Generowanie i edytowanie obrazów za pomocą Gemini (czyli „Nano Banana”)

import FirebaseAILogic

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
let generativeModel = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [.text, .image])
)

// Provide a text prompt instructing the model to generate an image
let prompt = "Generate an image of the Eiffel tower with fireworks in the background."

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

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    generationConfig = generationConfig {
responseModalities = listOf(ResponseModality.TEXT, ResponseModality.IMAGE) }
)

// Provide a text prompt instructing the model to generate an image
val prompt = "Generate an image of the Eiffel tower with fireworks in the background."

// To generate image output, call `generateContent` with the text input
val generatedImageAsBitmap = model.generateContent(prompt)
    // Handle the generated image
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel(
    "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    new GenerationConfig.Builder()
        .setResponseModalities(Arrays.asList(ResponseModality.TEXT, ResponseModality.IMAGE))
        .build()
);

GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide a text prompt instructing the model to generate an image
Content prompt = new Content.Builder()
        .addText("Generate an image of the Eiffel Tower with fireworks in the background.")
        .build();

// To generate an image, call `generateContent` with the text input
ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) { 
        // iterate over all the parts in the first candidate in the result object
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                // The returned image as a bitmap
                Bitmap generatedImageAsBitmap = imagePart.getImage();
                break;
            }
        }
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend, ResponseModality } 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 a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(ai, {
  model: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: {
    responseModalities: [ResponseModality.TEXT, ResponseModality.IMAGE],
  },
});

// Provide a text prompt instructing the model to generate an image
const prompt = 'Generate an image of the Eiffel Tower with fireworks in the background.';

// To generate an image, call `generateContent` with the text input
const result = model.generateContent(prompt);

// Handle the generated image
try {
  const inlineDataParts = result.response.inlineDataParts();
  if (inlineDataParts?.[0]) {
    const image = inlineDataParts[0].inlineData;
    console.log(image.mimeType, image.data);
  }
} catch (err) {
  console.error('Prompt or candidate was blocked:', err);
}

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

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-2.5-flash-image',
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [ResponseModalities.text, ResponseModalities.image]),
);

// Provide a text prompt instructing the model to generate an image
final prompt = [Content.text('Generate an image of the Eiffel Tower with fireworks in the background.')];

// To generate an image, call `generateContent` with the text input
final response = await model.generateContent(prompt);
if (response.inlineDataParts.isNotEmpty) {
  final imageBytes = response.inlineDataParts[0].bytes;
  // Process the image
} else {
  // Handle the case where no images were generated
  print('Error: No images were generated.');
}

using Firebase;
using Firebase.AI;

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: new GenerationConfig(
    responseModalities: new[] { ResponseModality.Text, ResponseModality.Image })
);

// Provide a text prompt instructing the model to generate an image
var prompt = "Generate an image of the Eiffel Tower with fireworks in the background.";

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

var text = response.Text;
if (!string.IsNullOrWhiteSpace(text)) {
  // Do something with the text
}

// Handle the generated image
var imageParts = response.Candidates.First().Content.Parts
                         .OfType<ModelContent.InlineDataPart>()
                         .Where(part => part.MimeType == "image/png");
foreach (var imagePart in imageParts) {
  // Load the Image into a Unity Texture2D object
  UnityEngine.Texture2D texture2D = new(2, 2);
  if (texture2D.LoadImage(imagePart.Data.ToArray())) {
    // Do something with the image
  }
}

import FirebaseAILogic

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
let generativeModel = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [.text, .image])
)

// Provide a text prompt instructing the model to generate interleaved text and images
let prompt = """
Generate an illustrated recipe for a paella.
Create images to go alongside the text as you generate the recipe
"""

// To generate interleaved text and images, call `generateContent` with the text input
let response = try await model.generateContent(prompt)

// Handle the generated text and image
guard let candidate = response.candidates.first else {
  fatalError("No candidates in response.")
}
for part in candidate.content.parts {
  switch part {
  case let textPart as TextPart:
    // Do something with the generated text
    let text = textPart.text
  case let inlineDataPart as InlineDataPart:
    // Do something with the generated image
    guard let uiImage = UIImage(data: inlineDataPart.data) else {
      fatalError("Failed to convert data to UIImage.")
    }
  default:
    fatalError("Unsupported part type: \(part)")
  }
}

