
| | | | |
AUTOMATIC1111/thread-safe-extranetworks-list_items
thread safe extra network list_items
|
| | | | | |
|
| | | | | |
|
| | | | | |
|
| | | | |
| | | |
| | | |
| | | | |
This reverts commit aab385d01b4311726127397552d791f4d71b7147.
|
| | | | | |
|
| |\ \ \ \
| | | | |
| | | | | |
Fix dependency address patch 1
|
| | | | | |
| | | | |
| | | | | |
Modify the stablediffusion dependency address
|
| | | |/ /
| |/| |
| | | | |
Modify the stablediffusion dependency address
|
| |\ \ \ \
| | | | |
| | | | | |
Fixes generation restart not working for some users when 'Ctrl+Enter' is pressed
|
| | | |_|/
| |/| | |
|
| |\ \ \ \
| | | | |
| | | | | |
Adds 'Path' sorting for Extra network cards
|
| | |/ / / |
|
| |\ \ \ \
| | | | |
| | | | | |
Hotfix: call shared.state.end() after postprocessing done
|
| | |/ / / |
|
| |\ \ \ \
| | | | |
| | | | | |
Support inference with OFT networks
|
| | | | | | |
|
| | | | | | |
|
| | |\ \ \ \
| | | | | |
| | | | | | |
Use same updown implementation for LyCORIS OFT as kohya-ss OFT
|
| | | | | | | |
|
| | |/ / / / |
|
| | |\ \ \ \
| | | | | |
| | | | | |
| | | | | |
| | | | | | |
Support LyCORIS diag-oft OFT implementation (minus MultiheadAttention layer), maintains support for kohya-ss OFT
|
| | | | | | |
| | | | | |
| | | | | |
| | | | | | |
and kb
|
| | | | | | | |
|
| | | | | | |
| | | | | |
| | | | | |
| | | | | | |
diag_oft has MultiheadAttn which kohya's doesn't?, attempt create new module based off network_lora.py, errors about tensor dim mismatch
|
| | | | | | | |
|
| | |/ / / / |
|
| | | | | | |
|
| | | | | | |
|
