| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-10-19 | face detection algo, configurability, reusability | captin411 | -136/+230 | |
| 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 | ||||
| 2022-10-20 | pass preprocess_txt_action param | DepFA | -3/+3 | |
| 2022-10-20 | add existing caption file handling | DepFA | -8/+24 | |
| 2022-10-20 | pass overwrite old flag | DepFA | -2/+2 | |
| 2022-10-20 | allow overwrite old embedding | DepFA | -2/+3 | |
| 2022-10-19 | fix entropy point calculation | captin411 | -15/+19 | |
| 2022-10-19 | Add auto focal point cropping to Preprocess images | captin411 | -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. | ||||
| 2022-10-18 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | -0/+1 | |
| 2022-10-17 | print list of embeddings on reload | DepFA | -0/+1 | |
| 2022-10-16 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | -0/+1 | |
| 2022-10-16 | ui fix, re organization of the code | MalumaDev | -1/+1 | |
| 2022-10-16 | do not reload embeddings from disk when doing textual inversion | AUTOMATIC | -0/+1 | |
| 2022-10-16 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | -4/+13 | |
| 2022-10-15 | Change vector size footer label | DepFA | -1/+1 | |
| 2022-10-15 | generalise to popular lossless formats | DepFA | -6/+2 | |
| 2022-10-15 | add webp for embed load | DepFA | -0/+4 | |
| 2022-10-15 | only save 1 image per embedding | DepFA | -1/+4 | |
| 2022-10-15 | add vector size to embed text | DepFA | -1/+7 | |
| 2022-10-15 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | -37/+74 | |
| 2022-10-15 | Merge branch 'master' into master | AUTOMATIC1111 | -22/+28 | |
| 2022-10-15 | add option to use batch size for training | AUTOMATIC | -21/+27 | |
| 2022-10-14 | Raise an assertion error if no training images have been found. | Melan | -1/+2 | |
| 2022-10-14 | remove duplicate code for log loss, add step, make it read from options ↵ | AUTOMATIC | -14/+30 | |
| rather than gradio input | ||||
| 2022-10-14 | Merge remote-tracking branch 'Melanpan/master' | AUTOMATIC | -0/+16 | |
| 2022-10-14 | add option to read generation params for learning previews from txt2img | AUTOMATIC | -7/+18 | |
| 2022-10-14 | init | MalumaDev | -11/+26 | |
| 2022-10-13 | Add learn_rate to csv and removed a left-over debug statement | Melan | -2/+3 | |
| 2022-10-12 | Save a csv containing the loss while training | Melan | -1/+16 | |
| 2022-10-12 | [2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenames | Greg Fuller | -1/+3 | |
| 2022-10-12 | deepbooru: added option to use spaces or underscores | AUTOMATIC | -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 | ||||
| 2022-10-12 | train: change filename processing to be more simple and configurable | AUTOMATIC | -36/+83 | |
| train: make it possible to make text files with prompts train: rework scheduler so that there's less repeating code in textual inversion and hypernets train: move epochs setting to options | ||||
| 2022-10-12 | Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-images | AUTOMATIC1111 | -2/+263 | |
| Add option to store TI embeddings in png chunks, and load from same. | ||||
| 2022-10-12 | formatting | DepFA | -11/+11 | |
| 2022-10-12 | formatting | DepFA | -79/+91 | |
| 2022-10-11 | resolved conflicts, moved settings under interrogate section, settings only ↵ | JC_Array | -1/+1 | |
| show if deepbooru flag is enabled | ||||
| 2022-10-11 | Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process | JC-Array | -29/+89 | |
| 2022-10-11 | reports that training with medvram is possible. | AUTOMATIC | -1/+1 | |
| 2022-10-11 | add file based test | DepFA | -0/+8 | |
| 2022-10-11 | Add files via upload | DepFA | -0/+0 | |
| 2022-10-11 | spacing | DepFA | -1/+1 | |
| 2022-10-11 | update imports | DepFA | -0/+3 | |
| 2022-10-11 | correct conflict resolution typo | DepFA | -1/+1 | |
| 2022-10-11 | apply lr schedule to hypernets | AUTOMATIC | -40/+38 | |
| 2022-10-11 | remove old caption method | DepFA | -37/+2 | |
| 2022-10-11 | shift embedding logic out of textual_inversion | DepFA | -119/+6 | |
| 2022-10-11 | Merge branch 'learning_rate-scheduling' into learnschedule | AUTOMATIC1111 | -22/+41 | |
| 2022-10-11 | move embedding logic to separate file | DepFA | -0/+234 | |
| 2022-10-11 | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | -10/+21 | |
| 2022-10-11 | produce error when training with medvram/lowvram enabled | AUTOMATIC | -0/+3 | |
| 2022-10-11 | Merge pull request #2201 from alg-wiki/textual__inversion | AUTOMATIC1111 | -10/+11 | |
| Textual Inversion: Preprocess and Training will only pick-up image files instead | ||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |