aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
* make on_before_component/on_after_component possible earlierAUTOMATIC11112023-08-141-10/+25
|
* repair DDIM/PLMS/UniPC batchesAUTOMATIC11112023-08-142-11/+12
|
* also use setup callback for the refiner instead of before_processAUTOMATIC11112023-08-131-1/+1
|
* Merge pull request #12526 from brkirch/mps-adjust-sub-quadAUTOMATIC11112023-08-135-10/+17
|\ | | | | Fixes for `git checkout`, MPS/macOS fixes and optimizations
| * Fix DDIM and PLMS samplers on MPSbrkirch2023-08-131-2/+2
| |
| * Remove duplicate code for torchsde randnbrkirch2023-08-131-3/+0
| |
| * Change the repositories origin URLs when necessarybrkirch2023-08-131-0/+3
| |
| * `git checkout` with commit hashbrkirch2023-08-131-1/+1
| |
| * `torch.empty` can create issues; use `torch.zeros`brkirch2023-08-131-2/+2
| | | | | | | | For MPS, using a tensor created with `torch.empty()` can cause `torch.baddbmm()` to include NaNs in the tensor it returns, even though `beta=0`. However, with a tensor of shape [1,1,1], there should be a negligible performance difference between `torch.empty()` and `torch.zeros()` anyway, so it's better to just use `torch.zeros()` for this and avoid unnecessarily creating issues.
| * Make sub-quadratic the default for MPSbrkirch2023-08-131-2/+5
| |
| * Use fixed size for sub-quadratic chunking on MPSbrkirch2023-08-131-1/+5
| | | | | | | | Even if this causes chunks to be much smaller, performance isn't significantly impacted. This will usually reduce memory usage but should also help with poor performance when free memory is low.
* | Merge pull request #12530 from eltociear/eltociear-patch-1AUTOMATIC11112023-08-131-1/+1
|\ \ | | | | | | Fix typo in launch_utils.py
| * | Fix typo in launch_utils.pyIkko Eltociear Ashimine2023-08-131-1/+1
| | | | | | | | | existance -> existence
* | | fix 2 for git code botched by previous PRsAUTOMATIC11112023-08-131-1/+1
| | |
* | | fix broken XYZ plot seedsAUTOMATIC11112023-08-133-4/+47
| |/ |/| | | | | add new callback for scripts to be used before processing
* | fix for the broken run_git callsAUTOMATIC11112023-08-131-2/+2
| |
* | Merge pull request #12510 from catboxanon/feat/extnet/hashesAUTOMATIC11112023-08-134-3/+11
|\ \ | | | | | | Support search and display of hashes for all extra network items
| * | Support search and display of hashes for all extra network itemscatboxanon2023-08-134-3/+11
| | |
* | | Merge pull request #12515 from catboxanon/fix/gc1AUTOMATIC11112023-08-131-0/+3
|\ \ \ | | | | | | | | Clear sampler and garbage collect before decoding images to reduce VRAM
| * | | Clear sampler before decoding imagescatboxanon2023-08-131-0/+3
| |/ / | | | | | | | | | More significant VRAM reduction.
* | | Merge pull request #12514 from catboxanon/feat/batch-encodeAUTOMATIC11112023-08-131-1/+9
|\ \ \ | | | | | | | | Encode batch items individually to significantly reduce VRAM
| * | | Encode batches separatelycatboxanon2023-08-131-1/+9
| |/ / | | | | | | | | | | | | Significantly reduces VRAM. This makes encoding more inline with how decoding currently functions.
