Method: projects.locations.endpoints.predict

import vertexai
from vertexai.vision_models import Image, MultiModalEmbeddingModel

# TODO(developer): Update & uncomment line below
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")
image = Image.load_from_file(
    "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"
)

embeddings = model.get_embeddings(
    image=image,
    contextual_text="Colosseum",
    dimension=1408,
)
print(f"Image Embedding: {embeddings.image_embedding}")
print(f"Text Embedding: {embeddings.text_embedding}")
# Example response:
# Image Embedding: [-0.0123147098, 0.0727171078, ...]
# Text Embedding: [0.00230263756, 0.0278981831, ...]
multimodal_image_example.py

import vertexai

from vertexai.vision_models import MultiModalEmbeddingModel, Video
from vertexai.vision_models import VideoSegmentConfig

# TODO(developer): Update & uncomment line below
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")

embeddings = model.get_embeddings(
    video=Video.load_from_file(
        "gs://cloud-samples-data/vertex-ai-vision/highway_vehicles.mp4"
    ),
    video_segment_config=VideoSegmentConfig(end_offset_sec=1),
)

# Video Embeddings are segmented based on the video_segment_config.
print("Video Embeddings:")
for video_embedding in embeddings.video_embeddings:
    print(
        f"Video Segment: {video_embedding.start_offset_sec} - {video_embedding.end_offset_sec}"
    )
    print(f"Embedding: {video_embedding.embedding}")

# Example response:
# Video Embeddings:
# Video Segment: 0.0 - 1.0
# Embedding: [-0.0206376351, 0.0123456789, ...]
multimodal_video_example.py

import vertexai

from vertexai.vision_models import Image, MultiModalEmbeddingModel, Video
from vertexai.vision_models import VideoSegmentConfig

# TODO(developer): Update & uncomment line below
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")

image = Image.load_from_file(
    "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"
)
video = Video.load_from_file(
    "gs://cloud-samples-data/vertex-ai-vision/highway_vehicles.mp4"
)

embeddings = model.get_embeddings(
    image=image,
    video=video,
    video_segment_config=VideoSegmentConfig(end_offset_sec=1),
    contextual_text="Cars on Highway",
)

print(f"Image Embedding: {embeddings.image_embedding}")

# Video Embeddings are segmented based on the video_segment_config.
print("Video Embeddings:")
for video_embedding in embeddings.video_embeddings:
    print(
        f"Video Segment: {video_embedding.start_offset_sec} - {video_embedding.end_offset_sec}"
    )
    print(f"Embedding: {video_embedding.embedding}")

print(f"Text Embedding: {embeddings.text_embedding}")
# Example response:
# Image Embedding: [-0.0123144267, 0.0727186054, 0.000201397663, ...]
# Video Embeddings:
# Video Segment: 0.0 - 1.0
# Embedding: [-0.0206376351, 0.0345234685, ...]
# Text Embedding: [-0.0207006838, -0.00251058186, ...]
multimodal_example.py

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 in the background.

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

model = ImageGenerationModel.from_pretrained("imagegeneration@006")
base_img = Image.load_from_file(location=input_file)

images = model.edit_image(
    base_image=base_img,
    prompt=prompt,
    edit_mode="product-image",
)

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
edit_image_product_image.py

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;
    }
}
GenerateImage.cs

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();
  }
}
GenerateImageSample.java

/**
 * 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();
imagen-generate-image.js

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
generate_image.py

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

public class VerifyImageWatermarkSample {

  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";

    verifyImageWatermark(projectId, location, inputPath);
  }

  // Verify if an image contains a digital watermark. By default, a non-visible, digital watermark
  // (called a SynthID) is added to images generated by a model version that supports
  //  watermark generation.
  public static PredictResponse verifyImageWatermark(
      String projectId, String location, String inputPath) 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", "imageverification@001");

      // Encode image to Base64
      String imageBase64 =
          Base64.getEncoder().encodeToString(Files.readAllBytes(Paths.get(inputPath)));

      // Create the image map
      Map<String, String> imageMap = new HashMap<>();
      imageMap.put("bytesBase64Encoded", imageBase64);

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

      // Optional parameters
      Map<String, Object> paramsMap = new HashMap<>();
      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("decision")) {
          // "ACCEPT" if the image contains a digital watermark
          // "REJECT" if the image does not contain a digital watermark
          System.out.format(
              "Watermark verification result: %s", fieldsMap.get("decision").getStringValue());
        }
      }
      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();
  }
}
VerifyImageWatermarkSample.java

/**
 * TODO(developer): Update these variables before running the sample.
 */
const projectId = process.env.CAIP_PROJECT_ID;
const location = 'us-central1';
const inputFile = 'resources/dog_newspaper.png'; // has watermark

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 verifyImageWatermark() {
  const fs = require('fs');
  // Configure the parent resource
  const endpoint = `projects/${projectId}/locations/${location}/publishers/google/models/imageverification@001`;

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

  const instance = {
    image: {
      bytesBase64Encoded: encodedImage,
    },
  };
  const instanceValue = helpers.toValue(instance);
  const instances = [instanceValue];

  const request = {
    endpoint,
    instances,
  };

  // Predict request
  const [response] = await predictionServiceClient.predict(request);
  const predictions = response.predictions;
  if (predictions.length === 0) {
    console.log('No decision was generated. Check the request image.');
  } else {
    predictions.forEach(prediction => {
      // "ACCEPT" if the image contains a digital watermark
      // "REJECT" if the image does not contain a digital watermark
      console.log(prediction.structValue.fields.decision.stringValue);
    });
  }
}
await verifyImageWatermark();
imagen-verify-image-watermark.js

import vertexai
from vertexai.preview.vision_models import (
    Image,
    WatermarkVerificationModel,
)

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# input_file = "input-image.png"

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

verification_model = WatermarkVerificationModel.from_pretrained(
    "imageverification@001"
)
image = Image.load_from_file(location=input_file)

watermark_verification_response = verification_model.verify_image(image)

print(
    f"Watermark verification result: {watermark_verification_response.watermark_verification_result}"
)
# Example response:
# Watermark verification result: ACCEPT
# or "REJECT" if the image does not contain a digital watermark.
verify_image_watermark.py