bytedance/sa2va-8b-image

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

Public
13K runs
Run with an API
Pricing
GitHub
License
Weights
Paper
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