KohyaSS/requirements.txt

accelerate==0.15.0
transformers==4.26.0
ftfy
albumentations
opencv-python
einops
diffusers[torch]==0.10.2
pytorch_lightning
bitsandbytes==0.35.0
tensorboard
safetensors==0.2.6
gradio==3.16.2
altair
easygui
tk
# for BLIP captioning
requests
timm
fairscale
# for WD14 captioning
tensorflow<2.11
huggingface-hub
# for kohya_ss library
.
Update to v17 New GUI 2022-12-13 18:49:14 +00:00			`accelerate==0.15.0`
Update to latest kohya_ss sd-script code 2023-02-03 19:40:03 +00:00			`transformers==4.26.0`
1st commit 2022-10-30 15:15:09 +00:00			`ftfy`
			`albumentations`
			`opencv-python`
			`einops`
Update to v17 New GUI 2022-12-13 18:49:14 +00:00			`diffusers[torch]==0.10.2`
Update install instructions 2022-11-28 02:07:57 +00:00			`pytorch_lightning`
			`bitsandbytes==0.35.0`
Update requirements.txt 2022-12-03 23:31:12 +00:00			`tensorboard`
Update to v17 New GUI 2022-12-13 18:49:14 +00:00			`safetensors==0.2.6`
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 13:36:35 +00:00			`gradio==3.16.2`
Adding improved elements to GUI 2022-12-14 19:40:24 +00:00			`altair`
v18.1: Model conversion utility 2022-12-18 18:11:10 +00:00			`easygui`
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 13:36:35 +00:00			`tk`
- Fix file/folder opening behind the browser window - Add WD14 and BLIP captioning to utilities - Improve overall GUI layout 2022-12-19 14:22:52 +00:00			`# for BLIP captioning`
			`requests`
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 13:36:35 +00:00			`timm`
			`fairscale`
- Fix file/folder opening behind the browser window - Add WD14 and BLIP captioning to utilities - Improve overall GUI layout 2022-12-19 14:22:52 +00:00			`# for WD14 captioning`
			`tensorflow<2.11`
			`huggingface-hub`
			`# for kohya_ss library`
v18.1: Model conversion utility 2022-12-18 18:11:10 +00:00			`.`