aboutsummaryrefslogtreecommitdiff
path: root/modules
AgeCommit message (Collapse)Author
2023-08-14make on_before_component/on_after_component possible earlierAUTOMATIC1111
2023-08-14repair DDIM/PLMS/UniPC batchesAUTOMATIC1111
2023-08-13also use setup callback for the refiner instead of before_processAUTOMATIC1111
2023-08-13Merge pull request #12526 from brkirch/mps-adjust-sub-quadAUTOMATIC1111
Fixes for `git checkout`, MPS/macOS fixes and optimizations
2023-08-13Merge pull request #12530 from eltociear/eltociear-patch-1AUTOMATIC1111
Fix typo in launch_utils.py
2023-08-13fix 2 for git code botched by previous PRsAUTOMATIC1111
2023-08-14Fix typo in launch_utils.pyIkko Eltociear Ashimine
existance -> existence
2023-08-13fix broken XYZ plot seedsAUTOMATIC1111
add new callback for scripts to be used before processing
2023-08-13Fix DDIM and PLMS samplers on MPSbrkirch
2023-08-13Remove duplicate code for torchsde randnbrkirch
2023-08-13Change the repositories origin URLs when necessarybrkirch
2023-08-13`git checkout` with commit hashbrkirch
2023-08-13`torch.empty` can create issues; use `torch.zeros`brkirch
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.
2023-08-13Make sub-quadratic the default for MPSbrkirch
2023-08-13Use fixed size for sub-quadratic chunking on MPSbrkirch
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.
2023-08-13fix for the broken run_git callsAUTOMATIC1111
2023-08-13Merge pull request #12510 from catboxanon/feat/extnet/hashesAUTOMATIC1111
Support search and display of hashes for all extra network items
2023-08-13Merge pull request #12515 from catboxanon/fix/gc1AUTOMATIC1111
Clear sampler and garbage collect before decoding images to reduce VRAM
2023-08-13Merge pull request #12514 from catboxanon/feat/batch-encodeAUTOMATIC1111
Encode batch items individually to significantly reduce VRAM
2023-08-13Merge pull request #12520 from catboxanon/etaAUTOMATIC1111
Update description of eta setting
2023-08-13Merge pull request #12521 from catboxanon/feat/more-s-noiseAUTOMATIC1111
Add `s_noise` param to more samplers
2023-08-13Restore extra_params that was lost in mergecatboxanon
2023-08-13Merge branch 'feat/dpmpp3msde' into feat/more-s-noisecatboxanon
2023-08-13Discard penultimate sigma for DPM-Solver++(3M) SDEcatboxanon
2023-08-13Fix s_noise descriptioncatboxanon
2023-08-13Add s_noise param to more samplerscatboxanon
2023-08-13Lora: output warnings in UI rather than fail for unfitting loras; switch to ↵AUTOMATIC1111
logging for error output in console
2023-08-13Update description of eta settingcatboxanon
2023-08-13Add DPM-Solver++(3M) SDEcatboxanon
2023-08-13Clear sampler before decoding imagescatboxanon
More significant VRAM reduction.
2023-08-13Encode batches separatelycatboxanon
Significantly reduces VRAM. This makes encoding more inline with how decoding currently functions.
2023-08-13Support search and display of hashes for all extra network itemscatboxanon
2023-08-13use dataclass for StableDiffusionProcessingAUTOMATIC1111
2023-08-13add refiner to StableDiffusionProcessing classAUTOMATIC1111
write out correct model name in infotext, rather than the refiner model
2023-08-12make "send to" buttons into small tool buttonsAUTOMATIC1111
2023-08-12fix broken reuse seedAUTOMATIC1111
2023-08-12update seed/subseed HTML widthsAUTOMATIC1111
2023-08-12move seed, variation seed and variation seed strength to a single row, dump ↵AUTOMATIC1111
resize seed from UI add a way for scripts to register a callback for before/after just a single component's creation
2023-08-12make it possible to use hires fix together with refinerAUTOMATIC1111
2023-08-12put refiner into main UI, into the new accordions sectionAUTOMATIC1111
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
2023-08-12Merge pull request #12480 from catboxanon/fix/ccAUTOMATIC1111
Fix color correction by converting image to RGB
2023-08-12Merge pull request #12479 from catboxanon/fix/extras-generatorAUTOMATIC1111
Refactor postprocessing/extras tab to use generator to resolve OOM issues
2023-08-12disable extensions installer with argw-e-w
2023-08-11Fix color correction by converting image to RGBcatboxanon
2023-08-11Refactor postprocessing to use generator to resolve OOM issuescatboxanon
2023-08-11Merge pull request #12470 from Splendide-Imaginarius/mask-blur-property+kernelAUTOMATIC1111
Make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur`
2023-08-10fix: Properly return None when VAE hash is Nonecatboxanon
2023-08-10Merge pull request #12456 from AUTOMATIC1111/patch-#12453AUTOMATIC1111
Patch #12453
2023-08-10use default value if value errorw-e-w
2023-08-10Merge pull request #12454 from wfjsw/no-autofix-on-fetchAUTOMATIC1111
rm dir on failed clone, disable autofix for fetch
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-28 08:39:11 +0000