Remove objects from an image using inpaint

from google import genai
from google.genai.types import RawReferenceImage, MaskReferenceImage, MaskReferenceConfig, EditImageConfig

client = genai.Client()

# TODO(developer): Update and un-comment below line
# output_file = "output-image.png"

raw_ref = RawReferenceImage(
    reference_image=Image.from_file(location='test_resources/fruit.png'), reference_id=0)
mask_ref = MaskReferenceImage(
    reference_id=1,
    reference_image=Image.from_file(location='test_resources/fruit_mask.png'),
    config=MaskReferenceConfig(
        mask_mode="MASK_MODE_USER_PROVIDED",
        mask_dilation=0.01,
    ),
)

image = client.models.edit_image(
    model="imagen-3.0-capability-001",
    prompt="",
    reference_images=[raw_ref, mask_ref],
    config=EditImageConfig(
        edit_mode="EDIT_MODE_INPAINT_REMOVAL",
    ),
)

image.generated_images[0].image.save(output_file)

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

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"
# mask_file = "mask-image.png"
# output_file = "outpur-image.png"
# prompt = "" # The text prompt describing the entire image.

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

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

images = model.edit_image(
    base_image=base_img,
    mask=mask_img,
    prompt=prompt,
    edit_mode="inpainting-remove",
    # Optional parameters
    # negative_prompt="", # Describes the object being removed (i.e., "person")
)

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 12345678 bytes

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 EditImageInpaintingRemoveMaskSample {

  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 maskPath = "/path/to/my-mask.png";
    String prompt = ""; // The text prompt describing the entire image.

    editImageInpaintingRemoveMask(projectId, location, inputPath, maskPath, prompt);
  }

  // Edit an image using a mask file. Inpainting can remove an object from the masked area.
  public static PredictResponse editImageInpaintingRemoveMask(
      String projectId, String location, String inputPath, String maskPath, 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@006");

      // Encode image and mask to Base64
      String imageBase64 =
          Base64.getEncoder().encodeToString(Files.readAllBytes(Paths.get(inputPath)));
      String maskBase64 =
          Base64.getEncoder().encodeToString(Files.readAllBytes(Paths.get(maskPath)));

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

      Map<String, String> maskMap = new HashMap<>();
      maskMap.put("bytesBase64Encoded", maskBase64);
      Map<String, Map> imageMaskMap = new HashMap<>();
      imageMaskMap.put("image", maskMap);

      Map<String, Object> instancesMap = new HashMap<>();
      instancesMap.put("prompt", prompt); // [ "prompt", "<my-prompt>" ]
      instancesMap.put(
          "image", imageMap); // [ "image", [ "bytesBase64Encoded", "iVBORw0KGgo...==" ] ]
      instancesMap.put(
          "mask",
          imageMaskMap); // [ "mask", [ "image", [ "bytesBase64Encoded", "iJKDF0KGpl...==" ] ] ]
      instancesMap.put("editMode", "inpainting-remove"); // [ "editMode", "inpainting-remove" ]
      Value instances = mapToValue(instancesMap);

      // Optional parameters
      Map<String, Object> paramsMap = new HashMap<>();
      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();
  }
}

/**
 * TODO(developer): Update these variables before running the sample.
 */
const projectId = process.env.CAIP_PROJECT_ID;
const location = 'us-central1';
const inputFile = 'resources/volleyball_game.png';
const maskFile = 'resources/volleyball_game_inpainting_remove_mask.png';
const prompt = 'volleyball game';

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 editImageInpaintingRemoveMask() {
  const fs = require('fs');
  const util = require('util');
  // Configure the parent resource
  const endpoint = `projects/${projectId}/locations/${location}/publishers/google/models/imagegeneration@006`;

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

  const maskImageFile = fs.readFileSync(maskFile);
  // Convert the image mask data to a Buffer and base64 encode it.
  const encodedMask = Buffer.from(maskImageFile).toString('base64');

  const promptObj = {
    prompt: prompt, // The text prompt describing the entire image
    editMode: 'inpainting-remove',
    image: {
      bytesBase64Encoded: encodedImage,
    },
    mask: {
      image: {
        bytesBase64Encoded: encodedMask,
      },
    },
  };
  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 editImageInpaintingRemoveMask();

from google import genai
from google.genai.types import RawReferenceImage, MaskReferenceImage, MaskReferenceConfig, EditImageConfig

client = genai.Client()

# TODO(developer): Update and un-comment below line
# output_file = "output-image.png"

raw_ref = RawReferenceImage(
    reference_image=Image.from_file(location='test_resources/fruit.png'), reference_id=0)
mask_ref = MaskReferenceImage(
    reference_id=1,
    reference_image=None,
    config=MaskReferenceConfig(
        mask_mode="MASK_MODE_FOREGROUND",
    ),
)

image = client.models.edit_image(
    model="imagen-3.0-capability-001",
    prompt="",
    reference_images=[raw_ref, mask_ref],
    config=EditImageConfig(
        edit_mode="EDIT_MODE_INPAINT_REMOVAL",
    ),
)

image.generated_images[0].image.save(output_file)

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

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"
# mask_mode = "foreground" # 'background', 'foreground', or 'semantic'
# output_file = "output-image.png"
# prompt = "sports car" # The text prompt describing what you want to see in the edited image.

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,
    mask_mode=mask_mode,
    prompt=prompt,
    edit_mode="inpainting-remove",
)

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 1279948 bytes