DA3-LARGE-1.1

Name: DA3-LARGE-1.1
Author: depth-anything

by depth-anything

Depth Anything V3 Large checkpoint for spatial scene retrieval

93Kdl/month

14likes

411Mparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

depth-anything/DA3-LARGE-1.1

Feature URI

mixpeek://image_extractor@v1/depth_anything_v3_large_v1

Overview

Depth Anything V3 Large is a newer monocular depth checkpoint for estimating dense depth maps from images. It improves the depth channel available to perception pipelines where spatial layout matters as much as semantic content.

On Mixpeek, Depth Anything V3 Large can enrich images or video frames with depth-derived metadata such as foreground ratio, depth bands, relative distance, and scene layout. Agents can use those signals to find clips by spatial evidence before calling a heavier reasoning model.

Architecture

Depth estimation model from the Depth Anything V3 family. It produces dense per-pixel depth maps from single images and is exposed through the HuggingFace depth-estimation pipeline.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so DA3-LARGE-1.1 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.