aboutsummaryrefslogtreecommitdiffstats
path: root/modules
AgeCommit message (Collapse)AuthorLines
2023-11-29Fix the Ruff error about unused importhidenorly-1/+0
2023-11-29Add FP32 fallback support on torch.nn.functional.interpolatehidenorly-0/+16
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```
2023-11-29Revert "Add FP32 fallback support on sd_vae_approx"hidenorly-7/+1
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)
2023-11-21Add FP32 fallback support on sd_vae_approxhidenorly-1/+7
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.
2023-11-20Merge pull request #14009 from ↵AUTOMATIC1111-4/+21
AUTOMATIC1111/Option-to-show-batch-img2img-results-in-UI Option to show batch img2img results in UI
2023-11-20Merge branch 'dag' into devAUTOMATIC1111-153/+148
2023-11-20Merge pull request #13944 from wfjsw/dagAUTOMATIC1111-24/+188
implementing script metadata and DAG sorting mechanism
2023-11-20rework extensions metadata: use custom sorter that doesn't mess the order as ↵AUTOMATIC1111-153/+148
much and ignores cyclic errors, use classes with named fields instead of dictionaries, eliminate some duplicated code
2023-11-20save sysinfo as .jsonw-e-w-2/+2
GitHub now allows uploading of .json files in issues
2023-11-19Option to show batch img2img results in UIw-e-w-4/+21
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
2023-11-19use metadata.ini for meta filenamewfjsw-6/+6
2023-11-19Merge pull request #13931 from AUTOMATIC1111/style-hotkeysAUTOMATIC1111-2/+2
Enable prompt hotkeys in style editor
2023-11-19Merge pull request #13014 from ↵AUTOMATIC1111-6/+25
AUTOMATIC1111/thread-safe-extranetworks-list_items thread safe extra network list_items
2023-11-19Merge pull request #13968 from kaalibro/extranetworks-path-sortingAUTOMATIC1111-2/+3
Adds 'Path' sorting for Extra network cards
2023-11-19Merge pull request #13977 from AUTOMATIC1111/hotfix-postprocessing-state-endAUTOMATIC1111-1/+1
Hotfix: call shared.state.end() after postprocessing done
2023-11-19Merge pull request #13996 from Luxter77/patch-1AUTOMATIC1111-1/+26
Adds tqdm handler to logging_config.py for progress bar integration
2023-11-19Merge pull request #13826 from ezxzeng/ui_mobile_optimizationsAUTOMATIC1111-2/+13
added accordion settings options
2023-11-19Merge pull request #14004 from storyicon/masterAUTOMATIC1111-1/+1
feat: fix randn found element of type float at pos 2
2023-11-17feat: fix randn found element of type float at pos 2storyicon-1/+1
Signed-off-by: storyicon <storyicon@foxmail.com>
2023-11-16actually adds handler to logging_config.pyYour Name-1/+1
2023-11-16Take into account tqdm not being installed before first boot for loggingLucas Daniel Velazquez M-13/+24
2023-11-16Adds tqdm handler to logging_config.py for progress bar integrationLucas Daniel Velazquez M-0/+14
2023-11-15hotfix: call shared.state.end() after postprocessing doneAngelBottomless-1/+1
2023-11-13Adds 'Path' sorting for Extra network cardskaalibro-2/+3
2023-11-11bug fixwfjsw-7/+18
2023-11-11fixwfjsw-1/+0
2023-11-11allow comma and whitespace as separatorwfjsw-6/+9
2023-11-11remove the assumption of same namewfjsw-51/+30
2023-11-11reverse the extension load order so builtin extensions load earlier nativelywfjsw-1/+1
2023-11-11populate loaded_extensions from extension list insteadwfjsw-3/+2
2023-11-11implementing script metadata and DAG sorting mechanismwfjsw-24/+197
2023-11-10ExitStack as alternative to suppressEmily Zeng-3/+10
2023-11-11fix added accordion settings optionsw-e-w-5/+3
2023-11-09Enable prompt hotkeys in style editormissionfloyd-2/+2
2023-11-09multiline with statement for readibilityEmily Zeng-2/+6
2023-11-09removed changes that weren't merged properlyEmily Zeng-50/+1
2023-11-09moved nested with to single line to remove extra tabsEmily Zeng-296/+295
2023-11-07Merge branch 'dev' into ui_mobile_optimizationsezxzeng-187/+369
2023-11-07fix pix2pix producing bad resultsAUTOMATIC1111-1/+1
2023-11-07Add option to set notification sound volumeGerryDE-0/+1
2023-11-06fix exception related to the pix2pixAUTOMATIC1111-0/+4
2023-11-06fix img2img_tabs errorAUTOMATIC1111-10/+10
2023-11-05more changes for #13865: fix formatting, rename the function, add comment ↵AUTOMATIC1111-12/+14
and add a readme entry
2023-11-05linterAUTOMATIC1111-4/+4
2023-11-05Merge branch 'dev' into masterAUTOMATIC1111-390/+846
2023-11-05compact prompt option disabled by defaultAUTOMATIC1111-1/+1
2023-11-05added compact prompt optionAUTOMATIC1111-167/+257
2023-11-05Use devices.torch_gc() instead of empty_cache()Ritesh Gangnani-5/+1
2023-11-05Added memory clearance after deletionRitesh Gangnani-1/+5
2023-11-05Add SSD-1B as a supported modelRitesh Gangnani-3/+21
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-17 09:33:20 +0000