使用 Gemini 生成圖像

你可以使用 Gemini 根據文字提示詞生成圖像。支援的介面包括 Google Cloud 控制台和 Agent Platform API。

下列 Gemini 模型支援生成圖像：

按一下即可展開支援的機型

如要進一步瞭解 Gemini 模型的功能，請參閱「Gemini 模型」。

生成圖像

以下說明如何使用 Agent Studio 或 API 生成圖片。

如要進一步瞭解提示詞的最佳做法，請參閱「設計多模態提示詞」。

控制台

如要使用 Gemini 生成圖像，請按照下列步驟操作：

  1. 開啟 Agent Studio > 建立提示。
  2. 按一下「切換模型」，然後選取顯示的模型。
  3. 在「輸出」面板中，從下拉式選單選取「圖片和文字」。
  4. 在「撰寫提示」文字區域中，輸入要生成的圖片說明。
  5. 按一下「提示」 () 按鈕。

Gemini 會根據您的描述生成圖片。這項程序需要幾秒鐘，但視容量而定，速度可能會相對較慢。

Python

安裝

pip install --upgrade google-genai

詳情請參閱 SDK 參考文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

import os
from io import BytesIO

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

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.1-flash-image",
    contents=("Generate an image of the Eiffel tower with fireworks in the background."),
    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)))
        # Ensure the output directory exists
        output_dir = "output_folder"
        os.makedirs(output_dir, exist_ok=True)
        image.save(os.path.join(output_dir, "example-image-eiffel-tower.png"))

Go

瞭解如何安裝或更新 Go。

詳情請參閱 SDK 參考文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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

	"google.golang.org/genai"
)

// generateMMFlashWithText demonstrates how to generate both text and image outputs.
func generateMMFlashWithText(w io.Writer) error {
	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)
	}

	modelName := "gemini-2.5-flash-image"
	contents := []*genai.Content{
		{
			Parts: []*genai.Part{
				{Text: "Generate an image of the Eiffel tower with fireworks in the background."},
			},
			Role: genai.RoleUser,
		},
	}

	resp, err := client.Models.GenerateContent(ctx,
		modelName,
		contents,
		&genai.GenerateContentConfig{
			ResponseModalities: []string{
				string(genai.ModalityText),
				string(genai.ModalityImage),
			},
			CandidateCount: int32(1),
			SafetySettings: []*genai.SafetySetting{
				{Method: genai.HarmBlockMethodProbability},
				{Category: genai.HarmCategoryDangerousContent},
				{Threshold: genai.HarmBlockThresholdBlockMediumAndAbove},
			},
		},
	)
	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 candidates returned")
	}
	var fileName string
	for _, part := range resp.Candidates[0].Content.Parts {
		if part.Text != "" {
			fmt.Fprintln(w, part.Text)
		} else if part.InlineData != nil {
			fileName = "example-image-eiffel-tower.png"
			if err := os.WriteFile(fileName, part.InlineData.Data, 0o644); err != nil {
				return fmt.Errorf("failed to save image: %w", err)
			}
		}
	}
	fmt.Fprintln(w, fileName)

	// Example response:
	// I will generate an image of the Eiffel Tower at night, with a vibrant display of
	// colorful fireworks exploding in the dark sky behind it.
	// ....
	return nil
}

Node.js

安裝

npm install @google/genai

詳情請參閱 SDK 參考文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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';

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

  const response = await client.models.generateContentStream({
    model: 'gemini-2.5-flash-image',
    contents:
      'Generate an image of the Eiffel tower with fireworks in the background.',
    config: {
      responseModalities: [Modality.TEXT, Modality.IMAGE],
    },
  });

  const generatedFileNames = [];
  let imageIndex = 0;

  for await (const chunk of response) {
    const text = chunk.text;
    const data = chunk.data;
    if (text) {
      console.debug(text);
    } else if (data) {
      const outputDir = 'output-folder';
      if (!fs.existsSync(outputDir)) {
        fs.mkdirSync(outputDir, {recursive: true});
      }
      const fileName = `${outputDir}/generate_content_streaming_image_${imageIndex++}.png`;
      console.debug(`Writing response image to file: ${fileName}.`);
      try {
        fs.writeFileSync(fileName, data);
        generatedFileNames.push(fileName);
      } catch (error) {
        console.error(`Failed to write image file ${fileName}:`, error);
      }
    }
  }

  // Example response:
  //  I will generate an image of the Eiffel Tower at night, with a vibrant display of
  //  colorful fireworks exploding in the dark sky behind it. The tower will be
  //  illuminated, standing tall as the focal point of the scene, with the bursts of
  //  light from the fireworks creating a festive atmosphere.

