# IDEA-Research/Grounding-DINO-1.5-API

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

Repository: https://github.com/IDEA-Research/Grounding-DINO-1.5-API
Canonical: https://ross.abutalabs.com/products/grounding-dino-15-api
Homepage: https://arxiv.org/abs/2405.10300
Language: Python
License: Apache-2.0
License Family: permissive
Topics: grounding-dino, object-detection, open-set, foundation-model, open-vocabulary-detection, open-world, zero-shot-object-detection
Last push: 2025-01-21T11:24:30+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 2, release rhythm 35, longevity 60
- inputs: {"age_days": 841, "days_push": 589, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1143, forks 46 (observed 2026-08-28T04:03:44.924601+00:00)

## What it is
Python examples and API client for Grounding DINO 1.5/1.6, IDEA Research's open-world (open-set) object detection model series hosted on DeepDataSpace. Models detect arbitrary objects from natural-language text prompts with zero-shot generalization, accessed via a paid/token-gated cloud API.

## Use cases
- detect arbitrary objects in images from a text prompt
- zero-shot object detection without training a custom model
- find specific objects described in natural language in photos
- open-vocabulary detection for rare or unusual object categories
- build a pipeline that labels images with bounding boxes from text queries
- detect animals or text in images without fine-tuning

## When to choose
- you need state-of-the-art zero-shot/open-set detection via a hosted API
- you want to detect custom object categories described in text without training
- you can accept a cloud API with token quotas and paid usage

## When to avoid
- you need fully local/offline inference (use open-source Grounding DINO instead)
- you cannot rely on an external paid API or token application process
- you need real-time edge deployment with no network access

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, machine-learning, sdk
- domain: computer-vision, artificial-intelligence, machine-learning
- platform: python, cloud
- tags: object-detection, open-vocabulary-detection, zero-shot-detection, grounding-dino, api-client, vision-language

## Member repositories
- IDEA-Research/Grounding-DINO-1.5-API (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.924601+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:34:54.335873+00:00, confidence not recorded.
  - readme: https://github.com/IDEA-Research/Grounding-DINO-1.5-API (fetched 2026-08-28T04:03:44.924601+00:00, sha ee9f8e6d78aa)
  - homepage: https://arxiv.org/abs/2405.10300 (fetched 2026-08-29T12:40:08.901498+00:00, sha a1f48c14a965)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:40:08.931950+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:40:08.926445+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:40:08.935085+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:40:08.929086+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.