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    generationConfig = generationConfig {
responseModalities = listOf(ResponseModality.TEXT, ResponseModality.IMAGE) }
)

// Provide a text prompt instructing the model to generate interleaved text and images
val prompt = """
    Generate an illustrated recipe for a paella.
    Create images to go alongside the text as you generate the recipe
    """.trimIndent()

// To generate interleaved text and images, call `generateContent` with the text input
val responseContent = model.generateContent(prompt).candidates.first().content

// The response will contain image and text parts interleaved
for (part in responseContent.parts) {
    when (part) {
        is ImagePart -> {
            // ImagePart as a bitmap
            val generatedImageAsBitmap: Bitmap? = part.asImageOrNull()
        }
        is TextPart -> {
            // Text content from the TextPart
            val text = part.text
        }
    }
}

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel(
    "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    new GenerationConfig.Builder()
        .setResponseModalities(Arrays.asList(ResponseModality.TEXT, ResponseModality.IMAGE))
        .build()
);

GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide a text prompt instructing the model to generate interleaved text and images
Content prompt = new Content.Builder()
        .addText("Generate an illustrated recipe for a paella.\n" +
                 "Create images to go alongside the text as you generate the recipe")
        .build();

// To generate interleaved text and images, call `generateContent` with the text input
ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        Content responseContent = result.getCandidates().get(0).getContent();
        // The response will contain image and text parts interleaved
        for (Part part : responseContent.getParts()) {
            if (part instanceof ImagePart) {
                // ImagePart as a bitmap
                Bitmap generatedImageAsBitmap = ((ImagePart) part).getImage();
            } else if (part instanceof TextPart){
                // Text content from the TextPart
                String text = ((TextPart) part).getText();
            }
        }
    }

    @Override
    public void onFailure(Throwable t) {
        System.err.println(t);
    }
}, executor);

import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend, ResponseModality } 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 a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(ai, {
  model: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: {
    responseModalities: [ResponseModality.TEXT, ResponseModality.IMAGE],
  },
});

// Provide a text prompt instructing the model to generate interleaved text and images
const prompt = 'Generate an illustrated recipe for a paella.\n.' +
  'Create images to go alongside the text as you generate the recipe';

// To generate interleaved text and images, call `generateContent` with the text input
const result = await model.generateContent(prompt);

// Handle the generated text and image
try {
  const response = result.response;
  if (response.candidates?.[0].content?.parts) {
    for (const part of response.candidates?.[0].content?.parts) {
      if (part.text) {
        // Do something with the text
        console.log(part.text)
      }
      if (part.inlineData) {
        // Do something with the image
        const image = part.inlineData;
        console.log(image.mimeType, image.data);
      }
    }
  }

} catch (err) {
  console.error('Prompt or candidate was blocked:', err);
}

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

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-2.5-flash-image',
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [ResponseModalities.text, ResponseModalities.image]),
);

// Provide a text prompt instructing the model to generate interleaved text and images
final prompt = [Content.text(
  'Generate an illustrated recipe for a paella\n ' +
  'Create images to go alongside the text as you generate the recipe'
)];

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

// Handle the generated text and image
final parts = response.candidates.firstOrNull?.content.parts
if (parts.isNotEmpty) {
  for (final part in parts) {
    if (part is TextPart) {
      // Do something with text part
      final text = part.text
    }
    if (part is InlineDataPart) {
      // Process image
      final imageBytes = part.bytes
    }
  }
} else {
  // Handle the case where no images were generated
  print('Error: No images were generated.');
}

using Firebase;
using Firebase.AI;

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: new GenerationConfig(
    responseModalities: new[] { ResponseModality.Text, ResponseModality.Image })
);

// Provide a text prompt instructing the model to generate interleaved text and images
var prompt = "Generate an illustrated recipe for a paella \n" +
  "Create images to go alongside the text as you generate the recipe";

// To generate interleaved text and images, call `GenerateContentAsync` with the text input
var response = await model.GenerateContentAsync(prompt);

