owlvit-large-patch14

Name: owlvit-large-patch14
Author: google

by google

Simple open-vocabulary object detection with Vision Transformers

10Kdl/month

29likes

~300Mparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

google/owlvit-large-patch14

Feature URI

mixpeek://image_extractor@v1/google_owlvit_large_v1

Overview

OWL-ViT transfers image-text pre-trained models to open-vocabulary object detection using a standard ViT with minimal modifications. It supports both text-conditioned zero-shot detection and one-shot image-conditioned detection.

On Mixpeek, OWL-ViT provides a clean, well-scaling detection model that improves consistently with larger pre-trained backbones and more data.

Architecture

Plain Vision Transformer (ViT-L/14) pre-trained with contrastive image-text learning, then fine-tuned end-to-end for detection. No detection-specific backbone changes needed.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so owlvit-large-patch14 runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // Boxes, masks, depth maps and anomaly scores are structured
          // results, not vectors. They go in payload and are reachable
          // through pre_filters on a retriever, not through similarity.
          payload: {
            detections: modelOutput,
            source_key: "archive/2026/asset-00412",
          },
        },
      ],
    }),
  },
);

// No managed alternative for an open label set. Two extractors do emit a
// bbox, for the one thing each detects: document_graph_extractor@v1 per
// layout block, face_identity_extractor@v1 per face. Nothing ships that
// returns masks, depth maps or anomaly scores.