  return generatedFileNames;
}

Java

瞭解如何安裝或更新 Java。

詳情請參閱 SDK 參考說明文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 


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 com.google.genai.types.SafetySetting;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import javax.imageio.ImageIO;

public class ImageGenMmFlashWithText {

  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/example-image-eiffel-tower.png";
    generateContent(modelId, outputFile);
  }

  // Generates an image with 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()) {

      GenerateContentConfig contentConfig =
          GenerateContentConfig.builder()
              .responseModalities("TEXT", "IMAGE")
              .candidateCount(1)
              .safetySettings(
                  SafetySetting.builder()
                      .method("PROBABILITY")
                      .category("HARM_CATEGORY_DANGEROUS_CONTENT")
                      .threshold("BLOCK_MEDIUM_AND_ABOVE")
                      .build())
              .build();

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              "Generate an image of the Eiffel tower with fireworks in the background.",
              contentConfig);

      // 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:
      // Here is the Eiffel Tower with fireworks in the background...
      //
      // Content written to: resources/output/example-image-eiffel-tower.png
    }
  }
}

REST

在終端機中執行下列指令，在目前目錄中建立或覆寫這個檔案：

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${API_ENDPOINT}:generateContent \
  -d '{
    "contents": {
      "role": "USER",
      "parts": [
        {
          "text": "Create a tutorial explaining how to make a peanut butter and jelly sandwich in three easy steps."
        }
      ]
    },
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {
        "aspectRatio": "16:9",
      },
     },
     "safetySettings": {
      "method": "PROBABILITY",
      "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
      "threshold": "BLOCK_MEDIUM_AND_ABOVE"
    },
  }' 2>/dev/null >response.json

Gemini 會根據您的描述生成圖片。這項程序只需要幾秒鐘，但視容量而定，速度可能會比較慢。

生成圖像與文字交雜的內容

你可以使用 Gemini 生成穿插文字回覆的圖片。舉例來說，你可以為生成的食譜中的每個步驟生成圖片，不必分別向模型提出要求。

下列 Gemini 模型支援生成圖像與文字交雜的內容：

按一下即可展開支援的機型

控制台

如要生成圖像與文字回應交雜的內容，請按照下列步驟操作：

  1. 開啟 Agent Studio > Create prompt。
  2. 按一下「切換模型」，然後選取顯示的模型。
  3. 在「輸出」面板中，從下拉式選單選取「圖片和文字」。
  4. 在「撰寫提示」文字區域中，輸入要生成的圖片說明。例如：「製作教學課程，說明如何用簡單的三個步驟製作花生醬和果醬三明治。請為每個步驟提供標題 (附上步驟編號)、說明，並生成圖片，每張圖片的長寬比為 1:1。"
  5. 按一下「提示」 () 按鈕。

Gemini 會根據說明生成回覆。這項程序只需要幾秒鐘，但視容量而定，速度可能會比較慢。

Python

安裝

pip install --upgrade google-genai

詳情請參閱 SDK 參考文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.1-flash-image",
    contents=(
        "Generate an illustrated recipe for a paella."
        "Create images to go alongside the text as you generate the recipe"
    ),
    config=GenerateContentConfig(response_modalities=[Modality.TEXT, Modality.IMAGE]),
)
with open("output_folder/paella-recipe.md", "w") as fp:
    for i, part in enumerate(response.candidates[0].content.parts):
        if part.text is not None:
            fp.write(part.text)
        elif part.inline_data is not None:
            image = Image.open(BytesIO((part.inline_data.data)))
            image.save(f"output_folder/example-image-{i+1}.png")
            fp.write(f"![image](example-image-{i+1}.png)")

Java

瞭解如何安裝或更新 Java。

詳情請參閱 SDK 參考說明文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 


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.BufferedWriter;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import javax.imageio.ImageIO;

public class ImageGenMmFlashTextAndImageWithText {

  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/paella-recipe.md";
    generateContent(modelId, outputFile);
  }

  // Generates text and image with 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()) {

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromText("Generate an illustrated recipe for a paella."),
                  Part.fromText(
                      "Create images to go alongside the text as you generate the recipe.")),
              GenerateContentConfig.builder().responseModalities("TEXT", "IMAGE").build());

      try (BufferedWriter writer = new BufferedWriter(new FileWriter(outputFile))) {

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

        int index = 1;
        // 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()) {
            writer.write(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("resources/output/example-image-" + index + ".png"));
            writer.write("![image](example-image-" + index + ".png)");
          }
          index++;
        }

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

        // Example response:
        // A markdown page for a Paella recipe(`paella-recipe.md`) has been generated.
        // It includes detailed steps and several images illustrating the cooking process.
        //
        // Content written to:  resources/output/paella-recipe.md
      }
    }
  }
}

