使用 Imagen 生成图片


借助 Firebase AI Logic SDK，您可以访问 Imagen 模型（通过 Imagen API）， 以便根据文本提示生成图片。 借助此功能，您可以执行以下操作：

  • 根据自然语言编写的提示生成图片
  • 生成各种格式和样式的图片
  • 在图片中呈现文本

本指南介绍了如何仅通过 提供文本提示来使用 Imagen 生成图片。

不过请注意，Imagen 还可以使用其 自定义功能 （目前仅适用于 Android 和 Flutter）根据参考 图片生成图片。在请求中，您需要提供文本提示和参考图片，以引导模型根据指定的样式、主题（例如商品、人物或动物）或控件生成新图片。例如，您可以根据猫的照片或火箭和月亮的图画生成新图片。

跳转到仅限文本输入的代码

准备工作

点击您的 Gemini API 提供商，以查看此页面上特定于提供商的内容 和代码。

如果尚未完成，请完成 入门指南，其中介绍了如何 设置 Firebase 项目、将应用连接到 Firebase、添加 SDK、 为所选的 API 提供商初始化后端服务，以及 创建 ImagenModel 实例。

支持此功能的模型

Gemini Developer API 支持通过最新的 稳定 Imagen 模型生成图片。此支持的 Imagen 模型限制无论您如何访问 Gemini Developer API 都适用。

  • imagen-4.0-generate-001
  • imagen-4.0-fast-generate-001
  • imagen-4.0-ultra-generate-001
  • imagen-3.0-generate-002

根据仅限文本输入生成图片

您可以仅通过文本提示来要求 Imagen 模型生成图片。您可以生成一张图片或 多张图片。

您还可以为图片生成设置许多不同的 配置选项， 例如宽高比和图片格式。

根据仅限文本输入生成一张图片

在尝试此示例之前，请完成本指南的 准备工作部分， 以设置您的项目和应用。
在该部分中，您还需要点击所选 Gemini API提供商的按钮，以便在此页面上看到特定于提供商的内容 。

您可以仅通过文本提示来要求 Imagen 模型生成一张图片 。

请务必创建 ImagenModel 实例并调用 generateImages。

Swift 


import FirebaseAILogic

// Initialize the Gemini Developer API backend service
let ai = FirebaseAI.firebaseAI(backend: .googleAI())

// Create an `ImagenModel` instance with a model that supports your use case
let model = ai.imagenModel(modelName: "imagen-4.0-generate-001")

// Provide an image generation prompt
let prompt = "An astronaut riding a horse"

// To generate an image, call `generateImages` with the text prompt
let response = try await model.generateImages(prompt: prompt)

// Handle the generated image
guard let image = response.images.first else {
  fatalError("No image in the response.")
}
let uiImage = UIImage(data: image.data)

Kotlin 


suspend fun generateImage() {
  // Initialize the Gemini Developer API backend service
  val ai = Firebase.ai(backend = GenerativeBackend.googleAI())

  // Create an `ImagenModel` instance with an Imagen model that supports your use case
  val model = ai.imagenModel("imagen-4.0-generate-001")

  // Provide an image generation prompt
  val prompt = "An astronaut riding a horse"

  // To generate an image, call `generateImages` with the text prompt
  val imageResponse = model.generateImages(prompt)

  // Handle the generated image
  val image = imageResponse.images.first()

  val bitmapImage = image.asBitmap()
}

Java 


// Initialize the Gemini Developer API backend service
// Create an `ImagenModel` instance with an Imagen model that supports your use case
ImagenModel imagenModel = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .imagenModel(
                /* modelName */ "imagen-4.0-generate-001");

ImagenModelFutures model = ImagenModelFutures.from(imagenModel);

// Provide an image generation prompt
String prompt = "An astronaut riding a horse";

// To generate an image, call `generateImages` with the text prompt
Futures.addCallback(model.generateImages(prompt), new FutureCallback<ImagenGenerationResponse<ImagenInlineImage>>() {
    @Override
    public void onSuccess(ImagenGenerationResponse<ImagenInlineImage> result) {
        if (result.getImages().isEmpty()) {
            Log.d("TAG", "No images generated");
        }
        Bitmap bitmap = result.getImages().get(0).asBitmap();
        // Use the bitmap to display the image in your UI
    }

    @Override
    public void onFailure(Throwable t) {
        // ...
    }
}, Executors.newSingleThreadExecutor());

Web 


import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create an `ImagenModel` instance with an Imagen model that supports your use case
const model = getImagenModel(ai, { model: "imagen-4.0-generate-001" });

// Provide an image generation prompt
const prompt = "An astronaut riding a horse.";

// To generate an image, call `generateImages` with the text prompt
const response = await model.generateImages(prompt)

// If fewer images were generated than were requested,
// then `filteredReason` will describe the reason they were filtered out
if (response.filteredReason) {
  console.log(response.filteredReason);
}

if (response.images.length == 0) {
  throw new Error("No images in the response.")
}

const image = response.images[0];

Dart 

import 'package:firebase_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

// Initialize FirebaseApp
await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Gemini Developer API backend service
final model = FirebaseAI.googleAI();

