KohyaSS/library
bmaltais 045750b46a v20.6.0
- Increase max LoRA rank (dim) size to 1024.
    - Update finetune preprocessing scripts.
        - ``.bmp`` and ``.jpeg`` are supported. Thanks to breakcore2 and p1atdev!
        - The default weights of ``tag_images_by_wd14_tagger.py`` is now ``SmilingWolf/wd-v1-4-convnext-tagger-v2``. You can specify another model id from ``SmilingWolf`` by ``--repo_id`` option. Thanks to SmilingWolf for the great work.
        - To change the weight, remove ``wd14_tagger_model`` folder, and run the script again.
        - ``--max_data_loader_n_workers`` option is added to each script. This option uses the DataLoader for data loading to speed up loading, 20%~30% faster.
        - Please specify 2 or 4, depends on the number of CPU cores.
        - ``--recursive`` option is added to ``merge_dd_tags_to_metadata.py`` and ``merge_captions_to_metadata.py``, only works with ``--full_path``.
        - ``make_captions_by_git.py`` is added. It uses [GIT microsoft/git-large-textcaps](https://huggingface.co/microsoft/git-large-textcaps) for captioning.
        - ``requirements.txt`` is updated. If you use this script, [please update the libraries](https://github.com/kohya-ss/sd-scripts#upgrade).
        - Usage is almost the same as ``make_captions.py``, but batch size should be smaller.
        - ``--remove_words`` option removes as much text as possible (such as ``the word "XXXX" on it``).
        - ``--skip_existing`` option is added to ``prepare_buckets_latents.py``. Images with existing npz files are ignored by this option.
        - ``clean_captions_and_tags.py`` is updated to remove duplicated or conflicting tags, e.g. ``shirt`` is removed when ``white shirt`` exists. if ``black hair`` is with ``red hair``, both are removed.
    - Tag frequency is added to the metadata in ``train_network.py``. Thanks to space-nuko!
        - __All tags and number of occurrences of the tag are recorded.__ If you do not want it, disable metadata storing with ``--no_metadata`` option.
2023-02-04 08:36:35 -05:00
..
__init__.py v18.1: Model conversion utility 2022-12-18 13:11:10 -05:00
basic_caption_gui.py Add default for caption extension tools 2023-01-20 18:41:37 -05:00
blip_caption_gui.py Add default for caption extension tools 2023-01-20 18:41:37 -05:00
common_gui.py Add support for lr_scheduler_num_cycles, lr_scheduler_power 2023-01-30 08:26:15 -05:00
convert_model_gui.py Add support for: 2022-12-19 21:50:05 -05:00
dataset_balancing_gui.py Fix issue with LR 2022-12-29 21:17:41 -05:00
dreambooth_folder_creation_gui.py Fix issue with LR 2022-12-29 21:17:41 -05:00
extract_lora_gui.py v20.6.0 2023-02-04 08:36:35 -05:00
git_caption_gui.py v20.6.0 2023-02-04 08:36:35 -05:00
merge_lora_gui.py Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
model_util.py Sync with kohya 2023/01/29 update 2023-01-29 11:10:06 -05:00
train_util.py Update to latest kohya_ss sd-script code 2023-02-03 14:40:03 -05:00
utilities.py v20.6.0 2023-02-04 08:36:35 -05:00
verify_lora_gui.py - Add new tool to verify LoRA weights produced by the trainer. Can be found under "Dreambooth LoRA/Tools/Verify LoRA 2023-01-22 11:40:14 -05:00
wd14_caption_gui.py Add default for caption extension tools 2023-01-20 18:41:37 -05:00