Go

瞭解如何安裝或更新 Go。

詳情請參閱 SDK 參考文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

import (
	"context"
	"fmt"
	"io"
	"os"
	"path/filepath"

	"google.golang.org/genai"
)

// generateMMFlashTxtImgWithText demonstrates how to generate an illustrated recipe
// combining text and image outputs into a markdown file.
func generateMMFlashTxtImgWithText(w io.Writer) error {
	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)
	}

	modelName := "gemini-2.5-flash-image"
	contents := []*genai.Content{
		{
			Parts: []*genai.Part{
				{Text: "Generate an illustrated recipe for a paella. " +
					"Create images to go alongside the text as you generate the recipe."},
			},
			Role: genai.RoleUser,
		},
	}

	resp, err := client.Models.GenerateContent(ctx,
		modelName,
		contents,
		&genai.GenerateContentConfig{
			ResponseModalities: []string{
				string(genai.ModalityText),
				string(genai.ModalityImage),
			},
			CandidateCount: int32(1),
		},
	)
	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 candidates returned")
	}

	outputFolder := ""

	// Create the markdown file
	mdFile := filepath.Join(outputFolder, "paella-recipe.md")
	fp, err := os.Create(mdFile)
	if err != nil {
		return fmt.Errorf("failed to create markdown file: %w", err)
	}
	defer fp.Close()

	for i, part := range resp.Candidates[0].Content.Parts {
		if part.Text != "" {
			if _, err := fp.WriteString(part.Text); err != nil {
				return fmt.Errorf("failed to write text: %w", err)
			}
		} else if part.InlineData != nil {
			imgFile := filepath.Join(outputFolder, fmt.Sprintf("example-image-%d.png", i+1))
			if err := os.WriteFile(imgFile, part.InlineData.Data, 0644); err != nil {
				return fmt.Errorf("failed to save image: %w", err)
			}
			if _, err := fp.WriteString(fmt.Sprintf("![image](%s)", filepath.Base(imgFile))); err != nil {
				return fmt.Errorf("failed to write image reference: %w", err)
			}
		}
	}

	fmt.Fprintln(w, mdFile)

	// Example response:
	//  A markdown page for a Paella recipe (`paella-recipe.md`) has been generated.
	//  It includes detailed steps and several images illustrating the cooking process.
	return nil
}

Node.js

安裝

npm install @google/genai

詳情請參閱 SDK 參考文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK： 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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';

async function savePaellaRecipe(response) {
  const parts = response.candidates[0].content.parts;

  let mdText = '';
  const outputDir = 'output-folder';

  for (let i = 0; i < parts.length; i++) {
    const part = parts[i];

    if (part.text) {
      mdText += part.text + '\n';
    } else if (part.inlineData) {
      if (!fs.existsSync(outputDir)) {
        fs.mkdirSync(outputDir, {recursive: true});
      }
      const imageBytes = Buffer.from(part.inlineData.data, 'base64');
      const imagePath = `example-image-${i + 1}.png`;
      const saveImagePath = `${outputDir}/${imagePath}`;

      fs.writeFileSync(saveImagePath, imageBytes);
      mdText += `![image](./${imagePath})\n`;
    }
  }
  const mdFile = `${outputDir}/paella-recipe.md`;

  fs.writeFileSync(mdFile, mdText);
  console.log(`Saved recipe to: ${mdFile}`);
}

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

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash-image',
    contents:
      'Generate an illustrated recipe for a paella. Create images to go alongside the text as you generate the recipe',
    config: {
      responseModalities: [Modality.TEXT, Modality.IMAGE],
    },
  });
  console.log(response);

  await savePaellaRecipe(response);

  return response;
}
// Example response:
//  A markdown page for a Paella recipe(`paella-recipe.md`) has been generated.
//  It includes detailed steps and several images illustrating the cooking process.

REST

在終端機中執行下列指令，在目前目錄中建立或覆寫這個檔案：

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${API_ENDPOINT}:generateContent \
  -d '{
    "contents": {
      "role": "USER",
      "parts": [
        {
          "text": "Generate an illustrated recipe for a paella. Create images to
          go alongside the text as you generate the recipe."
        }
      ]
    },
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {
        "aspectRatio": "16:9",
      },
    },
    "safetySettings": {
      "method": "PROBABILITY",
      "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
      "threshold": "BLOCK_MEDIUM_AND_ABOVE"
    },
  }' 2>/dev/null >response.json

Gemini 會根據您的描述生成圖片。這項程序只需要幾秒鐘，但視容量而定，速度可能會比較慢。

後續步驟

如要進一步瞭解 Gemini 圖像生成功能，請參閱下列連結：