aboutsummaryrefslogtreecommitdiffstats
path: root/modules/processing.py
Commit message (Collapse)AuthorAgeFilesLines
...
* Infotext saves more specific hypernet name.timntorres2022-10-191-1/+1
|
* Merge remote-tracking branch 'origin/api'AUTOMATIC2022-10-191-8/+16
|\
| * example API working with gradioarcticfaded2022-10-171-7/+15
| |
| * initial prototype by borrowing contractsarcticfaded2022-10-171-1/+1
| |
* | remove dependence on TQDM for sampler progress/interrupt functionalityAUTOMATIC2022-10-181-6/+0
|/
* Only make output dir when creating outputCookieHCl2022-10-161-6/+0
|
* do not reload embeddings from disk when doing textual inversionAUTOMATIC2022-10-161-2/+3
|
* add First pass size always regardless of whether it was auto chosen or specifiedAUTOMATIC2022-10-151-1/+1
|
* bring back scale latent option in settingsAUTOMATIC2022-10-151-4/+4
|
* Set to -1 when seed input is nonegithublsx2022-10-151-1/+1
|
* set firstpass w/h to 0 by default and rever to old behavior when any are 0AUTOMATIC2022-10-141-19/+30
|
* remove scale latent and no-crop options from hires fixAUTOMATIC2022-10-141-37/+27
| | | | support copy-pasting new parameters for hires fix
* Fixed Scale ratio problemBuckzor2022-10-141-14/+11
|
* Option between stretch and crop for Highres. fixBuckzor2022-10-141-12/+22
|
* Added first_pass_width and height as adjustable inputs to "High Res Fix"Buckzor2022-10-141-2/+4
|
* Restore last generation paramsTrung Ngo2022-10-131-0/+4
|
* add eta noise seed delta optionAUTOMATIC2022-10-101-1/+5
|
* --no-half-vae pt2AUTOMATIC2022-10-101-2/+1
|
* --no-half-vaeAUTOMATIC2022-10-101-2/+9
|
* do not add clip skip to parameters if it's 1 or 0AUTOMATIC2022-10-091-1/+1
|
* Fix issues with CLIP ignore option name changeFampai2022-10-091-2/+2
|
* change up #2056 to make it work how i want it to plus make xy plot write ↵AUTOMATIC2022-10-091-3/+2
| | | | correct values to images
* Sanitize infotext output (for now)William Moorehouse2022-10-091-3/+3
|
* Fix grabbing the model name for infotextWilliam Moorehouse2022-10-091-1/+1
|
* Added extended model details to infotextWilliam Moorehouse2022-10-091-0/+3
|
* additional changes for saving pnginfo for #1803AUTOMATIC2022-10-091-2/+4
|
* remove line breakfrostydad2022-10-091-1/+0
|
* Fix incorrect sampler name in outputfrostydad2022-10-091-1/+8
|
* support loading .yaml config with same name as modelAUTOMATIC2022-10-081-1/+1
| | | | support EMA weights in processing (????)
* chore: Fix typosAidan Holland2022-10-081-1/+1
|
* add 'Ignore last layers of CLIP model' option as a parameter to the infotextAUTOMATIC2022-10-081-1/+5
|
* fix bug where when using prompt composition, hijack_comments generated ↵MrCheeze2022-10-081-0/+1
| | | | before the final AND will be dropped
* do not let user choose his own prompt token count limitAUTOMATIC2022-10-081-5/+0
|
* check specifically for skippedTrung Ngo2022-10-081-2/+1
|
* Add button to skip the current iterationTrung Ngo2022-10-081-0/+4
|
* let user choose his own prompt token count limitAUTOMATIC2022-10-081-0/+6
|
* Added job_timestamp to ProcessedMilly2022-10-061-0/+2
| | | | So `[job_timestamp]` pattern can use in saving image UI.
* Added styles to ProcessedMilly2022-10-061-0/+2
| | | | So `[styles]` pattern can use in saving image UI.
* add generation parameters to images shown in web uiAUTOMATIC2022-10-061-2/+6
|
* Merge branch 'master' into fix-vramJairo Correa2022-10-061-8/+8
|\
| * integrate the new samplers PRAUTOMATIC2022-10-061-3/+4
| |
| * option to let users select which samplers they want to hideAUTOMATIC2022-10-061-7/+6
| |
| * added support for AND from ↵AUTOMATIC2022-10-051-1/+1
| | | | | | | | https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
* | Removing parts no longer needed to fix vramJairo Correa2022-10-051-13/+8
| |
* | Merge branch 'master' into fix-vramJairo Correa2022-10-041-20/+33
|\|
| * prompt_parser: allow spaces in schedules, add test, log/ignore errorsRae Fu2022-10-041-5/+5
| | | | | | | | | | | | Only build the parser once (at import time) instead of for each step. doctest is run by simply executing modules/prompt_parser.py
| * do not touch p.seed/p.subseed during processing #1181AUTOMATIC2022-10-041-9/+17
| |
| * emergency fix for img2imgAUTOMATIC2022-10-041-1/+2
| |
| * support interrupting after the previous changeAUTOMATIC2022-10-041-1/+3
| |
| * send all three of GFPGAN's and codeformer's models to CPU memory instead of ↵AUTOMATIC2022-10-041-7/+9
| | | | | | | | just one for #1283
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-02 20:06:04 +0000