* | | Merge pull request #12520 from catboxanon/etaAUTOMATIC11112023-08-131-1/+1
|\ \ \ | | | | | | | | Update description of eta setting
| * | | Update description of eta settingcatboxanon2023-08-131-1/+1
| |/ /
* | | Merge pull request #12521 from catboxanon/feat/more-s-noiseAUTOMATIC11112023-08-134-6/+15
|\ \ \ | | | | | | | | Add `s_noise` param to more samplers
| * \ \ Merge branch 'feat/dpmpp3msde' into feat/more-s-noisecatboxanon2023-08-131-3/+3
| |\ \ \
| | * | | Discard penultimate sigma for DPM-Solver++(3M) SDEcatboxanon2023-08-131-3/+3
| | | | |
| * | | | Fix s_noise descriptioncatboxanon2023-08-131-1/+1
| | | | |
| * | | | Add s_noise param to more samplerscatboxanon2023-08-132-4/+10
| |/ / /
| * / / Add DPM-Solver++(3M) SDEcatboxanon2023-08-132-1/+4
| |/ /
* | | Restore extra_params that was lost in mergecatboxanon2023-08-131-0/+2
| | |
* | | Lora: output warnings in UI rather than fail for unfitting loras; switch to ↵AUTOMATIC11112023-08-131-5/+8
|/ / | | | | | | logging for error output in console
* | use dataclass for StableDiffusionProcessingAUTOMATIC11112023-08-132-147/+176
| |
* | add refiner to StableDiffusionProcessing classAUTOMATIC11112023-08-133-20/+36
| | | | | | | | write out correct model name in infotext, rather than the refiner model
* | make "send to" buttons into small tool buttonsAUTOMATIC11112023-08-121-5/+9
| |
* | fix broken reuse seedAUTOMATIC11112023-08-122-19/+25
| |
* | update seed/subseed HTML widthsAUTOMATIC11112023-08-121-10/+15
| |
* | move seed, variation seed and variation seed strength to a single row, dump ↵AUTOMATIC11112023-08-126-124/+184
| | | | | | | | | | | | resize seed from UI add a way for scripts to register a callback for before/after just a single component's creation
* | make it possible to use hires fix together with refinerAUTOMATIC11112023-08-123-1/+10
| |
* | put refiner into main UI, into the new accordions sectionAUTOMATIC11112023-08-1211-67/+168
| | | | | | | | | | | | add VAE from main model into infotext, not from refiner model option to make scripts UI without gr.Group fix inconsistencies with refiner when usings samplers that do more denoising than steps
* | Merge pull request #12480 from catboxanon/fix/ccAUTOMATIC11112023-08-121-1/+1
|\ \ | | | | | | Fix color correction by converting image to RGB
| * | Fix color correction by converting image to RGBcatboxanon2023-08-111-1/+1
| | |
* | | Merge pull request #12479 from catboxanon/fix/extras-generatorAUTOMATIC11112023-08-121-32/+31
|\ \ \ | | | | | | | | Refactor postprocessing/extras tab to use generator to resolve OOM issues
| * | | Refactor postprocessing to use generator to resolve OOM issuescatboxanon2023-08-111-32/+31
| |/ /
* / / disable extensions installer with argw-e-w2023-08-121-1/+1
|/ /
* | Merge pull request #12470 from Splendide-Imaginarius/mask-blur-property+kernelAUTOMATIC11112023-08-111-5/+20
|\ \ | | | | | | Make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur`
| * | Reduce mask blur kernel size to 2.5 sigmasSplendide Imaginarius2023-08-051-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | This more closely matches the old behavior of PIL's Gaussian blur, and fixes breakage when tiling. See https://github.com/Coyote-A/ultimate-upscale-for-automatic1111/issues/111#issuecomment-1663504109 Thanks to Алексей Трофимов and eunnone for reporting the issue.
| * | Make StableDiffusionProcessingImg2Img.mask_blur a propertySplendide Imaginarius2023-08-031-3/+18
| | | | | | | | | | | | | | | | | | | | | | | | Fixes breakage when mask_blur is set after construction. See https://github.com/Coyote-A/ultimate-upscale-for-automatic1111/issues/111#issuecomment-1652091424 Thanks to Алексей Трофимов and eunnone for reporting the issue.
* | | fix: Properly return None when VAE hash is Nonecatboxanon2023-08-101-1/+3
| | |
* | | Merge pull request #12456 from AUTOMATIC1111/patch-#12453AUTOMATIC11112023-08-101-2/+2
|\ \ \ | | | | | | | | Patch #12453
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-04 23:47:43 +0000