IDEA-Research/Grounding-DINO-1.5-API

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1143 stars · 46 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

computer-vision image-processing machine-learning sdk computer-vision artificial-intelligence machine-learning python cloud object-detection open-vocabulary-detection zero-shot-detection grounding-dino api-client vision-language

Member repositories

For agents

markdown · JSON · MCP: product_card(name="IDEA-Research/Grounding-DINO-1.5-API")