NEWVectors or files. Pick a path.Start →
    Models/Detection & Recognition/google/owlv2-large-patch14-ensemble
    HFObject Detectionapache-2.0

    owlv2-large-patch14-ensemble

    by google

    Open-vocabulary OWLv2 detector for text-conditioned object search

    73Kdl/month
    39likes
    438Mparams
    Identifiers
    Model ID
    google/owlv2-large-patch14-ensemble
    Feature URI
    mixpeek://image_extractor@v1/google_owlv2_large_ensemble_v1

    Overview

    OWLv2 Large Patch14 Ensemble is Google's open-vocabulary detector for zero-shot object localization. It lets a pipeline search for objects described in text instead of relying only on a fixed supervised label set.

    On Mixpeek, OWLv2 is useful when an agent needs to find visual categories that change by task: a specific product shape, a UI control, damaged equipment, or a visual policy violation. The detector outputs boxes and labels that can be stored, filtered, and joined with embeddings or captions.

    Architecture

    Vision Transformer based open-vocabulary object detector. It aligns text queries and image regions so arbitrary text labels can guide detection at inference time.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    await mx.collections.ingest({
    collection_id: "product-images",
    source: { url: "s3://catalog/images/" },
    feature_extractors: [{
    feature: "object_detection",
    model: "google/owlv2-large-patch14-ensemble"
    }]
    });

    Capabilities

    • Zero-shot object detection
    • Text-conditioned visual localization
    • Strong fit for dynamic agent queries
    • Apache 2.0 license

    Use Cases on Mixpeek

    Search frames for object classes not known during ingestion design
    Find UI controls or visual states from natural-language prompts
    Build long-tail visual filters over product and media libraries
    Pair open-vocabulary boxes with scene captions for agent evidence

    Specification

    FrameworkHF
    Organizationgoogle
    FeatureObject Detection
    Outputbbox + label
    Modalitiesvideo, image
    RetrieverObject Filter
    Parameters438M
    Licenseapache-2.0
    Downloads/mo73K
    Likes39

    Research Paper

    OWLv2 Large Patch14 Ensemble

    arxiv.org

    Build a pipeline with owlv2-large-patch14-ensemble

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

    Open Studio