Skip to content

Latest commit

 

History

History
4 lines (4 loc) · 407 Bytes

README.md

File metadata and controls

4 lines (4 loc) · 407 Bytes

This is a project investigating the possibility of building a text to image model without using any labeled training data, relying only on CLIP and unlabeled images. The best description of the project is here. As of this point, there's little reason for anybody but me to run any of this code.