Instructions to use SmilingWolf/wd-v1-4-moat-tagger-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use SmilingWolf/wd-v1-4-moat-tagger-v2 with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("SmilingWolf/wd-v1-4-moat-tagger-v2") - Notebooks
- Google Colab
- Kaggle
Creating Copyright Illustration Tag Filter Mechanism using Illustration Analysis Model
I am a freeware developer in Japan.
Your created illustration analysis model is fantastic, and I'm using it in my software.
I would like to create a mechanism to filter copyright illustration tags using this model.
If there is a way to extract the list of copyright illustration tags included in this model, please let me know.
I'm not the author of this model, but I hope this helps.
All tags have categories, which can be seen in /selected_tags.csv.
https://huggingface.co/SmilingWolf/wd-v1-4-moat-tagger-v2/blob/main/selected_tags.csv
The category number means:
0: general (e.g.1girl)4: character (e.g.hatsune_miku)9: rating (e.g.sensitive)
So if you want to get character tags, you should filter tags whose category number is 4 instead of 0.
An example of the code to filter character tags:
https://huggingface.co/spaces/SmilingWolf/wd-v1-4-tags/blob/main/app.py#L92
Thank you very much! Your advice was very helpful