Releases: bmaltais/kohya_ss
Releases · bmaltais/kohya_ss
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.
v20.5.2
v20.5.0
v20.0.4
What's Changed
- Add support for `network_alpha` under the Training tab and support for `--training_comment` under the Folders tab.
- Add ``--network_alpha`` option to specify ``alpha`` value to prevent underflows for stable training. Thanks to CCRcmcpe!
- Details of the issue are described in https://github.com/kohya-ss/sd-webui-additional-networks/issues/49 .
- The default value is ``1``, scale ``1 / rank (or dimension)``. Set same value as ``network_dim`` for same behavior to old version.
- LoRA with a large dimension (rank) seems to require a higher learning rate with ``alpha=1`` (e.g. 1e-3 for 128-dim, still investigating).
- For generating images in Web UI, __the latest version of the extension ``sd-webui-additional-networks`` (v0.3.0 or later) is required for the models trained with this release or later.__
- Add logging for the learning rate for U-Net and Text Encoder independently, and for running average epoch loss. Thanks to mgz-dev!
- Add more metadata such as dataset/reg image dirs, session ID, output name etc... See https://github.com/kohya-ss/sd-scripts/pull/77 for details. Thanks to space-nuko!
- __Now the metadata includes the folder name (the basename of the folder contains image files, not fullpath).__ If you do not want it, disable metadata storing with ``--no_metadata`` option.
- Add ``--training_comment`` option. You can specify an arbitrary string and refer to it by the extension.
Full Changelog: v20.3.1...v20.0.4
v20.3.1
v20.3.0
v20.2.1
v20.1
v20.0
What's Changed
- Update code base to match latest kohys_ss code upgrade in https://github.com/kohya-ss/sd-scripts
- Add vae support to dreambooth GUI
- Add gradient_checkpointing, gradient_accumulation_steps, mem_eff_attn, shuffle_caption to finetune GUI
- Add gradient_accumulation_steps, mem_eff_attn to dreambooth lora gui
Full Changelog: v19.4.1...v20.0
v19.4.2
What's Changed
- Add find/replace option to Basic Caption utility
- Add resume training and save_state option to finetune UI
Full Changelog: v19.4.1...v19.4.2