使用 Gemini 編輯圖片

from google import genai
from google.genai.types import GenerateContentConfig, Modality
from PIL import Image
from io import BytesIO

client = genai.Client()

# Using an image of Eiffel tower, with fireworks in the background.
image = Image.open("test_resources/example-image-eiffel-tower.png")

response = client.models.generate_content(
    model="gemini-3.1-flash-image",
    contents=[image, "Edit this image to make it look like a cartoon."],
    config=GenerateContentConfig(response_modalities=[Modality.TEXT, Modality.IMAGE]),
)
for part in response.candidates[0].content.parts:
    if part.text:
        print(part.text)
    elif part.inline_data:
        image = Image.open(BytesIO((part.inline_data.data)))
        image.save("output_folder/bw-example-image.png")

import com.google.genai.Client;
import com.google.genai.types.Blob;
import com.google.genai.types.Candidate;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentConfig;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.Part;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;
import javax.imageio.ImageIO;

public class ImageGenMmFlashEditImageWithTextAndImage {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash-image";
    String outputFile = "resources/output/bw-example-image.png";
    generateContent(modelId, outputFile);
  }

  // Edits an image with image and text input
  public static void generateContent(String modelId, String outputFile) throws IOException {
    // Client Initialization. Once created, it can be reused for multiple requests.
    try (Client client = Client.builder().location("global").vertexAI(true).build()) {

      byte[] localImageBytes =
          Files.readAllBytes(Paths.get("resources/example-image-eiffel-tower.png"));

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromBytes(localImageBytes, "image/png"),
                  Part.fromText("Edit this image to make it look like a cartoon.")),
              GenerateContentConfig.builder().responseModalities("TEXT", "IMAGE").build());

      // Get parts of the response
      List<Part> parts =
          response
              .candidates()
              .flatMap(candidates -> candidates.stream().findFirst())
              .flatMap(Candidate::content)
              .flatMap(Content::parts)
              .orElse(new ArrayList<>());

      // For each part print text if present, otherwise read image data if present and
      // write it to the output file
      for (Part part : parts) {
        if (part.text().isPresent()) {
          System.out.println(part.text().get());
        } else if (part.inlineData().flatMap(Blob::data).isPresent()) {
          BufferedImage image =
              ImageIO.read(new ByteArrayInputStream(part.inlineData().flatMap(Blob::data).get()));
          ImageIO.write(image, "png", new File(outputFile));
        }
      }

      System.out.println("Content written to: " + outputFile);

      // Example response:
      // No problem! Here's the image in a cartoon style...
      //
      // Content written to: resources/output/bw-example-image.png
    }
  }
}

import (
	"context"
	"fmt"
	"io"
	"os"

	"google.golang.org/genai"
)

// generateImageMMFlashEditWithTextImg demonstrates editing an image with text and image inputs.
func generateImageMMFlashEditWithTextImg(w io.Writer) error {
	// TODO(developer): Update below lines
	outputFile := "bw-example-image.png"
	inputFile := "example-image-eiffel-tower.png"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	image, err := os.ReadFile(inputFile)
	if err != nil {
		return fmt.Errorf("failed to read image: %w", err)
	}

	modelName := "gemini-2.5-flash-image"
	prompt := "Edit this image to make it look like a cartoon."
	contents := []*genai.Content{
		{
			Role: "user",
			Parts: []*genai.Part{
				{Text: prompt},
				{InlineData: &genai.Blob{
					MIMEType: "image/png",
					Data:     image,
				}},
			},
		},
	}
	resp, err := client.Models.GenerateContent(ctx,
		modelName,
		contents,
		&genai.GenerateContentConfig{
			ResponseModalities: []string{
				string(genai.ModalityText),
				string(genai.ModalityImage),
			},
		},
	)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	if len(resp.Candidates) == 0 || resp.Candidates[0].Content == nil {
		return fmt.Errorf("no content was generated")
	}

	for _, part := range resp.Candidates[0].Content.Parts {
		if part.Text != "" {
			fmt.Fprintln(w, part.Text)
		} else if part.InlineData != nil {
			if len(part.InlineData.Data) > 0 {
				if err := os.WriteFile(outputFile, part.InlineData.Data, 0644); err != nil {
					return fmt.Errorf("failed to save image: %w", err)
				}
				fmt.Fprintln(w, outputFile)
			}
		}
	}

	// Example response:
	// Here's the image of the Eiffel Tower and fireworks, cartoonized for you!
	// Cartoon-style edit:
	//  - Simplified the Eiffel Tower with bolder lines and slightly exaggerated proportions.
	//  - Brightened and saturated the colors of the sky, fireworks, and foliage for a more vibrant, cartoonish look.
	//  ....
	return nil
}

const fs = require('fs');
const {GoogleGenAI, Modality} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION =
  process.env.GOOGLE_CLOUD_LOCATION || 'us-central1';

const FILE_NAME = 'test-data/example-image-eiffel-tower.png';

async function generateImage(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const imageBytes = fs.readFileSync(FILE_NAME);

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash-image',
    contents: [
      {
        role: 'user',
        parts: [
          {
            inlineData: {
              mimeType: 'image/png',
              data: imageBytes.toString('base64'),
            },
          },
          {
            text: 'Edit this image to make it look like a cartoon',
          },
        ],
      },
    ],
    config: {
      responseModalities: [Modality.TEXT, Modality.IMAGE],
    },
  });

  for (const part of response.candidates[0].content.parts) {
    if (part.text) {
      console.log(`${part.text}`);
    } else if (part.inlineData) {
      const outputDir = 'output-folder';
      if (!fs.existsSync(outputDir)) {
        fs.mkdirSync(outputDir, {recursive: true});
      }
      const imageBytes = Buffer.from(part.inlineData.data, 'base64');
      const filename = `${outputDir}/bw-example-image.png`;
      fs.writeFileSync(filename, imageBytes);
    }
  }

  // Example response:
  // Okay, I will edit this image to give it a cartoonish style, with bolder outlines, simplified details, and more vibrant colors.
  return response;
}