aboutsummaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorLines
2023-08-15Merge pull request #12578 from AUTOMATIC1111/changelog-fixAUTOMATIC1111-1/+1
Changelog minor correction
2023-08-15Update CHANGELOG.mdw-e-w-1/+1
2023-08-15Use the new SD VAE override settingbrkirch-1/+1
2023-08-15Merge pull request #12573 from catboxanon/changelogAUTOMATIC1111-39/+39
Add PR refs to changelog
2023-08-15Add PR refs to changelogcatboxanon-39/+39
2023-08-15update changelog fileAUTOMATIC1111-0/+96
2023-08-15Merge pull request #12564 from catboxanon/feat/img2img-noiseAUTOMATIC1111-1/+12
Add extra noise param for img2img operations
2023-08-15Add NoCrypt/miku gradio themeNoCrypt-1/+2
2023-08-15Add extra img2img noisecatboxanon-1/+12
2023-08-15fix processing error that happens if batch_size is not a multiple of how ↵AUTOMATIC1111-1/+6
many prompts/negative prompts there are #12509
2023-08-15get XYZ plot to work with recent changes to refined specified in fields of p ↵AUTOMATIC1111-15/+7
rather than in settings
2023-08-15Merge pull request #12476 from AnyISalIn/devAUTOMATIC1111-0/+19
xyz_grid: support refiner_checkpoint and refiner_switch_at
2023-08-15Merge pull request #12552 from brkirch/update-sdxl-commit-hashAUTOMATIC1111-1/+1
Update SD XL commit hash
2023-08-14correctly add Eta DDIM to infotext when it's 1.0 and do not add it when it's ↵AUTOMATIC1111-1/+3
0.0.
2023-08-14when refreshing cards in extra networks UI, do not discard user's custom ↵AUTOMATIC1111-1/+1
resolution
2023-08-14revert changed inpainting mask conditioning calculation after #12311AUTOMATIC1111-1/+1
2023-08-14Merge pull request #12547 from whitebell/fix-typoAUTOMATIC1111-1/+1
Fix typo in shared_options.py
2023-08-14Merge pull request #12551 from AUTOMATIC1111/separate-Extra-optionsAUTOMATIC1111-5/+7
separate Extra options
2023-08-14Update hash for SD XL Repobrkirch-1/+1
2023-08-14separate Extra optionsw-e-w-5/+7
2023-08-14add second_order to samplers that mistakenly didn't have itAUTOMATIC1111-3/+3
2023-08-14hires prompt timeline: merge to latests, slightly simplify diffRobert Barron-4/+4
2023-08-14fix API always using -1 as seedAUTOMATIC1111-6/+16
2023-08-14Merge remote-tracking branch 'auto1111/dev' into shared-hires-prompt-testRobert Barron-527/+1107
2023-08-14return seed controls UI to how it was beforeAUTOMATIC1111-18/+44
2023-08-14further repair the /docs page to not break styles with the attempted fixAUTOMATIC1111-1/+3
2023-08-14Fix typo in shared_options.pywhitebell-1/+1
unperdictable -> unpredictable
2023-08-14repair /docs pageAUTOMATIC1111-5/+7
2023-08-14Merge pull request #12542 from AUTOMATIC1111/res-samplerAUTOMATIC1111-0/+10
Add RES sampler and reorder the sampler list
2023-08-14Merge pull request #12543 from AUTOMATIC1111/extra-norm-moduleAUTOMATIC1111-9/+30
Fix MHA error with ex_bias and support ex_bias for layers which don't have bias
2023-08-14revert to applying mask before denoising for k-diffusion, like it was beforeAUTOMATIC1111-1/+6
2023-08-14remove "if bias exist" checkKohaku-Blueleaf-1/+1
2023-08-14Put frequently used sampler backKohaku-Blueleaf-4/+4
2023-08-14make on_before_component/on_after_component possible earlierAUTOMATIC1111-10/+25
2023-08-14repair DDIM/PLMS/UniPC batchesAUTOMATIC1111-11/+12
2023-08-14Merge branch 'dev' into extra-norm-moduleKohaku-Blueleaf-272/+452
2023-08-14Fix MHA updown err and support ex-bias for no-bias layerKohaku-Blueleaf-8/+29
2023-08-14add res(dpmdd 2m sde heun) and reorder the sampler listKohaku-Blueleaf-4/+14
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.
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-17 23:06:36 +0000