// Create an `ImagenModel` instance with an Imagen model that supports your use case
final model = ai.imagenModel(model: 'imagen-4.0-generate-001');

// Provide an image generation prompt
const prompt = 'An astronaut riding a horse.';

// To generate an image, call `generateImages` with the text prompt
final response = await model.generateImages(prompt);

if (response.images.isNotEmpty) {
  final image = response.images[0];
  // Process the image
} else {
  // Handle the case where no images were generated
  print('Error: No images were generated.');
}

Unity 


using Firebase.AI;

// Initialize the Gemini Developer API backend service
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());

// Create an `ImagenModel` instance with a model that supports your use case
var model = ai.GetImagenModel(modelName: "imagen-4.0-generate-001");

// Provide an image generation prompt
var prompt = "An astronaut riding a horse";

// To generate an image, call `generateImages` with the text prompt
var response = await model.GenerateImagesAsync(prompt: prompt);

// Handle the generated image
if (response.Images.Count == 0) {
  throw new Exception("No image in the response.");
}
var image = response.Images[0].AsTexture2D();

了解如何选择适合您的应用场景和应用的模型，以及（可选）模型位置。

根据仅限文本输入生成多张图片

在尝试此示例之前，请完成本指南的 准备工作部分， 以设置您的项目和应用。
在该部分中，您还需要点击所选 Gemini API提供商的按钮，以便在此页面上看到特定于提供商的内容 。

默认情况下，Imagen 模型每个请求仅生成一张图片。 不过，您可以在创建 ImagenModel 实例时提供 ImagenGenerationConfig ，以要求 Imagen 模型每个请求生成多张图片 。

请务必创建 ImagenModel 实例并调用 generateImages。

Swift 


import FirebaseAILogic

// Initialize the Gemini Developer API backend service
let ai = FirebaseAI.firebaseAI(backend: .googleAI())

// Create an `ImagenModel` instance with a model that supports your use case
let model = ai.imagenModel(
  modelName: "imagen-4.0-generate-001",
  // Configure the model to generate multiple images for each request
  // See: https://firebase.google.com/docs/ai-logic/model-parameters
  generationConfig: ImagenGenerationConfig(numberOfImages: 4)
)

// Provide an image generation prompt
let prompt = "An astronaut riding a horse"

// To generate images, call `generateImages` with the text prompt
let response = try await model.generateImages(prompt: prompt)

// If fewer images were generated than were requested,
// then `filteredReason` will describe the reason they were filtered out
if let filteredReason = response.filteredReason {
  print(filteredReason)
}

// Handle the generated images
let uiImages =  response.images.compactMap { UIImage(data: $0.data) }

Kotlin 


suspend fun generateImage() {
  // Initialize the Gemini Developer API backend service
  val ai = Firebase.ai(backend = GenerativeBackend.googleAI())

  // Create an `ImagenModel` instance with an Imagen model that supports your use case
  val model = ai.imagenModel(
    modelName = "imagen-4.0-generate-001",
    // Configure the model to generate multiple images for each request
    // See: https://firebase.google.com/docs/ai-logic/model-parameters
    generationConfig = ImagenGenerationConfig(numberOfImages = 4)
  )

  // Provide an image generation prompt
  val prompt = "An astronaut riding a horse"

  // To generate images, call `generateImages` with the text prompt
  val imageResponse = model.generateImages(prompt)

  // If fewer images were generated than were requested,
  // then `filteredReason` will describe the reason they were filtered out
  if (imageResponse.filteredReason != null) {
    Log.d(TAG, "FilteredReason: ${imageResponse.filteredReason}")
  }

  for (image in imageResponse.images) {
    val bitmap = image.asBitmap()
    // Use the bitmap to display the image in your UI
  }
}

Java 


// Configure the model to generate multiple images for each request
// See: https://firebase.google.com/docs/ai-logic/model-parameters
ImagenGenerationConfig imagenGenerationConfig = new ImagenGenerationConfig.Builder()
        .setNumberOfImages(4)
        .build();

// Initialize the Gemini Developer API backend service
// Create an `ImagenModel` instance with an Imagen model that supports your use case
ImagenModel imagenModel = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .imagenModel(
                /* modelName */ "imagen-4.0-generate-001",
                /* imageGenerationConfig */ imagenGenerationConfig);

ImagenModelFutures model = ImagenModelFutures.from(imagenModel);

// Provide an image generation prompt
String prompt = "An astronaut riding a horse";

// To generate images, call `generateImages` with the text prompt
Futures.addCallback(model.generateImages(prompt), new FutureCallback<ImagenGenerationResponse<ImagenInlineImage>>() {
    @Override
    public void onSuccess(ImagenGenerationResponse<ImagenInlineImage> result) {
        // If fewer images were generated than were requested,
        // then `filteredReason` will describe the reason they were filtered out
        if (result.getFilteredReason() != null){
            Log.d("TAG", "FilteredReason: " + result.getFilteredReason());
        }

        // Handle the generated images
        List<ImagenInlineImage> images = result.getImages();
        for (ImagenInlineImage image : images) {
            Bitmap bitmap = image.asBitmap();
            // Use the bitmap to display the image in your UI
        }
    }

