✋ This model is not published yet.

You can claim this model if you're @j-min on GitHub. Contact us.

Unifying Vision-and-Language Tasks via Text Generation

Cold

Public

714 runs

License

GitHub

Paper

Playground API Examples README Versions

Prediction

j-min/vl-t5:560b0f84

Model

j-min/vl-t5:560b0f84

dyrpwgljczhabhnrwfviv633qi

Status

Succeeded

Source

Web

Hardware

–

Total duration

1m 55s

Created

over 3 years ago

Input

image
question: what is in the picture?

{
  "image": "https://replicate.delivery/mgxm/d80b0dac-f162-4c23-ae6c-9f5a72725900/demo.jpg",
  "question": "what is in the picture?"
}

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 j-min/vl-t5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "j-min/vl-t5:560b0f8439191dddf5babf188e34b63fb4e4d679fdb2c10d82988d25df798b7c",
  {
    input: {
      image: "https://replicate.delivery/mgxm/d80b0dac-f162-4c23-ae6c-9f5a72725900/demo.jpg",
      question: "what is in the picture?"
    }
  }
);

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 j-min/vl-t5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "j-min/vl-t5:560b0f8439191dddf5babf188e34b63fb4e4d679fdb2c10d82988d25df798b7c",
    input={
        "image": "https://replicate.delivery/mgxm/d80b0dac-f162-4c23-ae6c-9f5a72725900/demo.jpg",
        "question": "what is in the picture?"
    }
)

print(output)

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

Run j-min/vl-t5 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": "j-min/vl-t5:560b0f8439191dddf5babf188e34b63fb4e4d679fdb2c10d82988d25df798b7c",
    "input": {
      "image": "https://replicate.delivery/mgxm/d80b0dac-f162-4c23-ae6c-9f5a72725900/demo.jpg",
      "question": "what is in the picture?"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

dog

Generated in

5.6 seconds

Tweak it Iterate in playground Share Report

Prediction

j-min/vl-t5:560b0f84

Model

j-min/vl-t5:560b0f84

cfdj2xlfwraxdjyivkbwa3b3jq

Status

Succeeded

Source

Web

Hardware

–

Total duration

7.4s

Created

over 3 years ago

Input

image
question: where are they?

{
  "image": "https://replicate.delivery/mgxm/8427a624-2fb8-46c5-b2b1-726a5ee8e474/demo.jpg",
  "question": "where are they?"
}

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 j-min/vl-t5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "j-min/vl-t5:560b0f8439191dddf5babf188e34b63fb4e4d679fdb2c10d82988d25df798b7c",
  {
    input: {
      image: "https://replicate.delivery/mgxm/8427a624-2fb8-46c5-b2b1-726a5ee8e474/demo.jpg",
      question: "where are they?"
    }
  }
);

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 j-min/vl-t5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "j-min/vl-t5:560b0f8439191dddf5babf188e34b63fb4e4d679fdb2c10d82988d25df798b7c",
    input={
        "image": "https://replicate.delivery/mgxm/8427a624-2fb8-46c5-b2b1-726a5ee8e474/demo.jpg",
        "question": "where are they?"
    }
)

print(output)

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

Run j-min/vl-t5 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": "j-min/vl-t5:560b0f8439191dddf5babf188e34b63fb4e4d679fdb2c10d82988d25df798b7c",
    "input": {
      "image": "https://replicate.delivery/mgxm/8427a624-2fb8-46c5-b2b1-726a5ee8e474/demo.jpg",
      "question": "where are they?"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

beach

Generated in

7.3 seconds

Tweak it Iterate in playground Share Report

Want to make some of these yourself?

Run this model

Prediction

Input

Output

Prediction

Input

Output

Logs (dyrpwgljczhabhnrwfviv633qi)

Logs (cfdj2xlfwraxdjyivkbwa3b3jq)