Google 会使用 AI 技术将内容翻译成您偏好的语言。AI 翻译可能包含错误。

使用 Gemini 生成图片

您可以使用 Gemini 根据文本提示生成图片。支持的界面包括 Google Cloud 控制台和 Agent Platform API。

以下 Gemini 模型支持图片生成：

点击即可展开支持的模型

如需详细了解 Gemini 模型的功能，请参阅 Gemini models。

生成图片

以下内容介绍了如何使用 Agent Studio 或 API 生成图片。

如需详细了解提示方面的最佳实践，请参阅设计多模态提示。

控制台

如需使用 Gemini 生成图片，请执行以下操作：

依次打开 Agent Studio > 创建提示。
点击切换模型 ，然后选择其中一个显示的模型。
在输出面板中，从下拉菜单中选择图片和文本。
在编写提示文本区域中，撰写要生成的图片的说明。
点击提示（）按钮。

Gemini 会根据您的说明生成图片。此过程需要几秒钟，但可能会相对较慢，具体取决于容量。

Python

安装

pip install --upgrade google-genai

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

了解如何安装或更新 Go。

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

安装

npm install @google/genai

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

了解如何安装或更新 Java。

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

在终端中运行以下命令，在当前目录中创建或覆盖此文件：

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 会根据您的说明生成图片。此过程需要几秒钟，但可能会相对较慢，具体取决于容量。

生成图文交织的内容

您可以使用 Gemini 生成图文交织的回答。例如，您可以为所生成食谱的每个步骤生成图片，而无需单独向模型发出请求。

以下 Gemini 模型支持生成图文交织的内容：

点击即可展开支持的模型

控制台

如需生成图文交织的回答，请执行以下操作：

依次打开 Agent Studio > 创建提示。
点击切换模型 ，然后选择其中一个显示的模型。
在输出面板中，从下拉菜单中选择图片和文本。
在编写提示文本区域中，撰写要生成的图片的说明。例如，“创建一个教程，说明如何通过三个简单步骤制作花生酱和果酱三明治。对于每个步骤，提供一个包含步骤编号的标题、一段说明，并生成一张图片，每张图片的宽高比为 1:1。”
点击提示（）按钮。

Gemini 会根据您的说明生成回答。此过程需要几秒钟，但可能会相对较慢，具体取决于容量。

Python

安装

pip install --upgrade google-genai

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

了解如何安装或更新 Java。

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

了解如何安装或更新 Go。

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

安装

npm install @google/genai

如需了解详情，请参阅 SDK 参考文档。

设置环境变量以将 Google Gen AI SDK 与 Vertex AI 搭配使用：

# 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

在终端中运行以下命令，在当前目录中创建或覆盖此文件：

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 会根据您的说明生成图片。此过程需要几秒钟，但可能会相对较慢，具体取决于容量。

接下来怎么做？

如需详细了解 Gemini 图片生成，请参阅以下链接：

使用 Gemini 生成图片 使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。

点击即可展开支持的模型

生成图片

控制台

Python

安装

Go

Node.js

安装

Java

REST

生成图文交织的内容

点击即可展开支持的模型

控制台

Python

安装

Java

Go

Node.js

安装

REST

接下来怎么做？

使用 Gemini 生成图片