日本語 Readme

This is a WebUI tool to edit training dataset for Text2Image Models.
This is a standalone version of Dataset Tag Editor, which is an extension for Stable Diffusion web UI by AUTOMATIC1111.
Please do not put into extensions folder of AUTOMATIC1111's webUI.

It works well with text captions in comma-separated style (such as the tags generated by DeepDanbooru interrogator).

Caption in the filenames of images can be loaded, but edited captions can only be saved in the form of text files.

(Pros)

• Avoid bugs caused by specific version of gradio
• Much faster startup and running
• More captioning interrogators (GIT (paper (arXiv)), BLIP-2 (paper (arXiv)): may extremely heavy)

(Cons)

• Hijacked CLIP tokenizer is not available (which has SDwebUI specific features like embedding, emphasis, …)
• No more support for old Python < 3.9

All requirements are listed in requirements.txt

Please install the followings first:

• Python >= 3.9 (Developed on 3.10.11)
• PyTorch with CUDA >= 1.10.0 (onnx-pytorch requirement; for TorchDeepDanbooru)
  PyTorch version mostly depends on transformers, please follow the instruction to install transformers if install specific version manually.

If you want to use DirectML, please install manually in venv (install pytorch-directml to enable, not tested).

Just run install.bat

Run following commands on the root directory of this repo.

python -m venv --system-site-packages venv
source ./venv/Scripts/activate
pip install -r requirements.txt

(Note: just .\venv\Scripts\activate is needed to activate venv on Windows)

You can see available command line args with -h or --help option.

Just run launch_user.bat

source ./venv/bin/activate
python scripts/launch.py [arguments]

Note. "tag" means each blocks of caption separated by commas.

• Edit and save captions in text file (webUI style) or json file (kohya-ss sd-scripts metadata)
• Edit captions while viewing related images
• Search tags
• Filter images to edit their caption by tags
  • AND/OR logic can be used in each Positive/Negative filters
• Batch replace/remove/append tags
• Batch sort tags
• Batch search and replace
  • regular expression can be used
• Use interrogators
  • BLIP, BLIP2, GIT, DeepDanbooru, SmilingWolf's WDv1.4 Tagger (v1, v2 and some variants of them)
• Batch remove image and/or caption files

1. Make dataset
   • better to use already cropped images
2. Load them
   • use interrogator if needed
3. Edit their captions
   • filter images you want to edit by tags in "Filter by Tags" tab
   • filter images manually in "Filter by Selection" tab
   • replace/remove tags or append new tags in "Batch Edit Captions" tab
   • edit captions individually in "Edit Caption of Selected Image" tab
     • you also can use interrogator here
   • move/delete files in "Move or Delete Files" tab if needed
4. Click "Save all changes" button

Basic workflow is as follows:

1. Filter images
2. Batch edit

Please note that all batch editing will be applyed only to displayed images (=filtered images).

• I want to edit all at once
  No filter is required.
• Some images require editing
  1. They should / shouldn't already have same tag(s)
     Go to "Filter by Tags" so that the only images to be edited are displayed.
  2. They have nothing in common
     Go to "Filter by Selection" and apply.
     Images can also be added to the filter by pushing [Enter] key.

• I want to add some new tags

  1. Go to "Batch Edit Captions" tab
  2. Append tags to "Edit tags" textbox
  3. Push "Apply changes to filtered images" button
     
     "foo" and "bar" will be added to all images displayed.

• I want to replace the tags which are common to displayed images

  1. Go to "Batch Edit Captions" tab
  2. Replace tags in "Edit tags" textbox
  3. Push "Apply changes to filtered images" button
     
     "male focus" and "solo" will be replaced with "foo" and "bar".

• I want to remove some tags
  The same as replacing. Just replace the tags with "blank".
  Also you can use "Remove" tab in "Batch Edit Captions".

• I want to add/replace/remove tags more flexibly

  1. Go to "Batch Edit Captions" tab
  2. Use "Search and Replace" with "Use regex" checked
     
     "1boy", "2boys", … will be replaced with "1girl", "2girls", … in each tags of images displayed.
     A comma will be regarded as the sepalator of two tags.
     By using regex, you can add/replace/remove tags according to more complex conditions.

Set folder to store temporaly image in the "Settings" tab. Input path in "Directory to save temporary files" and check "Force using temporary file…"

• To install PyTorch in your system to share it with other scripts
  1. Follow the PyTorch installation guide with -U (--upgrade) option
     (example) pip3 install -U torch torchvision --index-url https://download.pytorch.org/whl/cu118
  2. Remove venv folder
  3. Run install.bat
• To install PyTorch only in venv
  1. Open launch_user.bat with some text editor
  2. Change the 3rd line to set COMMANDLINE_ARGS="--force-install-torch cu118" (you can choose from cu117, cu118 or cpu)
  3. Run launch_user.bat
  4. (Remove the command line argument)