aboutsummaryrefslogtreecommitdiff
path: root/modules/textual_inversion/preprocess.py
AgeCommit message (Collapse)Author
2023-01-27add data-dir flag and set all user data directories based on itMax Audron
2023-01-19Fix of fixdan
2023-01-19Simplification and bugfixdan
2023-01-17Add auto-sized cropping UIdan
2023-01-15big rework of progressbar/preview system to allow multiple users to prompts ↵AUTOMATIC
at the same time and do not get previews of each other
2023-01-11set descriptionsVladimir Mandic
2023-01-03add job info to modulesVladimir Mandic
2022-11-20moved deepdanbooru to pure pytorch implementationAUTOMATIC
2022-11-08move functions out of main body for image preprocessing for easier hijackingAUTOMATIC
2022-10-25download better face detection module dynamicallycaptin411
2022-10-25Focal crop UI elementscaptin411
2022-10-25Merge branch 'master' into focal-point-croppingcaptin411
2022-10-21prevent error spam when processing images without txt files for captionsAUTOMATIC
2022-10-21Merge branch 'master' into fix/train-preprocess-keep-ratioAUTOMATIC1111
2022-10-20train: ui: added `Split image threshold` and `Split image overlap ratio` to ↵Milly
preprocess
2022-10-20train: fixed preprocess image ratioMilly
2022-10-20do caption copy for both flipsDepFA
2022-10-19face detection algo, configurability, reusabilitycaptin411
Try to move the crop in the direction of a face if it is present More internal configuration options for choosing weights of each of the algorithm's findings Move logic into its module
2022-10-20pass preprocess_txt_action paramDepFA
2022-10-20add existing caption file handlingDepFA
2022-10-19fix entropy point calculationcaptin411
2022-10-19Add auto focal point cropping to Preprocess imagescaptin411
This algorithm plots a bunch of points of interest on the source image and averages their locations to find a center. Most points come from OpenCV. One point comes from an entropy model. OpenCV points account for 50% of the weight and the entropy based point is the other 50%. The center of all weighted points is calculated and a bounding box is drawn as close to centered over that point as possible.
2022-10-12[2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenamesGreg Fuller
2022-10-12deepbooru: added option to use spaces or underscoresAUTOMATIC
deepbooru: added option to quote (\) in tags deepbooru/BLIP: write caption to file instead of image filename deepbooru/BLIP: now possible to use both for captions deepbooru: process is stopped even if an exception occurs
2022-10-11resolved conflicts, moved settings under interrogate section, settings only ↵JC_Array
show if deepbooru flag is enabled
2022-10-11Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_processJC-Array
2022-10-11Switched to exception handlingalg-wiki
2022-10-10added alpha sort and threshold variables to create process method in ↵JC_Array
preprocessing
2022-10-10Merge branch 'deepdanbooru_pre_process' into masterJC-Array
2022-10-11Added .webp .bmpalg-wiki
2022-10-11Textual Inversion: Preprocess and Training will only pick-up image filesalg-wiki
2022-10-10Custom Width and Heightalg-wiki
2022-10-10Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki
per input image in a single epoch
2022-10-10Custom Width and Heightalg-wiki
2022-10-10Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki
per input image in a single epoch
2022-10-09refactored the deepbooru module to improve speed on running multiple ↵JC_Array
interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
2022-10-06removed unused import, fixed typoRaphael Stoeckli
2022-10-06Add sanitizer for captions in Textual inversionRaphael Stoeckli
2022-10-04add support for gelbooru tags in filenames for textual inversionAUTOMATIC
2022-10-02preprocessing for textual inversion addedAUTOMATIC
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 15:38:48 +0000