aboutsummaryrefslogtreecommitdiffstats
path: root/modules/textual_inversion/preprocess.py
Commit message (Collapse)AuthorAgeFilesLines
* remove Train/Preprocessing tab and put all its functionality into extras ↵AUTOMATIC11112023-12-021-232/+0
| | | | batch images mode
* fix Auto focal point crop for opencv >= 4.8.xw-e-w2023-11-281-2/+2
| | | | | | | autocrop.download_and_cache_models in opencv >= 4.8 the face detection model was updated download the base on opencv version returns the model path or raise exception
* sync default value of process_focal_crop_entropy_weight between ui and apihunshcn2023-06-291-1/+1
|
* Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressionsAarni Koskela2023-06-021-2/+2
|
* Autofix Ruff W (not W605) (mostly whitespace)Aarni Koskela2023-05-111-1/+1
|
* imports cleanup for ruffAUTOMATIC2023-05-101-4/+0
|
* Fix up string formatting/concatenation to f-strings where feasibleAarni Koskela2023-05-091-3/+3
|
* Merge pull request #8924 from kurilee/masterAUTOMATIC11112023-04-291-3/+7
|\ | | | | Add option "keep original size" to textual inversion images preprocess
| * Add option "keep original size" to textual inversion images preprocesskurilee2023-03-251-3/+7
| |
* | Pythonic way to achieve itAndre Ubuntu2023-04-051-17/+1
| |
* | fix preprocess orientationAndre Ubuntu2023-04-051-1/+19
|/
* add data-dir flag and set all user data directories based on itMax Audron2023-01-271-3/+2
|
* Fix of fixdan2023-01-191-2/+2
|
* Simplification and bugfixdan2023-01-191-7/+5
|
* Add auto-sized cropping UIdan2023-01-171-3/+35
|
* big rework of progressbar/preview system to allow multiple users to prompts ↵AUTOMATIC2023-01-151-1/+1
| | | | at the same time and do not get previews of each other
* set descriptionsVladimir Mandic2023-01-111-1/+6
|
* add job info to modulesVladimir Mandic2023-01-031-0/+1
|
* moved deepdanbooru to pure pytorch implementationAUTOMATIC2022-11-201-8/+4
|
* move functions out of main body for image preprocessing for easier hijackingAUTOMATIC2022-11-081-69/+93
|
* download better face detection module dynamicallycaptin4112022-10-251-2/+11
|
* Focal crop UI elementscaptin4112022-10-251-13/+13
|
* Merge branch 'master' into focal-point-croppingcaptin4112022-10-251-32/+59
|\
| * prevent error spam when processing images without txt files for captionsAUTOMATIC2022-10-211-5/+4
| |
| * Merge branch 'master' into fix/train-preprocess-keep-ratioAUTOMATIC11112022-10-211-9/+25
| |\
| | * do caption copy for both flipsDepFA2022-10-201-1/+1
| | |
| | * pass preprocess_txt_action paramDepFA2022-10-191-3/+3
| | |
| | * add existing caption file handlingDepFA2022-10-191-8/+24
| | |
| * | train: ui: added `Split image threshold` and `Split image overlap ratio` to ↵Milly2022-10-201-5/+5
| | | | | | | | | | | | preprocess
| * | train: fixed preprocess image ratioMilly2022-10-201-19/+35
| |/
* | face detection algo, configurability, reusabilitycaptin4112022-10-201-136/+14
| | | | | | | | | | | | | | 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
* | fix entropy point calculationcaptin4112022-10-191-15/+19
| |
* | Add auto focal point cropping to Preprocess imagescaptin4112022-10-191-5/+146
|/ | | | | | | | | | | 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.
* [2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenamesGreg Fuller2022-10-121-1/+3
|
* deepbooru: added option to use spaces or underscoresAUTOMATIC2022-10-121-52/+40
| | | | | | | 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
* resolved conflicts, moved settings under interrogate section, settings only ↵JC_Array2022-10-111-1/+1
| | | | show if deepbooru flag is enabled
* Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_processJC-Array2022-10-111-1/+4
|\
| * Switched to exception handlingalg-wiki2022-10-111-3/+5
| |
| * Added .webp .bmpalg-wiki2022-10-101-1/+1
| |
| * Textual Inversion: Preprocess and Training will only pick-up image filesalg-wiki2022-10-101-1/+2
| |
| * Custom Width and Heightalg-wiki2022-10-101-9/+10
| |
| * Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki2022-10-101-2/+2
| | | | | | | | per input image in a single epoch
* | added alpha sort and threshold variables to create process method in ↵JC_Array2022-10-101-1/+1
| | | | | | | | preprocessing
* | Merge branch 'deepdanbooru_pre_process' into masterJC-Array2022-10-101-2/+20
|\ \
| * | refactored the deepbooru module to improve speed on running multiple ↵JC_Array2022-10-101-2/+20
| |/ | | | | | | interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
* | Custom Width and Heightalg-wiki2022-10-101-9/+10
| |
* | Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki2022-10-101-2/+2
|/ | | | per input image in a single epoch
* removed unused import, fixed typoRaphael Stoeckli2022-10-061-2/+1
|
* Add sanitizer for captions in Textual inversionRaphael Stoeckli2022-10-061-0/+28
|
* add support for gelbooru tags in filenames for textual inversionAUTOMATIC2022-10-041-1/+3
|
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-28 14:39:42 +0000