aboutsummaryrefslogtreecommitdiff
path: root/modules/sd_hijack.py
AgeCommit message (Collapse)Author
2023-08-05Merge branch 'dev' into multiple_loaded_modelsAUTOMATIC1111
2023-08-04resolve some of circular import issues for kohakuAUTOMATIC1111
2023-08-01repair PLMSAUTOMATIC1111
2023-08-01option to keep multiple models in memoryAUTOMATIC1111
2023-07-29textual inversion support for SDXLAUTOMATIC1111
2023-07-19Merge pull request #11878 from Bourne-M/patch-1AUTOMATIC1111
【bug】reload altclip model error
2023-07-19【bug】reload altclip model erroryfzhou
When using BertSeriesModelWithTransformation as the cond_stage_model, the undo_hijack should be performed using the FrozenXLMREmbedderWithCustomWords type; otherwise, it will result in a failed model reload.
2023-07-16Merge pull request #11757 from AUTOMATIC1111/sdxlAUTOMATIC1111
SD XL support
2023-07-15add textual inversion hashes to infotextAUTOMATIC1111
2023-07-14initial SDXL refiner supportAUTOMATIC1111
2023-07-13fix CLIP doing the unneeded normalizationAUTOMATIC1111
revert SD2.1 back to use the original repo add SDXL's force_zero_embeddings to negative prompt
2023-07-12SDXL supportAUTOMATIC1111
2023-07-11getting SD2.1 to run on SDXL repoAUTOMATIC1111
2023-06-01revert default cross attention optimization to DoggettxAUTOMATIC
make --disable-opt-split-attention command line option work again
2023-05-27custom unet supportAUTOMATIC
2023-05-23possible fix for empty list of optimizations #10605AUTOMATIC
2023-05-19make it actually work after suggestionsAUTOMATIC
2023-05-19fix linter issuesAUTOMATIC
2023-05-18make it possible for scripts to add cross attention optimizationsAUTOMATIC
add UI selection for cross attention optimization
2023-05-14fix model loading twice in some situationsAUTOMATIC
2023-05-11Autofix Ruff W (not W605) (mostly whitespace)Aarni Koskela
2023-05-10ruff auto fixesAUTOMATIC
2023-05-10imports cleanup for ruffAUTOMATIC
2023-05-10autofixes from ruffAUTOMATIC
2023-03-10sdp_attnblock_forward hijackPam
2023-03-10sdp refactoringPam
2023-03-10argument to disable memory efficient for sdpPam
2023-03-07scaled dot product attentionPam
2023-02-19Merge branch 'master' into weighted-learningAUTOMATIC1111
2023-02-15Hijack to add weighted_forward to model: return loss * weight mapShondoit
2023-02-07Apply hijacks in ddpm_edit for upcast samplingbrkirch
To avoid import errors, ddpm_edit hijacks are done after an instruct pix2pix model is loaded.
2023-01-28Merge pull request #7309 from brkirch/fix-embeddingsAUTOMATIC1111
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28automatically detect v-parameterization for SD2 checkpointsAUTOMATIC
2023-01-28Refactor conditional casting, fix upscalersbrkirch
2023-01-26Fix embeddings dtype mismatchbrkirch
2023-01-19write a comment for fix_checkpoint functionAUTOMATIC
2023-01-18add option to show/hide warningsAUTOMATIC
removed hiding warnings from LDSR fixed/reworked few places that produced warnings
2023-01-08make it possible for extensions/scripts to add their own embedding directoriesAUTOMATIC
2023-01-07Merge pull request #6055 from brkirch/sub-quad_attn_optAUTOMATIC1111
Add Birch-san's sub-quadratic attention implementation
2023-01-07CLIP hijack reworkAUTOMATIC
2023-01-06Allow Doggettx's cross attention opt without CUDAbrkirch
2023-01-06Merge remote-tracking branch 'upstream/master' into sub-quad_attn_optbrkirch
2023-01-06Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_optbrkirch
2023-01-06Add Birch-san's sub-quadratic attention implementationbrkirch
2023-01-04add cross-attention infoVladimir Mandic
2022-12-31alt-diffusion integrationAUTOMATIC
2022-12-31Merge remote-tracking branch 'baai-open-internal/master' into alt-diffusionAUTOMATIC
2022-12-10cleanup some unneeded imports for hijack filesAUTOMATIC
2022-12-10do not replace entire unet for the resolution hackAUTOMATIC
2022-12-10Merge pull request #4978 from aliencaocao/support_any_resolutionAUTOMATIC1111
Patch UNet Forward to support resolutions that are not multiples of 64
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 15:43:56 +0000