aboutsummaryrefslogtreecommitdiffstats
path: root/modules/processing.py
AgeCommit message (Collapse)AuthorLines
2022-10-22removed aesthetic gradients as built-inAUTOMATIC-13/+22
added support for extensions
2022-10-21Refer to Hypernet's name, sensibly, by its name variable.timntorres-1/+1
2022-10-21do not load aesthetic clip model until it's neededAUTOMATIC-2/+2
add refresh button for aesthetic embeddings add aesthetic params to images' infotext
2022-10-21Fix Hypernet infotext string split bug for PR #3283AUTOMATIC-1/+1
2022-10-21updated readme and some small stylistic changes to codeAUTOMATIC-8/+6
2022-10-20Made dummy latents smaller. Minor code cleanupsrandom_thoughtss-3/+4
2022-10-19Fixed non-square highres fix generationrandom_thoughtss-3/+6
2022-10-19Don't compute latent mask if were not using it. Also added support for fixed ↵random_thoughtss-27/+45
highres_fix generation.
2022-10-19Added support for RunwayML inpainting modelrandom_thoughtss-2/+32
2022-10-19Infotext saves more specific hypernet name.timntorres-1/+1
2022-10-19Merge remote-tracking branch 'origin/api'AUTOMATIC-8/+16
2022-10-18remove dependence on TQDM for sampler progress/interrupt functionalityAUTOMATIC-6/+0
2022-10-17example API working with gradioarcticfaded-7/+15
2022-10-17initial prototype by borrowing contractsarcticfaded-1/+1
2022-10-16Only make output dir when creating outputCookieHCl-6/+0
2022-10-16do not reload embeddings from disk when doing textual inversionAUTOMATIC-2/+3
2022-10-15add First pass size always regardless of whether it was auto chosen or specifiedAUTOMATIC-1/+1
2022-10-15bring back scale latent option in settingsAUTOMATIC-4/+4
2022-10-15Set to -1 when seed input is nonegithublsx-1/+1
2022-10-14set firstpass w/h to 0 by default and rever to old behavior when any are 0AUTOMATIC-19/+30
2022-10-14remove scale latent and no-crop options from hires fixAUTOMATIC-37/+27
support copy-pasting new parameters for hires fix
2022-10-14Fixed Scale ratio problemBuckzor-14/+11
2022-10-14Option between stretch and crop for Highres. fixBuckzor-12/+22
2022-10-14Added first_pass_width and height as adjustable inputs to "High Res Fix"Buckzor-2/+4
2022-10-13Restore last generation paramsTrung Ngo-0/+4
2022-10-10add eta noise seed delta optionAUTOMATIC-1/+5
2022-10-10--no-half-vae pt2AUTOMATIC-2/+1
2022-10-10--no-half-vaeAUTOMATIC-2/+9
2022-10-09do not add clip skip to parameters if it's 1 or 0AUTOMATIC-1/+1
2022-10-09Fix issues with CLIP ignore option name changeFampai-2/+2
2022-10-09change up #2056 to make it work how i want it to plus make xy plot write ↵AUTOMATIC-3/+2
correct values to images
2022-10-09Sanitize infotext output (for now)William Moorehouse-3/+3
2022-10-09Fix grabbing the model name for infotextWilliam Moorehouse-1/+1
2022-10-09Added extended model details to infotextWilliam Moorehouse-0/+3
2022-10-09additional changes for saving pnginfo for #1803AUTOMATIC-2/+4
2022-10-09remove line breakfrostydad-1/+0
2022-10-09Fix incorrect sampler name in outputfrostydad-1/+8
2022-10-08support loading .yaml config with same name as modelAUTOMATIC-1/+1
support EMA weights in processing (????)
2022-10-08chore: Fix typosAidan Holland-1/+1
2022-10-08add 'Ignore last layers of CLIP model' option as a parameter to the infotextAUTOMATIC-1/+5
2022-10-08fix bug where when using prompt composition, hijack_comments generated ↵MrCheeze-0/+1
before the final AND will be dropped
2022-10-08do not let user choose his own prompt token count limitAUTOMATIC-5/+0
2022-10-08check specifically for skippedTrung Ngo-2/+1
2022-10-08Add button to skip the current iterationTrung Ngo-0/+4
2022-10-08let user choose his own prompt token count limitAUTOMATIC-0/+6
2022-10-06Added job_timestamp to ProcessedMilly-0/+2
So `[job_timestamp]` pattern can use in saving image UI.
2022-10-06Added styles to ProcessedMilly-0/+2
So `[styles]` pattern can use in saving image UI.
2022-10-06add generation parameters to images shown in web uiAUTOMATIC-2/+6
2022-10-06Merge branch 'master' into fix-vramJairo Correa-8/+8
2022-10-06integrate the new samplers PRAUTOMATIC-3/+4