Use Visual Question Answering (VQA) to get image information

Visual Question Answering (VQA) lets you provide an image to the model and ask a question about the image's contents. In response to your question you get one or more natural language answers.

Sample VQA image, question and answers in the console
Image source (shown in Google Cloud console): Sharon Pittaway on Unsplash
Prompt question: What objects are in the image?
Answer 1: marbles
Answer 2: glass marbles

Languages supported

VQA is available in the following languages:

  • English (en)

Performance and limitations

The following limits apply when you use this model:

Limits Value
Maximum number of API requests (short-form) per minute per project 500
Maximum number of tokens returned in response (short-form) 64 tokens
Maximum number of tokens accepted in request (VQA short-form only) 80 tokens

The following service latency estimates apply when you use this model. These values are meant to be illustrative and are not a promise of service:

Latency Value
API requests (short-form) 1.5 seconds


A location is a region you can specify in a request to control where data is stored at rest. For a list of available regions, see Generative AI on Vertex AI locations.

Use VQA on an image (short-form responses)

Use the following samples to ask a question and get an answer about an image.


  1. In the Google Cloud console, open the Vertex AI Studio > Vision tab in the Vertex AI dashboard.

    Go to the Vertex AI Studio tab

  2. In the lower menu, click Visual Q & A.

  3. Click Upload image to select your local image to caption.

  4. In the Parameters panel, choose your Number of captions and Language.

  5. In the prompt field, enter a question about your uploaded image.

  6. Click Submit.


For more information about imagetext model requests, see the imagetext model API reference.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your Google Cloud project ID.
  • LOCATION: Your project's region. For example, us-central1, europe-west2, or asia-northeast3. For a list of available regions, see Generative AI on Vertex AI locations.
  • VQA_PROMPT: The question you want to get answered about your image.
    • What color is this shoe?
    • What type of sleeves are on the shirt?
  • B64_IMAGE: The image to get captions for. The image must be specified as a base64-encoded byte string. Size limit: 10 MB.
  • RESPONSE_COUNT: The number of answers you want to generate. Accepted integer values: 1-3.

HTTP method and URL:


Request JSON body:

  "instances": [
      "prompt": "VQA_PROMPT",
      "image": {
          "bytesBase64Encoded": "B64_IMAGE"
  "parameters": {
    "sampleCount": RESPONSE_COUNT

To send your request, choose one of these options:


Save the request body in a file named request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \


Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "" | Select-Object -Expand Content
The following sample responses are for a request with "sampleCount": 2 and "prompt": "What is this?". The response returns two prediction string answers.
  "predictions": [
  "deployedModelId": "DEPLOYED_MODEL_ID",
  "model": "projects/PROJECT_ID/locations/LOCATION/models/MODEL_ID",
  "modelDisplayName": "MODEL_DISPLAYNAME",
  "modelVersionId": "1"


Before trying this sample, follow the Python setup instructions in the Generative AI quickstart using client libraries. For more information, see the Generative AI Python API reference documentation.

To authenticate to Generative AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

In this sample you use the load_from_file method to reference a local file as the base Image to get information about. After you specify the base image, you use the ask_question method on the ImageTextModel and print the answers.

import argparse

import vertexai
from vertexai.preview.vision_models import Image, ImageTextModel

def get_short_form_image_responses(
    project_id: str, location: str, input_file: str, question: str
) -> list:
    """Get short-form responses to a question about a local image.
      project_id: Google Cloud project ID, used to initialize Vertex AI.
      location: Google Cloud region, used to initialize Vertex AI.
      input_file: Local path to the input image file.
      question: The question about the contents of the image."""

    vertexai.init(project=project_id, location=location)

    model = ImageTextModel.from_pretrained("imagetext@001")
    source_img = Image.load_from_file(location=input_file)

    answers = model.ask_question(
        # Optional parameters


    return answers

Use parameters for VQA

When you get VQA responses there are several parameters you can set depending on your use case.

Number of results

Use the number of results parameter to limit the amount of responses returned for each request you send. For more information, see the imagetext (VQA) model API reference.

Seed number

A number you add to a request to make generated responses deterministic. Adding a seed number with your request is a way to assure you get the same prediction (responses) each time. However, the answers aren't necessarily returned in the same order. For more information, see the imagetext (VQA) model API reference.

What's next