An app that tries to leverage LLMs and Vision API to create real-life captions
If you are interested please contact me at one of the places listed here: https://apolotary.com/
Slides
https://docs.google.com/presentation/d/1J5kJ4mM1GrQFuY-WCx8NQMKoSphUFHdAwf4LUllU0rg/edit?usp=sharing
Video
YouTube mirror