aboutsummaryrefslogtreecommitdiff
path: root/modules/processing.py
AgeCommit message (Collapse)Author
2022-10-21do not load aesthetic clip model until it's neededAUTOMATIC
add refresh button for aesthetic embeddings add aesthetic params to images' infotext
2022-10-21Fix Hypernet infotext string split bug for PR #3283AUTOMATIC
2022-10-21updated readme and some small stylistic changes to codeAUTOMATIC
2022-10-20Made dummy latents smaller. Minor code cleanupsrandom_thoughtss
2022-10-19Fixed non-square highres fix generationrandom_thoughtss
2022-10-19Don't compute latent mask if were not using it. Also added support for fixed ↵random_thoughtss
highres_fix generation.
2022-10-19Added support for RunwayML inpainting modelrandom_thoughtss
2022-10-19Infotext saves more specific hypernet name.timntorres
2022-10-19Merge remote-tracking branch 'origin/api'AUTOMATIC
2022-10-18remove dependence on TQDM for sampler progress/interrupt functionalityAUTOMATIC
2022-10-17example API working with gradioarcticfaded
2022-10-17initial prototype by borrowing contractsarcticfaded
2022-10-16Only make output dir when creating outputCookieHCl
2022-10-16do not reload embeddings from disk when doing textual inversionAUTOMATIC
2022-10-15add First pass size always regardless of whether it was auto chosen or specifiedAUTOMATIC
2022-10-15bring back scale latent option in settingsAUTOMATIC
2022-10-15Set to -1 when seed input is nonegithublsx
2022-10-14set firstpass w/h to 0 by default and rever to old behavior when any are 0AUTOMATIC
2022-10-14remove scale latent and no-crop options from hires fixAUTOMATIC
support copy-pasting new parameters for hires fix
2022-10-14Fixed Scale ratio problemBuckzor
2022-10-14Option between stretch and crop for Highres. fixBuckzor
2022-10-14Added first_pass_width and height as adjustable inputs to "High Res Fix"Buckzor
2022-10-13Restore last generation paramsTrung Ngo
2022-10-10add eta noise seed delta optionAUTOMATIC
2022-10-10--no-half-vae pt2AUTOMATIC
2022-10-10--no-half-vaeAUTOMATIC
2022-10-09do not add clip skip to parameters if it's 1 or 0AUTOMATIC
2022-10-09Fix issues with CLIP ignore option name changeFampai
2022-10-09change up #2056 to make it work how i want it to plus make xy plot write ↵AUTOMATIC
correct values to images
2022-10-09Sanitize infotext output (for now)William Moorehouse
2022-10-09Fix grabbing the model name for infotextWilliam Moorehouse
2022-10-09Added extended model details to infotextWilliam Moorehouse
2022-10-09additional changes for saving pnginfo for #1803AUTOMATIC
2022-10-09remove line breakfrostydad
2022-10-09Fix incorrect sampler name in outputfrostydad
2022-10-08support loading .yaml config with same name as modelAUTOMATIC
support EMA weights in processing (????)
2022-10-08chore: Fix typosAidan Holland
2022-10-08add 'Ignore last layers of CLIP model' option as a parameter to the infotextAUTOMATIC
2022-10-08fix bug where when using prompt composition, hijack_comments generated ↵MrCheeze
before the final AND will be dropped
2022-10-08do not let user choose his own prompt token count limitAUTOMATIC
2022-10-08check specifically for skippedTrung Ngo
2022-10-08Add button to skip the current iterationTrung Ngo
2022-10-08let user choose his own prompt token count limitAUTOMATIC
2022-10-06Added job_timestamp to ProcessedMilly
So `[job_timestamp]` pattern can use in saving image UI.
2022-10-06Added styles to ProcessedMilly
So `[styles]` pattern can use in saving image UI.
2022-10-06add generation parameters to images shown in web uiAUTOMATIC
2022-10-06Merge branch 'master' into fix-vramJairo Correa
2022-10-06integrate the new samplers PRAUTOMATIC
2022-10-06option to let users select which samplers they want to hideAUTOMATIC
2022-10-05added support for AND from ↵AUTOMATIC
https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-22 13:24:47 +0000