nateraw / video-llava

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

  • Public
  • 486.3K runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Versions
  1. Author
    @lucataco
    Version
    22.04
    Commit
    1be81beb90c6064821650bf04e15ae3cf01273fe

    26387f81

    Latest

    Release notes

    Updated to work with Video-LLaVA-7B commit b1d6a63f98cc93153d3e9ff295bd6dee5ffafe4c