Age | Commit message (Collapse) | Author | |
---|---|---|---|
2022-10-31 | Fixed minor bug | Fampai | |
when unloading vae during TI training, generating images after training will error out | |||
2022-10-31 | Merge branch 'master' of ↵ | Fampai | |
https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations | |||
2022-10-31 | Added TI training optimizations | Fampai | |
option to use xattention optimizations when training option to unload vae when training | |||
2022-10-30 | Merge pull request #3928 from R-N/validate-before-load | AUTOMATIC1111 | |
Optimize training a little | |||
2022-10-30 | Fix dataset still being loaded even when training will be skipped | Muhammad Rizqi Nur | |
2022-10-30 | Add missing info on hypernetwork/embedding model log | Muhammad Rizqi Nur | |
Mentioned here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528#discussioncomment-3991513 Also group the saving into one | |||
2022-10-30 | Revert "Add cleanup after training" | Muhammad Rizqi Nur | |
This reverts commit 3ce2bfdf95bd5f26d0f6e250e67338ada91980d1. | |||
2022-10-29 | Additional assert on dataset | Muhammad Rizqi Nur | |
2022-10-29 | Add cleanup after training | Muhammad Rizqi Nur | |
2022-10-29 | Add input validations before loading dataset for training | Muhammad Rizqi Nur | |
2022-10-29 | Improve lr schedule error message | Muhammad Rizqi Nur | |
2022-10-29 | Allow trailing comma in learning rate | Muhammad Rizqi Nur | |
2022-10-29 | Merge pull request #3858 from R-N/log-csv | AUTOMATIC1111 | |
Fix log off by 1 #3847 | |||
2022-10-28 | Fix log off by 1 | Muhammad Rizqi Nur | |
2022-10-28 | Fix random dataset shuffle on TI | FlameLaw | |
2022-10-26 | typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir | DepFA | |
2022-10-26 | Implement PR #3625 but for embeddings. | timntorres | |
2022-10-26 | Implement PR #3309 but for embeddings. | timntorres | |
2022-10-26 | Implement PR #3189 but for embeddings. | timntorres | |
2022-10-26 | enable creating embedding with --medvram | AUTOMATIC | |
2022-10-25 | update default weights | captin411 | |
2022-10-25 | download better face detection module dynamically | captin411 | |
2022-10-25 | Focal crop UI elements | captin411 | |
2022-10-25 | Merge branch 'master' into focal-point-cropping | captin411 | |
2022-10-25 | improve debug markers, fix algo weighting | captin411 | |
2022-10-23 | auto cropping now works with non square crops | captin411 | |
2022-10-21 | prevent error spam when processing images without txt files for captions | AUTOMATIC | |
2022-10-21 | Merge branch 'master' into fix/train-preprocess-keep-ratio | AUTOMATIC1111 | |
2022-10-21 | Update image_embedding.py | DepFA | |
2022-10-21 | Use opts in textual_inversion image_embedding.py for dynamic fonts | DepFA | |
2022-10-21 | Merge branch 'ae' | AUTOMATIC | |
2022-10-21 | Merge branch 'master' into training-help-text | AUTOMATIC1111 | |
2022-10-21 | Allow datasets with only 1 image in TI | guaneec | |
2022-10-20 | train: ui: added `Split image threshold` and `Split image overlap ratio` to ↵ | Milly | |
preprocess | |||
2022-10-20 | train: fixed preprocess image ratio | Milly | |
2022-10-20 | improve face detection a lot | captin411 | |
2022-10-20 | do caption copy for both flips | DepFA | |
2022-10-19 | face detection algo, configurability, reusability | captin411 | |
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 | |
2022-10-20 | add existing caption file handling | DepFA | |
2022-10-20 | pass overwrite old flag | DepFA | |
2022-10-20 | allow overwrite old embedding | DepFA | |
2022-10-19 | fix entropy point calculation | captin411 | |
2022-10-19 | Add auto focal point cropping to Preprocess images | captin411 | |
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 | |
2022-10-17 | print list of embeddings on reload | DepFA | |
2022-10-16 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | |
2022-10-16 | ui fix, re organization of the code | MalumaDev | |
2022-10-16 | do not reload embeddings from disk when doing textual inversion | AUTOMATIC | |
2022-10-16 | Merge branch 'master' into test_resolve_conflicts | MalumaDev | |