Awesome

This branch is unmaintained! https://github.com/toriato/stable-diffusion-webui-wd14-tagger/issues/108

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

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

Extensions -> Install from URL -> Enter URL of this repository -> Press Install button
- or clone this repository under extensions/
```
$ git clone https://github.com/toriato/stable-diffusion-webui-wd14-tagger.git extensions/tagger
```
(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.
    - DeepDanbooru models
    - e621 model by 🐾Zack🐾#1984 (link contains NSFW contents!)
  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
  │ └╴...
  │
  ...
```
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!"

Artwork made by hecattaart

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