// Handle the generated text and image
foreach (var part in response.Candidates.First().Content.Parts) {
  if (part is ModelContent.TextPart textPart) {
    if (!string.IsNullOrWhiteSpace(textPart.Text)) {
      // Do something with the text
    }
  } else if (part is ModelContent.InlineDataPart dataPart) {
    if (dataPart.MimeType == "image/png") {
      // Load the Image into a Unity Texture2D object
      UnityEngine.Texture2D texture2D = new(2, 2);
      if (texture2D.LoadImage(dataPart.Data.ToArray())) {
        // Do something with the image
      }
    }
  }
}

import FirebaseAILogic

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
let generativeModel = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [.text, .image])
)

// Provide an image for the model to edit
guard let image = UIImage(named: "scones") else { fatalError("Image file not found.") }

// Provide a text prompt instructing the model to edit the image
let prompt = "Edit this image to make it look like a cartoon"

// To edit the image, call `generateContent` with the image and text input
let response = try await model.generateContent(image, prompt)

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    generationConfig = generationConfig {
responseModalities = listOf(ResponseModality.TEXT, ResponseModality.IMAGE) }
)

// Provide an image for the model to edit
val bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.scones)

// Provide a text prompt instructing the model to edit the image
val prompt = content {
    image(bitmap)
    text("Edit this image to make it look like a cartoon")
}

// To edit the image, call `generateContent` with the prompt (image and text input)
val generatedImageAsBitmap = model.generateContent(prompt)
    // Handle the generated text and image
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel(
    "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    new GenerationConfig.Builder()
        .setResponseModalities(Arrays.asList(ResponseModality.TEXT, ResponseModality.IMAGE))
        .build()
);

GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide an image for the model to edit
Bitmap bitmap = BitmapFactory.decodeResource(resources, R.drawable.scones);

// Provide a text prompt instructing the model to edit the image
Content promptcontent = new Content.Builder()
        .addImage(bitmap)
        .addText("Edit this image to make it look like a cartoon")
        .build();

// To edit the image, call `generateContent` with the prompt (image and text input)
ListenableFuture<GenerateContentResponse> response = model.generateContent(promptcontent);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        // iterate over all the parts in the first candidate in the result object
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                Bitmap generatedImageAsBitmap = imagePart.getImage();
                break;
            }
        }
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend, ResponseModality } 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 a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(ai, {
  model: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: {
    responseModalities: [ResponseModality.TEXT, ResponseModality.IMAGE],
  },
});

// Prepare an image for the model to edit
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(',')[1]);
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

// Provide a text prompt instructing the model to edit the image
const prompt = "Edit this image to make it look like a cartoon";

const fileInputEl = document.querySelector("input[type=file]");
const imagePart = await fileToGenerativePart(fileInputEl.files[0]);

// To edit the image, call `generateContent` with the image and text input
const result = await model.generateContent([prompt, imagePart]);

// Handle the generated image
try {
  const inlineDataParts = result.response.inlineDataParts();
  if (inlineDataParts?.[0]) {
    const image = inlineDataParts[0].inlineData;
    console.log(image.mimeType, image.data);
  }
} catch (err) {
  console.error('Prompt or candidate was blocked:', err);
}

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

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-2.5-flash-image',
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [ResponseModalities.text, ResponseModalities.image]),
);

// Prepare an image for the model to edit
final image = await File('scones.jpg').readAsBytes();
final imagePart = InlineDataPart('image/jpeg', image);

// Provide a text prompt instructing the model to edit the image
final prompt = TextPart("Edit this image to make it look like a cartoon");

// To edit the image, call `generateContent` with the image and text input
final response = await model.generateContent([
  Content.multi([prompt,imagePart])
]);

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

using Firebase;
using Firebase.AI;

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: new GenerationConfig(
    responseModalities: new[] { ResponseModality.Text, ResponseModality.Image })
);

// Prepare an image for the model to edit
var imageFile = System.IO.File.ReadAllBytes(System.IO.Path.Combine(
  UnityEngine.Application.streamingAssetsPath, "scones.jpg"));
var image = ModelContent.InlineData("image/jpeg", imageFile);

// Provide a text prompt instructing the model to edit the image
var prompt = ModelContent.Text("Edit this image to make it look like a cartoon.");

