Generate an image from text

This sample demonstrates how to use the Imagen model to generate an image from text.

Explore further

For detailed documentation that includes this code sample, see the following:

• Generate images
• Generate images using text prompts

Code sample

C#

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

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

using Google.Cloud.AIPlatform.V1;
using System;
using System.IO;
using System.Linq;
using System.Threading.Tasks;
using Value = Google.Protobuf.WellKnownTypes.Value;

public class GenerateImage
{
    public async Task<FileInfo> Generate(
        string projectId = "your-project-id")
    {
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = "us-central1-aiplatform.googleapis.com"
        }.Build();


        string prompt = "a dog reading a newspaper";
        string outputFileName = "dog_newspaper.png";
        string model = "imagegeneration@006";

        var predictRequest = new PredictRequest
        {
            EndpointAsEndpointName = EndpointName.FromProjectLocationPublisherModel(projectId, "us-central1", "google", model),
            Instances =
            {
                Value.ForStruct(new()
                {
                    Fields =
                    {
                        ["prompt"] = Value.ForString(prompt)
                    }
                })
            },
            Parameters = Value.ForStruct(new()
            {
                Fields =
                {
                    ["sampleCount"] = Value.ForNumber(1)
                }
            })
        };

        PredictResponse response = await predictionServiceClient.PredictAsync(predictRequest);
        byte[] imageBytes = Convert.FromBase64String(response.Predictions.First().StructValue.Fields["bytesBase64Encoded"].StringValue);

        File.WriteAllBytes(outputFileName, imageBytes);
        FileInfo fileInfo = new FileInfo(Path.GetFullPath(outputFileName));

        Console.WriteLine($"Created output image {fileInfo.FullName} with {fileInfo.Length} bytes");
        return fileInfo;
    }
}

Java

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

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

import com.google.api.gax.rpc.ApiException;
import com.google.cloud.aiplatform.v1.EndpointName;
import com.google.cloud.aiplatform.v1.PredictResponse;
import com.google.cloud.aiplatform.v1.PredictionServiceClient;
import com.google.cloud.aiplatform.v1.PredictionServiceSettings;
import com.google.gson.Gson;
import com.google.protobuf.InvalidProtocolBufferException;
import com.google.protobuf.Value;
import com.google.protobuf.util.JsonFormat;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.Base64;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

public class GenerateImageSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "my-project-id";
    String location = "us-central1";
    String prompt = ""; // The text prompt describing what you want to see.

    generateImage(projectId, location, prompt);
  }

  // Generate an image using a text prompt using an Imagen model
  public static PredictResponse generateImage(String projectId, String location, String prompt)
      throws ApiException, IOException {
    final String endpoint = String.format("%s-aiplatform.googleapis.com:443", location);
    PredictionServiceSettings predictionServiceSettings =
        PredictionServiceSettings.newBuilder().setEndpoint(endpoint).build();

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (PredictionServiceClient predictionServiceClient =
        PredictionServiceClient.create(predictionServiceSettings)) {

      final EndpointName endpointName =
          EndpointName.ofProjectLocationPublisherModelName(
              projectId, location, "google", "imagen-3.0-generate-001");

      Map<String, Object> instancesMap = new HashMap<>();
      instancesMap.put("prompt", prompt);
      Value instances = mapToValue(instancesMap);

      Map<String, Object> paramsMap = new HashMap<>();
      paramsMap.put("sampleCount", 1);
      // You can't use a seed value and watermark at the same time.
      // paramsMap.put("seed", 100);
      // paramsMap.put("addWatermark", false);
      paramsMap.put("aspectRatio", "1:1");
      paramsMap.put("safetyFilterLevel", "block_some");
      paramsMap.put("personGeneration", "allow_adult");
      Value parameters = mapToValue(paramsMap);

