bytedance / sa2va-8b-image

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

  • Public
  • 57 runs
  • GitHub
  • Weights
  • Paper
  • License
Run with an API
Playground API Examples README Versions
  1. Author
    @lucataco
    Version
    cuda12.4-python3.10-torch2.4.0-X64
    Commit
    6f59e55da541fad1ffc370419265eab6f511569f

    956baf05

    Latest

    Release notes

    fixed masking

  2. Author
    @lucataco
    Version
    cuda12.4-python3.10-torch2.4.0-X64
    Commit
    6f59e55da541fad1ffc370419265eab6f511569f

    27bf9e1f