Edit image content using mask-free editing with Imagen v.002

This sample demonstrates how to use the Imagen model for mask-free image editing. Specify the edits using a text prompt.

Code sample

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.nio.file.Paths;
import java.util.Base64;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

public class EditImageMaskFreeSample {

  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 inputPath = "/path/to/my-input.png";
    String prompt = ""; // The text prompt describing what you want to see.

    editImageMaskFree(projectId, location, inputPath, prompt);
  }

  // Edit an image without using a mask. The edit is applied to the entire image and is saved to a
  // new file.
  public static PredictResponse editImageMaskFree(
      String projectId, String location, String inputPath, 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", "imagegeneration@002");

      // Convert the image to Base64 and create the image map
      String imageBase64 =
          Base64.getEncoder().encodeToString(Files.readAllBytes(Paths.get(inputPath)));
      Map<String, String> imageMap = new HashMap<>();
      imageMap.put("bytesBase64Encoded", imageBase64);

      Map<String, Object> instancesMap = new HashMap<>();
      instancesMap.put("prompt", prompt); // [ "prompt", "<my-prompt>" ]
      instancesMap.put(
          "image", imageMap); // [ "image", [ "bytesBase64Encoded", "iVBORw0KGgo...==" ] ]
      Value instances = mapToValue(instancesMap);

      Map<String, Object> paramsMap = new HashMap<>();
      // Optional parameters
      paramsMap.put("seed", 1);
      // Controls the strength of the prompt.
      // 0-9 (low strength), 10-20 (medium strength), 21+ (high strength)
      paramsMap.put("guidanceScale", 21);
      paramsMap.put("sampleCount", 1);
      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 inputFile = 'resources/cat.png';
const prompt = 'dog';

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 editImageMaskFree() {
  const fs = require('fs');
  const util = require('util');
  // Configure the parent resource
  const endpoint = `projects/${projectId}/locations/${location}/publishers/google/models/imagegeneration@002`;

  const imageFile = fs.readFileSync(inputFile);
  // Convert the image data to a Buffer and base64 encode it.
  const encodedImage = Buffer.from(imageFile).toString('base64');

  const promptObj = {
    prompt: prompt, // The text prompt describing what you want to see
    image: {
      bytesBase64Encoded: encodedImage,
    },
  };
  const instanceValue = helpers.toValue(promptObj);
  const instances = [instanceValue];

  const parameter = {
    // Optional parameters
    seed: 100,
    // Controls the strength of the prompt
    // 0-9 (low strength), 10-20 (medium strength), 21+ (high strength)
    guidanceScale: 21,
    sampleCount: 1,
  };
  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 editImageMaskFree();

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 Image, ImageGenerationModel

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

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

model = ImageGenerationModel.from_pretrained("imagegeneration@002")
base_img = Image.load_from_file(location=input_file)

images = model.edit_image(
    base_image=base_img,
    prompt=prompt,
    # Optional parameters
    seed=1,
    # Controls the strength of the prompt.
    # -- 0-9 (low strength), 10-20 (medium strength), 21+ (high strength)
    guidance_scale=21,
    number_of_images=1,
)

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

# Optional. View the edited 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.