adirik / grounding-dino

Detect everything with language!

Warm

Public
7.3M runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Prediction

adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa

Model

adirik/grounding-dino:efd10a8d

57jvoqzc4xbh2in6gow2oq7hci

Status

Succeeded

Source

Web

Hardware

Total duration

1.7s

Created

over 1 year ago

Input

image
query: pink mug
box_threshold: 0.2
text_threshold: 0.2
show_visualisation

{
  "image": "https://replicate.delivery/pbxt/JlgUQIQCDemKg7bnfn5zKMqLgAPrZdpMMHzkXgHX5HUlbw9z/mugs.webp",
  "query": "pink mug",
  "box_threshold": 0.2,
  "text_threshold": 0.2,
  "show_visualisation": true
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/grounding-dino using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlgUQIQCDemKg7bnfn5zKMqLgAPrZdpMMHzkXgHX5HUlbw9z/mugs.webp",
      query: "pink mug",
      box_threshold: 0.2,
      text_threshold: 0.2,
      show_visualisation: true
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run adirik/grounding-dino using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa",
    input={
        "image": "https://replicate.delivery/pbxt/JlgUQIQCDemKg7bnfn5zKMqLgAPrZdpMMHzkXgHX5HUlbw9z/mugs.webp",
        "query": "pink mug",
        "box_threshold": 0.2,
        "text_threshold": 0.2,
        "show_visualisation": True
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run adirik/grounding-dino using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlgUQIQCDemKg7bnfn5zKMqLgAPrZdpMMHzkXgHX5HUlbw9z/mugs.webp",
      "query": "pink mug",
      "box_threshold": 0.2,
      "text_threshold": 0.2,
      "show_visualisation": true
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

detections

{ "bbox": [ 19, 204, 408, 563 ], "label": "pink mug", "confidence": 0.8077122569084167 }

{ "bbox": [ 545, 263, 952, 650 ], "label": "pink mug", "confidence": 0.7644544839859009 }

{ "bbox": [ 416, 60, 764, 380 ], "label": "pink mug", "confidence": 0.4754282832145691 }

{ "bbox": [ 909, 161, 1078, 487 ], "label": "pink mug", "confidence": 0.43150201439857483 }

result_image

Generated in

1.7 seconds

Tweak it ShareReport

Prediction

adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa

Model

adirik/grounding-dino:efd10a8d

24j3axzc4tmw2gpcgudgd6j7ru

Status

Succeeded

Source

Web

Hardware

Total duration

1.7s

Created

over 1 year ago

Input

image
query: a cat, a dog
box_threshold: 0.25
text_threshold: 0.2
show_visualisation

{
  "image": "https://replicate.delivery/pbxt/JlgUyeh3hBWO2SArXLtWqHVfDRSHuokfF1qkLW2Q6uHjLGXS/Two-Dogs-With-Cat.jpg",
  "query": "a cat, a dog",
  "box_threshold": 0.25,
  "text_threshold": 0.2,
  "show_visualisation": true
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run adirik/grounding-dino using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlgUyeh3hBWO2SArXLtWqHVfDRSHuokfF1qkLW2Q6uHjLGXS/Two-Dogs-With-Cat.jpg",
      query: "a cat, a dog",
      box_threshold: 0.25,
      text_threshold: 0.2,
      show_visualisation: true
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run adirik/grounding-dino using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa",
    input={
        "image": "https://replicate.delivery/pbxt/JlgUyeh3hBWO2SArXLtWqHVfDRSHuokfF1qkLW2Q6uHjLGXS/Two-Dogs-With-Cat.jpg",
        "query": "a cat, a dog",
        "box_threshold": 0.25,
        "text_threshold": 0.2,
        "show_visualisation": True
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run adirik/grounding-dino using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "adirik/grounding-dino:efd10a8ddc57ea28773327e881ce95e20cc1d734c589f7dd01d2036921ed78aa",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlgUyeh3hBWO2SArXLtWqHVfDRSHuokfF1qkLW2Q6uHjLGXS/Two-Dogs-With-Cat.jpg",
      "query": "a cat, a dog",
      "box_threshold": 0.25,
      "text_threshold": 0.2,
      "show_visualisation": true
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.