      PredictResponse predictResponse =
          predictionServiceClient.predict(
              endpointName, Collections.singletonList(instances), parameters);

      for (Value prediction : predictResponse.getPredictionsList()) {
        Map<String, Value> fieldsMap = prediction.getStructValue().getFieldsMap();
        if (fieldsMap.containsKey("bytesBase64Encoded")) {
          String bytesBase64Encoded = fieldsMap.get("bytesBase64Encoded").getStringValue();
          Path tmpPath = Files.createTempFile("imagen-", ".png");
          Files.write(tmpPath, Base64.getDecoder().decode(bytesBase64Encoded));
          System.out.format("Image file written to: %s\n", tmpPath.toUri());
        }
      }
      return predictResponse;
    }
  }

  private static Value mapToValue(Map<String, Object> map) throws InvalidProtocolBufferException {
    Gson gson = new Gson();
    String json = gson.toJson(map);
    Value.Builder builder = Value.newBuilder();
    JsonFormat.parser().merge(json, builder);
    return builder.build();
  }
}

Node.js

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

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

/**
 * TODO(developer): Update these variables before running the sample.
 */
const projectId = process.env.CAIP_PROJECT_ID;
const location = 'us-central1';
const prompt = 'a dog reading a newspaper';

const aiplatform = require('@google-cloud/aiplatform');

// Imports the Google Cloud Prediction Service Client library
const {PredictionServiceClient} = aiplatform.v1;

// Import the helper module for converting arbitrary protobuf.Value objects
const {helpers} = aiplatform;

// Specifies the location of the api endpoint
const clientOptions = {
  apiEndpoint: `${location}-aiplatform.googleapis.com`,
};

// Instantiates a client
const predictionServiceClient = new PredictionServiceClient(clientOptions);

async function generateImage() {
  const fs = require('fs');
  const util = require('util');
  // Configure the parent resource
  const endpoint = `projects/${projectId}/locations/${location}/publishers/google/models/imagen-3.0-generate-001`;

  const promptText = {
    prompt: prompt, // The text prompt describing what you want to see
  };
  const instanceValue = helpers.toValue(promptText);
  const instances = [instanceValue];

  const parameter = {
    sampleCount: 1,
    // You can't use a seed value and watermark at the same time.
    // seed: 100,
    // addWatermark: false,
    aspectRatio: '1:1',
    safetyFilterLevel: 'block_some',
    personGeneration: 'allow_adult',
  };
  const parameters = helpers.toValue(parameter);

  const request = {
    endpoint,
    instances,
    parameters,
  };

  // Predict request
  const [response] = await predictionServiceClient.predict(request);
  const predictions = response.predictions;
  if (predictions.length === 0) {
    console.log(
      'No image was generated. Check the request parameters and prompt.'
    );
  } else {
    let i = 1;
    for (const prediction of predictions) {
      const buff = Buffer.from(
        prediction.structValue.fields.bytesBase64Encoded.stringValue,
        'base64'
      );
      // Write image content to the output file
      const writeFile = util.promisify(fs.writeFile);
      const filename = `output${i}.png`;
      await writeFile(filename, buff);
      console.log(`Saved image ${filename}`);
      i++;
    }
  }
}
await generateImage();

Python

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

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

import vertexai
from vertexai.preview.vision_models import ImageGenerationModel

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# output_file = "input-image.png"
# prompt = "" # The text prompt describing what you want to see.

vertexai.init(project=PROJECT_ID, location="us-central1")

model = ImageGenerationModel.from_pretrained("imagen-3.0-generate-001")

images = model.generate_images(
    prompt=prompt,
    # Optional parameters
    number_of_images=1,
    language="en",
    # You can't use a seed value and watermark at the same time.
    # add_watermark=False,
    # seed=100,
    aspect_ratio="1:1",
    safety_filter_level="block_some",
    person_generation="allow_adult",
)

images[0].save(location=output_file, include_generation_parameters=False)

# Optional. View the generated image in a notebook.
# images[0].show()

print(f"Created output image using {len(images[0]._image_bytes)} bytes")
# Example response:
# Created output image using 1234567 bytes

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.