LocateAnything-3B

Name: LocateAnything-3B
Author: nvidia

by nvidia

Open-vocabulary visual grounding for locating arbitrary objects in images

95Kdl/month

2,963likes

3.8Bparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

nvidia/LocateAnything-3B

Feature URI

mixpeek://image_extractor@v1/nvidia_locateanything_3b_v1

Overview

LocateAnything 3B is an NVIDIA vision-language model for open-vocabulary localization. Instead of predicting only a fixed detector label set, it uses a text prompt to identify and localize the requested visual target.

On Mixpeek, LocateAnything is useful when an agent needs structured evidence from images or frames but the target classes are not known when the pipeline is built. The agent can ask for objects, UI components, safety conditions, or domain-specific items and store the resulting boxes as searchable metadata.

Architecture

3B-class vision-language model exposed as an image-text-to-text Transformers checkpoint. It accepts visual input plus a grounding prompt and returns localization-oriented outputs.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so LocateAnything-3B 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.