SdWeb
/
stable-diffusion-webui-wd14-tagger
mirror of https://github.com/picobyte/stable-diffusion-webui-wd14-tagger.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
Labeling extension for Automatic1111's Web UI
357 Commits
4 Branches
5 Tags
2.2 MiB
Python 86.8%
Shell 6.7%
JavaScript 5.7%
CSS 0.8%
 
 
 
 
Go to file
Roel Kluin e72d984bdb Apparently the onnxruntime entries were still giving issues. This changes 
makes it the user's responsibility to install the right onnxruntime
package
 		2023-11-04 12:58:30 +01:00
.github/workflows Create pylint.yml 2023-07-12 00:44:27 +02:00
docs docs: fix typos 2023-01-26 18:36:41 +09:00
javascript the issues seem resolved 2023-07-09 22:41:00 +02:00
json_schema only... like this 2023-07-25 20:49:23 +02:00
scripts lets try to get pylint working 2023-07-20 10:23:26 +02:00
shell_scripts no duplicates 2023-09-21 23:41:05 +02:00
tagger For the first image, if no queue name is provided, generate a random 2023-09-16 00:21:41 +02:00
.gitignore refactor: remove old ignores 2023-01-25 22:22:36 +09:00
CHANGELOG.md bump version 2023-09-16 01:47:01 +02:00
CONTRIBUTING.md Update CONTRIBUTING.md 2023-07-12 00:40:34 +02:00
README.ko.md Update README.ko.md 2023-08-01 23:54:03 -07:00
README.md Update README.md 2023-08-01 23:55:34 -07:00
install.py lets try to get pylint working 2023-07-20 10:23:26 +02:00
preload.py currently only one device is supported 2023-08-12 21:18:30 +02:00
pyproject.toml add pyproject.toml 2023-07-20 11:50:00 +02:00
requirements.txt Apparently the onnxruntime entries were still giving issues. This changes 2023-11-04 12:58:30 +01:00
style.css the issues seem resolved 2023-07-09 22:41:00 +02:00

README.md

Tagger for Automatic1111's WebUI

Interrogate booru style tags for single or multiple image files using various models, such as DeepDanbooru.

한국어를 사용하시나요? 여기에 한국어 설명서가 있습니다!

Disclaimer

I didn't make any models, and most of the code was heavily borrowed from the DeepDanbooru and MrSmillingWolf's tagger.

Installation

  1. Extensions -> Install from URL -> Enter URL of this repository -> Press Install button

    • or clone this repository under extensions/ 
      $ git clone https://github.com/picobyte/stable-diffusion-webui-wd14-tagger.git extensions/tagger

  2. (optional) Add interrogate model

    • Waifu Diffusion 1.4 Tagger by MrSmilingWolf

      Downloads automatically from the HuggingFace repository the first time you run it.

    • DeepDanbooru

      1. Various model files can be found below.

      2. Move the project folder containing the model and config to models/deepdanbooru

      3. The file structure should look like:

        models/
└╴deepdanbooru/
  ├╴deepdanbooru-v3-20211112-sgd-e28/
  │ ├╴project.json
  │ └╴...
  │
  ├╴deepdanbooru-v4-20200814-sgd-e30/
  │ ├╴project.json
  │ └╴...
  │
  ├╴e621-v3-20221117-sgd-e32/
  │ ├╴project.json
  │ └╴...
  │
  ...

  3. Start or restart the WebUI.

    • or you can press refresh button after Interrogator dropdown box.
    • "You must close stable diffusion completely after installation and re-run it!"

Model comparison

Model comparison

Screenshot

Screenshot

Artwork made by hecattaart

Copyright

Public domain, except borrowed parts (e.g. dbimutils.py)