// To edit the image, call `GenerateContent` with the image and text input
var response = await model.GenerateContentAsync(new [] { prompt, image });

var text = response.Text;
if (!string.IsNullOrWhiteSpace(text)) {
  // Do something with the text
}

// Handle the generated image
var imageParts = response.Candidates.First().Content.Parts
                         .OfType<ModelContent.InlineDataPart>()
                         .Where(part => part.MimeType == "image/png");
foreach (var imagePart in imageParts) {
  // Load the Image into a Unity Texture2D object
  Texture2D texture2D = new Texture2D(2, 2);
  if (texture2D.LoadImage(imagePart.Data.ToArray())) {
    // Do something with the image
  }
}

import FirebaseAILogic

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
let generativeModel = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [.text, .image])
)

// Initialize the chat
let chat = model.startChat()

guard let image = UIImage(named: "scones") else { fatalError("Image file not found.") }

// Provide an initial text prompt instructing the model to edit the image
let prompt = "Edit this image to make it look like a cartoon"

// To generate an initial response, send a user message with the image and text prompt
let response = try await chat.sendMessage(image, prompt)

// Inspect the generated image
guard let inlineDataPart = response.inlineDataParts.first else {
  fatalError("No image data in response.")
}
guard let uiImage = UIImage(data: inlineDataPart.data) else {
  fatalError("Failed to convert data to UIImage.")
}

// Follow up requests do not need to specify the image again
let followUpResponse = try await chat.sendMessage("But make it old-school line drawing style")

// Inspect the edited image after the follow up request
guard let followUpInlineDataPart = followUpResponse.inlineDataParts.first else {
  fatalError("No image data in response.")
}
guard let followUpUIImage = UIImage(data: followUpInlineDataPart.data) else {
  fatalError("Failed to convert data to UIImage.")
}

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    generationConfig = generationConfig {
responseModalities = listOf(ResponseModality.TEXT, ResponseModality.IMAGE) }
)

// Provide an image for the model to edit
val bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.scones)

// Create the initial prompt instructing the model to edit the image
val prompt = content {
    image(bitmap)
    text("Edit this image to make it look like a cartoon")
}

// Initialize the chat
val chat = model.startChat()

// To generate an initial response, send a user message with the image and text prompt
var response = chat.sendMessage(prompt)
// Inspect the returned image
var generatedImageAsBitmap = response
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image

// Follow up requests do not need to specify the image again
response = chat.sendMessage("But make it old-school line drawing style")
generatedImageAsBitmap = response
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel(
    "gemini-2.5-flash-image",
    // Configure the model to respond with text and images (required)
    new GenerationConfig.Builder()
        .setResponseModalities(Arrays.asList(ResponseModality.TEXT, ResponseModality.IMAGE))
        .build()
);

GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide an image for the model to edit
Bitmap bitmap = BitmapFactory.decodeResource(resources, R.drawable.scones);

// Initialize the chat
ChatFutures chat = model.startChat();

// Create the initial prompt instructing the model to edit the image
Content prompt = new Content.Builder()
        .setRole("user")
        .addImage(bitmap)
        .addText("Edit this image to make it look like a cartoon")
        .build();

// To generate an initial response, send a user message with the image and text prompt
ListenableFuture<GenerateContentResponse> response = chat.sendMessage(prompt);
// Extract the image from the initial response
ListenableFuture<@Nullable Bitmap> initialRequest = Futures.transform(response, result -> {
    for (Part part : result.getCandidates().get(0).getContent().getParts()) {
        if (part instanceof ImagePart) {
            ImagePart imagePart = (ImagePart) part;
            return imagePart.getImage();
        }
    }
    return null;
}, executor);

// Follow up requests do not need to specify the image again
ListenableFuture<GenerateContentResponse> modelResponseFuture = Futures.transformAsync(
        initialRequest,
        generatedImage -> {
            Content followUpPrompt = new Content.Builder()
                    .addText("But make it old-school line drawing style")
                    .build();
            return chat.sendMessage(followUpPrompt);
        },
        executor);

// Add a final callback to check the reworked image
Futures.addCallback(modelResponseFuture, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                Bitmap generatedImageAsBitmap = imagePart.getImage();
                break;
            }
        }
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend, ResponseModality } 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 a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(ai, {
  model: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: {
    responseModalities: [ResponseModality.TEXT, ResponseModality.IMAGE],
  },
});