    @Override
    public void onFailure(Throwable t) {
        // ...
    }
}, Executors.newSingleThreadExecutor());

Web 


import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create an `ImagenModel` instance with an Imagen model that supports your use case
const model = getImagenModel(
  ai,
  {
    model: "imagen-4.0-generate-001",
    // Configure the model to generate multiple images for each request
    // See: https://firebase.google.com/docs/ai-logic/model-parameters
    generationConfig: {
      numberOfImages: 4
    }
  }
);

// Provide an image generation prompt
const prompt = "An astronaut riding a horse.";

// To generate images, call `generateImages` with the text prompt
const response = await model.generateImages(prompt)

// If fewer images were generated than were requested,
// then `filteredReason` will describe the reason they were filtered out
if (response.filteredReason) {
  console.log(response.filteredReason);
}

if (response.images.length == 0) {
  throw new Error("No images in the response.")
}

const images = response.images[0];

Dart 

import 'package:firebase_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

// Initialize FirebaseApp
await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Gemini Developer API backend service
final ai = FirebaseAI.googleAI();

// Create an `ImagenModel` instance with an Imagen model that supports your use case
final model = ai.imagenModel(
  model: 'imagen-4.0-generate-001',
  // Configure the model to generate multiple images for each request
  // See: https://firebase.google.com/docs/ai-logic/model-parameters
  generationConfig: ImagenGenerationConfig(numberOfImages: 4),
);

// Provide an image generation prompt
const prompt = 'An astronaut riding a horse.';

// To generate images, call `generateImages` with the text prompt
final response = await model.generateImages(prompt);

// If fewer images were generated than were requested,
// then `filteredReason` will describe the reason they were filtered out
if (response.filteredReason != null) {
  print(response.filteredReason);
}

if (response.images.isNotEmpty) {
  final images = response.images;
  for(var image in images) {
  // Process the image
  }
} else {
  // Handle the case where no images were generated
  print('Error: No images were generated.');
}

Unity 


using Firebase.AI;

// Initialize the Gemini Developer API backend service
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());

// Create an `ImagenModel` instance with a model that supports your use case
var model = ai.GetImagenModel(
  modelName: "imagen-4.0-generate-001",
  // Configure the model to generate multiple images for each request
  // See: https://firebase.google.com/docs/ai-logic/model-parameters
  generationConfig: new ImagenGenerationConfig(numberOfImages: 4)
);

// Provide an image generation prompt
var prompt = "An astronaut riding a horse";

// To generate an image, call `generateImages` with the text prompt
var response = await model.GenerateImagesAsync(prompt: prompt);

// If fewer images were generated than were requested,
// then `filteredReason` will describe the reason they were filtered out
if (!string.IsNullOrEmpty(response.FilteredReason)) {
  UnityEngine.Debug.Log("Filtered reason: " + response.FilteredReason);
}

// Handle the generated images
var images = response.Images.Select(image => image.AsTexture2D());

了解如何选择适合您的应用场景和应用的模型，以及（可选）模型位置。


支持的功能和要求

Imagen 模型提供了许多与图片生成相关的功能。 本部分介绍了支持的功能 将模型与 Firebase AI Logic搭配使用时。

支持的 capability 和功能

Firebase AI Logic 支持 Imagen 模型的以下功能 ：

  • 在生成的图片中生成人物、面部和文本

  • 使用 时，编辑图片或在请求中添加图片Vertex AI Gemini API （目前仅适用于 Android 和 Flutter）

  • 为生成的图片添加水印

  • 验证数字水印 使用 Vertex AI Gemini API
    如果您想验证图片是否带有水印，可以将图片上传到 Vertex AI Studio，方法是使用其 媒体 标签页。

  • 配置图片生成参数， 例如生成的图片数量、宽高比和水印

  • 配置安全设置

Firebase AI Logic 不支持 以下 高级功能 Imagen 模型：

  • 设置输入文本的语言

  • 停用 提示重写器 （enhancePrompt 参数）。这意味着，基于 LLM 的提示重写工具始终会自动在提供的提示中添加更多详细信息，以提供更高质量的图片，从而更好地反映所提供的提示。

  • 将生成的图片直接写入 Google Cloud Storage，作为 模型响应的一部分（storageUri 参数）。相反，图片始终作为 base64 编码的图片字节在响应中返回。
    如果您想将生成的图片上传到Cloud Storage，可以使用 Cloud Storage for Firebase。

规范和限制

属性（每个请求） 值
输入 token 数上限 480 个 token
输出图片数量上限 4 张图片
支持的输出图片分辨率（像素）
  • 1024x1024 像素（宽高比为 1:1）
  • 896x1280（宽高比为 3:4）
  • 1280x896（宽高比为 4:3）
  • 768x1408（宽高比为 9:16）
  • 1408x768（宽高比为 16:9）


你还可以做些什么？

了解如何控制内容生成

详细了解支持的模型

了解适用于各种应用场景的 模型 及其 配额和 价格。


提供反馈 有关您的使用体验Firebase AI Logic