File size: 499 Bytes
7925ce3
 
 
 
 
95ad869
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
TODO:
- Fix sample images
- Allow other image types
- Allow the model to iteratively sample text
- Add nucleus size and other advanced options


<p>
Please note that this model was explicitly not trained on images of people, and as a result is not designed to caption images with humans.
This demo accompanies our paper RedCaps
Created by [Karan Desai](mailto:[email protected]), [Gaurav Kaul](mailto:[email protected]), [Zubin Aysola](mailto:[email protected]), [Justin Johnson]([email protected])
</p>