// Prepare an image for the model to edit
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(',')[1]);
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

const fileInputEl = document.querySelector("input[type=file]");
const imagePart = await fileToGenerativePart(fileInputEl.files[0]);

// Provide an initial text prompt instructing the model to edit the image
const prompt = "Edit this image to make it look like a cartoon";

// Initialize the chat
const chat = model.startChat();

// To generate an initial response, send a user message with the image and text prompt
const result = await chat.sendMessage([prompt, imagePart]);

// Request and inspect the generated image
try {
  const inlineDataParts = result.response.inlineDataParts();
  if (inlineDataParts?.[0]) {
    // Inspect the generated image
    const image = inlineDataParts[0].inlineData;
    console.log(image.mimeType, image.data);
  }
} catch (err) {
  console.error('Prompt or candidate was blocked:', err);
}

// Follow up requests do not need to specify the image again
const followUpResult = await chat.sendMessage("But make it old-school line drawing style");

// Request and inspect the returned image
try {
  const followUpInlineDataParts = followUpResult.response.inlineDataParts();
  if (followUpInlineDataParts?.[0]) {
    // Inspect the generated image
    const followUpImage = followUpInlineDataParts[0].inlineData;
    console.log(followUpImage.mimeType, followUpImage.data);
  }
} catch (err) {
  console.error('Prompt or candidate was blocked:', err);
}

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

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-2.5-flash-image',
  // Configure the model to respond with text and images (required)
  generationConfig: GenerationConfig(responseModalities: [ResponseModalities.text, ResponseModalities.image]),
);

// Prepare an image for the model to edit
final image = await File('scones.jpg').readAsBytes();
final imagePart = InlineDataPart('image/jpeg', image);

// Provide an initial text prompt instructing the model to edit the image
final prompt = TextPart("Edit this image to make it look like a cartoon");

// Initialize the chat
final chat = model.startChat();

// To generate an initial response, send a user message with the image and text prompt
final response = await chat.sendMessage([
  Content.multi([prompt,imagePart])
]);

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

// Follow up requests do not need to specify the image again
final followUpResponse = await chat.sendMessage([
  Content.text("But make it old-school line drawing style")
]);

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

using Firebase;
using Firebase.AI;

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a Gemini model that supports image output
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "gemini-2.5-flash-image",
  // Configure the model to respond with text and images (required)
  generationConfig: new GenerationConfig(
    responseModalities: new[] { ResponseModality.Text, ResponseModality.Image })
);

// Prepare an image for the model to edit
var imageFile = System.IO.File.ReadAllBytes(System.IO.Path.Combine(
  UnityEngine.Application.streamingAssetsPath, "scones.jpg"));
var image = ModelContent.InlineData("image/jpeg", imageFile);

// Provide an initial text prompt instructing the model to edit the image
var prompt = ModelContent.Text("Edit this image to make it look like a cartoon.");

// Initialize the chat
var chat = model.StartChat();

// To generate an initial response, send a user message with the image and text prompt
var response = await chat.SendMessageAsync(new [] { prompt, image });

// Inspect the returned image
var imageParts = response.Candidates.First().Content.Parts
                         .OfType<ModelContent.InlineDataPart>()
                         .Where(part => part.MimeType == "image/png");
// Load the image into a Unity Texture2D object
UnityEngine.Texture2D texture2D = new(2, 2);
if (texture2D.LoadImage(imageParts.First().Data.ToArray())) {
  // Do something with the image
}

// Follow up requests do not need to specify the image again
var followUpResponse = await chat.SendMessageAsync("But make it old-school line drawing style");

// Inspect the returned image
var followUpImageParts = followUpResponse.Candidates.First().Content.Parts
                         .OfType<ModelContent.InlineDataPart>()
                         .Where(part => part.MimeType == "image/png");
// Load the image into a Unity Texture2D object
UnityEngine.Texture2D followUpTexture2D = new(2, 2);
if (followUpTexture2D.LoadImage(followUpImageParts.First().Data.ToArray())) {
  // Do something with the image
}