NEWAgents can now see video via MCP.Try it now →
    Models/Image Segmentation/kumuji/Sa2VA-i-8B
    Image Segmentationtransformersapache-2.0

    Sa2VA-i-8B

    by kumuji

    Identifier
    Model ID
    kumuji/Sa2VA-i-8B

    Tags

    transformerssafetensorssa2va_chatfeature-extractionSa2VAcustom_codeimage-segmentationmultilingualarxiv:2509.19082arxiv:2501.04001base_model:ByteDance/Sa2VA-8Bbase_model:merge:ByteDance/Sa2VA-8Blicense:apache-2.0region:us

    Use Sa2VA-i-8B on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval, all through the Mixpeek pipeline builder.

    Open Pipeline Builder