File size: 230 Bytes
df14da1
 
 
 
 
1
2
3
4
5
# Model Description

This is a ViT based style classifier used for Pony V7 captioning.

See the [captioning colab](https://colab.research.google.com/drive/19PG-0ltob8EynxUZSwOdjMFmqyJ7ZOCB#scrollTo=1ZwQT6sZaJpE) for usage details.