NEWWhy single embeddings fail for video.Read the post →
    Models/Captioning/Qwen/Qwen3-VL-8B-Instruct
    HFScene Captioning

    Qwen3-VL-8B-Instruct

    by Qwen

    2.8Mdl/month
    HuggingFaceUse in Pipeline
    Identifiers
    Model ID
    Qwen/Qwen3-VL-8B-Instruct
    Feature URI
    mixpeek://image_extractor@v1/qwen3_vl_8b_v1

    Specification

    FrameworkHF
    OrganizationQwen
    FeatureScene Captioning
    Outputtext
    Modalitiesvideo, image
    RetrieverSemantic Search
    Downloads/mo2.8M

    Build a pipeline with Qwen3-VL-8B-Instruct

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Open Pipeline Builder

    Alternative Models

    Salesforce/blip2-opt-2.7b
    Scene Captioning
    microsoft/Florence-2-large
    Scene Captioning
    google/paligemma2-3b-mix-448
    Scene Captioning
    google/gemma-4-4b-it
    Scene Captioning