Instructions to use bep256/clip-tags with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PerceptionEncoder
How to use bep256/clip-tags with PerceptionEncoder:
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("bep256/clip-tags", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add PE Core B/16 and L/14 tags; rename vocabulary
Verified signature1973bb7
-
Add simple tags
Verified signaturedf99841 -
Store the vocabulary as TSV
Verified signaturecf61bf3 -
Store the vocabulary as safetensors
Verified signature9829838 -
Add tag vocabulary and embeddings for MetaCLIP 2 and SigLIP2
Verified signaturefe90ba1 -
initial commit
Verified signaturedc8d747