aboutsummaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorLines
2023-08-14make on_before_component/on_after_component possible earlierAUTOMATIC1111-10/+25
2023-08-14repair DDIM/PLMS/UniPC batchesAUTOMATIC1111-11/+12
2023-08-13also use setup callback for the refiner instead of before_processAUTOMATIC1111-1/+1
2023-08-13Merge pull request #12526 from brkirch/mps-adjust-sub-quadAUTOMATIC1111-12/+17
Fixes for `git checkout`, MPS/macOS fixes and optimizations
2023-08-13Merge pull request #12530 from eltociear/eltociear-patch-1AUTOMATIC1111-1/+1
Fix typo in launch_utils.py
2023-08-13fix 2 for git code botched by previous PRsAUTOMATIC1111-1/+1
2023-08-14Fix typo in launch_utils.pyIkko Eltociear Ashimine-1/+1
existance -> existence
2023-08-13fix broken XYZ plot seedsAUTOMATIC1111-4/+47
add new callback for scripts to be used before processing
2023-08-13Fix DDIM and PLMS samplers on MPSbrkirch-2/+2
2023-08-13Remove duplicate code for torchsde randnbrkirch-3/+0
2023-08-13Mac k-diffusion workarounds are no longer neededbrkirch-2/+0
2023-08-13Change the repositories origin URLs when necessarybrkirch-0/+3
2023-08-13`git checkout` with commit hashbrkirch-1/+1
2023-08-13`torch.empty` can create issues; use `torch.zeros`brkirch-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.
2023-08-13Make sub-quadratic the default for MPSbrkirch-2/+5
2023-08-13Use fixed size for sub-quadratic chunking on MPSbrkirch-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.
2023-08-13fix for the broken run_git callsAUTOMATIC1111-2/+2
2023-08-13Merge pull request #12510 from catboxanon/feat/extnet/hashesAUTOMATIC1111-4/+13
Support search and display of hashes for all extra network items
2023-08-13Merge pull request #12515 from catboxanon/fix/gc1AUTOMATIC1111-0/+3
Clear sampler and garbage collect before decoding images to reduce VRAM
2023-08-13Merge pull request #12514 from catboxanon/feat/batch-encodeAUTOMATIC1111-1/+9
Encode batch items individually to significantly reduce VRAM
2023-08-13Merge pull request #12520 from catboxanon/etaAUTOMATIC1111-1/+1
Update description of eta setting
2023-08-13Merge pull request #12521 from catboxanon/feat/more-s-noiseAUTOMATIC1111-6/+15
Add `s_noise` param to more samplers
2023-08-13Merge pull request #12522 from catboxanon/fix/extra_paramsAUTOMATIC1111-0/+2
Restore `extra_params` that was lost in merge
2023-08-13linterAUTOMATIC1111-1/+1
2023-08-13Restore extra_params that was lost in mergecatboxanon-0/+2
2023-08-13Merge branch 'feat/dpmpp3msde' into feat/more-s-noisecatboxanon-3/+3
2023-08-13Discard penultimate sigma for DPM-Solver++(3M) SDEcatboxanon-3/+3
2023-08-13Fix s_noise descriptioncatboxanon-1/+1
2023-08-13Add s_noise param to more samplerscatboxanon-4/+10
2023-08-13Lora: output warnings in UI rather than fail for unfitting loras; switch to ↵AUTOMATIC1111-34/+58
logging for error output in console
2023-08-13Update description of eta settingcatboxanon-1/+1
2023-08-13Add DPM-Solver++(3M) SDEcatboxanon-1/+4
2023-08-13Clear sampler before decoding imagescatboxanon-0/+3
More significant VRAM reduction.
2023-08-13Encode batches separatelycatboxanon-1/+9
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-4/+13
2023-08-13Merge pull request #12503 from AUTOMATIC1111/extra-norm-moduleAUTOMATIC1111-11/+104
Add Norm Module to lora ext and add "bias" support
2023-08-13Merge pull request #12491 from AUTOMATIC1111/xyz-csv-and-dropdown-modeAUTOMATIC1111-46/+78
Bring back CSV mode for XYZ grid
2023-08-13use dataclass for StableDiffusionProcessingAUTOMATIC1111-147/+176
2023-08-13rephrase and movew-e-w-2/+3
2023-08-13add refiner to StableDiffusionProcessing classAUTOMATIC1111-20/+36
write out correct model name in infotext, rather than the refiner model
2023-08-13remove debug printKohaku-Blueleaf-1/+0
2023-08-13return None if no ex_biasKohaku-Blueleaf-4/+4
2023-08-13Add extra norm module into built-in lora extKohaku-Blueleaf-11/+105
refer to LyCORIS 1.9.0.dev6 add new option and module for training norm layer (Which is reported to be good for style)
2023-08-13properly convert this into CSV stringw-e-w-3/+3
2023-08-13pass csv_modew-e-w-17/+16
2023-08-13convert value when switching modew-e-w-14/+21
2023-08-12make "send to" buttons into small tool buttonsAUTOMATIC1111-7/+11
2023-08-12fix quicksettings on ChromeAUTOMATIC1111-2/+1
2023-08-12fix broken reuse seedAUTOMATIC1111-19/+25
2023-08-12update seed/subseed HTML widthsAUTOMATIC1111-25/+15
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-16 09:43:12 +0000