Prediction

Model

salesforce/blip:5a977fcb

mojxr2cdczexzjxsvjuvbummqi

Status

Succeeded

Source

Web

Hardware

–

Total duration

1.2s

Created

almost 4 years ago

Webhook

–

Input

image: https://replicate.delivery/mgxm/ceba852d-1e52-4004-ae8b-86869790dbc3/beautiful-scenery-wallpapers-moonlight-beauty.jpg
task: visual_question_answering
question: what is standing on the rock?

{
  "image": "https://replicate.delivery/mgxm/ceba852d-1e52-4004-ae8b-86869790dbc3/beautiful-scenery-wallpapers-moonlight-beauty.jpg",
  "question": "what is standing on the rock?",
  "task": "visual_question_answering"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_GU7**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";

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

Run salesforce/blip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "salesforce/blip:5a977fcb091363cc3938cc870c9f6242f5938267040e6837373387bb90d23099",
  {
    input: {
      image: "https://replicate.delivery/mgxm/ceba852d-1e52-4004-ae8b-86869790dbc3/beautiful-scenery-wallpapers-moonlight-beauty.jpg",
      question: "what is standing on the rock?",
      task: "visual_question_answering"
    }
  }
);

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_GU7**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run salesforce/blip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "salesforce/blip:5a977fcb091363cc3938cc870c9f6242f5938267040e6837373387bb90d23099",
    input={
        "image": "https://replicate.delivery/mgxm/ceba852d-1e52-4004-ae8b-86869790dbc3/beautiful-scenery-wallpapers-moonlight-beauty.jpg",
        "question": "what is standing on the rock?",
        "task": "visual_question_answering"
    }
)

# The salesforce/blip model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/salesforce/blip/api#output-schema
    print(item)

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_GU7**********************************

This is your API token. Keep it to yourself.

Run salesforce/blip 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": "salesforce/blip:5a977fcb091363cc3938cc870c9f6242f5938267040e6837373387bb90d23099",
    "input": {
      "image": "https://replicate.delivery/mgxm/ceba852d-1e52-4004-ae8b-86869790dbc3/beautiful-scenery-wallpapers-moonlight-beauty.jpg",
      "question": "what is standing on the rock?",
      "task": "visual_question_answering"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "outputType": "object",
  "properties": {
    "text": {
      "outputType": "text",
      "inferred": false,
      "outputValue": "Answer: deer",
      "typeMismatch": false
    }
  },
  "inferred": false,
  "outputValue": {
    "text": "Answer: deer"
  },
  "typeMismatch": false
}

Generated in

0.9 seconds

Tweak it Report