datong-new / sam-point

Cold

Public
116 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

datong-new/sam-point:a121a2ad00780aa18585c7381f012aefe4cbe25b4126125d43519358113c6124

Model

datong-new/sam-point:a121a2ad

pddszgzcppao5r4zxerxjuyj4e

Status

Succeeded

Source

Web

Hardware

Total duration

17.9s

Created

over 1 year ago

Input

image
input_points: [[950,950]]

{
  "image": "https://replicate.delivery/pbxt/KX6QL1Amx5wP1zDvjyr5QNeObbrF7TR1aHGPA6JzNoBEdVEV/cup1.png",
  "input_points": "[[950,950]]"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run datong-new/sam-point using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "datong-new/sam-point:a121a2ad00780aa18585c7381f012aefe4cbe25b4126125d43519358113c6124",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KX6QL1Amx5wP1zDvjyr5QNeObbrF7TR1aHGPA6JzNoBEdVEV/cup1.png",
      input_points: "[[950,950]]"
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 datong-new/sam-point using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "datong-new/sam-point:a121a2ad00780aa18585c7381f012aefe4cbe25b4126125d43519358113c6124",
    input={
        "image": "https://replicate.delivery/pbxt/KX6QL1Amx5wP1zDvjyr5QNeObbrF7TR1aHGPA6JzNoBEdVEV/cup1.png",
        "input_points": "[[950,950]]"
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run datong-new/sam-point 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": "datong-new/sam-point:a121a2ad00780aa18585c7381f012aefe4cbe25b4126125d43519358113c6124",
    "input": {
      "image": "https://replicate.delivery/pbxt/KX6QL1Amx5wP1zDvjyr5QNeObbrF7TR1aHGPA6JzNoBEdVEV/cup1.png",
      "input_points": "[[950,950]]"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/datong-new/sam-point@sha256:a121a2ad00780aa18585c7381f012aefe4cbe25b4126125d43519358113c6124 \
  -i 'image="https://replicate.delivery/pbxt/KX6QL1Amx5wP1zDvjyr5QNeObbrF7TR1aHGPA6JzNoBEdVEV/cup1.png"' \
  -i 'input_points="[[950,950]]"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 r8.im/datong-new/sam-point@sha256:a121a2ad00780aa18585c7381f012aefe4cbe25b4126125d43519358113c6124
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KX6QL1Amx5wP1zDvjyr5QNeObbrF7TR1aHGPA6JzNoBEdVEV/cup1.png",
      "input_points": "[[950,950]]"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

Generated in

4.3 seconds

Tweak it ShareReport

Prediction

datong-new/sam-point:fdb48954f117ec15700619f48964c96d7277ab85051dadf03f9866d96664639f

Model

datong-new/sam-point:fdb48954

o6chrf3bifwoqblrylwjjyf3qa

Status

Succeeded

Source

Web

Hardware

A40

Total duration

21.5s

Created

over 1 year ago

Input

image
input_points: [[950,500], [396, 494]]

{
  "image": "https://replicate.delivery/pbxt/KXCckbfYjgvN0x2rzdaTA68eWX2UdfZvc0sp4hhSAzpA5Kzx/2.png",
  "input_points": "[[950,500], [396, 494]]"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run datong-new/sam-point using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "datong-new/sam-point:fdb48954f117ec15700619f48964c96d7277ab85051dadf03f9866d96664639f",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KXCckbfYjgvN0x2rzdaTA68eWX2UdfZvc0sp4hhSAzpA5Kzx/2.png",
      input_points: "[[950,500], [396, 494]]"
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 datong-new/sam-point using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "datong-new/sam-point:fdb48954f117ec15700619f48964c96d7277ab85051dadf03f9866d96664639f",
    input={
        "image": "https://replicate.delivery/pbxt/KXCckbfYjgvN0x2rzdaTA68eWX2UdfZvc0sp4hhSAzpA5Kzx/2.png",
        "input_points": "[[950,500], [396, 494]]"
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run datong-new/sam-point 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": "datong-new/sam-point:fdb48954f117ec15700619f48964c96d7277ab85051dadf03f9866d96664639f",
    "input": {
      "image": "https://replicate.delivery/pbxt/KXCckbfYjgvN0x2rzdaTA68eWX2UdfZvc0sp4hhSAzpA5Kzx/2.png",
      "input_points": "[[950,500], [396, 494]]"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/datong-new/sam-point@sha256:fdb48954f117ec15700619f48964c96d7277ab85051dadf03f9866d96664639f \
  -i 'image="https://replicate.delivery/pbxt/KXCckbfYjgvN0x2rzdaTA68eWX2UdfZvc0sp4hhSAzpA5Kzx/2.png"' \
  -i 'input_points="[[950,500], [396, 494]]"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 r8.im/datong-new/sam-point@sha256:fdb48954f117ec15700619f48964c96d7277ab85051dadf03f9866d96664639f
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KXCckbfYjgvN0x2rzdaTA68eWX2UdfZvc0sp4hhSAzpA5Kzx/2.png",
      "input_points": "[[950,500], [396, 494]]"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.