Generate images using Imagen

Imagen is Google's high-fidelity image generation model, capable of generating realistic and high quality images from text prompts. All generated images include a SynthID watermark. To learn more about the available Imagen model variants, see the Model versions section.

Migration to Nano Banana

Imagen models are deprecated and will shut down on August 17, 2026. We recommend migrating to Nano Banana for your image generation needs.

Migration involves the following changes:

  • Model name: Use gemini-2.5-flash-image instead of Imagen model names.
  • Method: Use client.models.generate_content instead of client.models.generate_images.
  • Response handling: Nano Banana returns content parts, which may include image data, instead of a specific image response object.

See the Image generation guide for more details and examples.

Generate images using the Imagen models

This example demonstrates generating images with an Imagen model:

Python

from google import genai
from google.genai import types
from PIL import Image
from io import BytesIO

client = genai.Client()

response = client.models.generate_images(
    model='imagen-4.0-generate-001',
    prompt='Robot holding a red skateboard',
    config=types.GenerateImagesConfig(
        number_of_images= 4,
    )
)
for generated_image in response.generated_images:
  generated_image.image.show()

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {

  const ai = new GoogleGenAI({});

  const response = await ai.models.generateImages({
    model: 'imagen-4.0-generate-001',
    prompt: 'Robot holding a red skateboard',
    config: {
      numberOfImages: 4,
    },
  });

  let idx = 1;
  for (const generatedImage of response.generatedImages) {
    let imgBytes = generatedImage.image.imageBytes;
    const buffer = Buffer.from(imgBytes, "base64");
    fs.writeFileSync(`imagen-${idx}.png`, buffer);
    idx++;
  }
}

main();

Go

package main

import (
  "context"
  "fmt"
  "os"
  "google.golang.org/genai"
)

func main() {

  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  config := &genai.GenerateImagesConfig{
      NumberOfImages: 4,
  }

  response, _ := client.Models.GenerateImages(
      ctx,
      "imagen-4.0-generate-001",
      "Robot holding a red skateboard",
      config,
  )

  for n, image := range response.GeneratedImages {
      fname := fmt.Sprintf("imagen-%d.png", n)
          _ = os.WriteFile(fname, image.Image.ImageBytes, 0644)
  }
}

REST

curl -X POST \
    "https://generativelanguage.googleapis.com/v1beta/models/imagen-4.0-generate-001:predict" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
        "instances": [
          {
            "prompt": "Robot holding a red skateboard"
          }
        ],
        "parameters": {
          "sampleCount": 4
        }
      }'
AI-generated image of a robot holding a red skateboard
AI-generated image of a robot holding a red skateboard

Imagen configuration

Imagen supports English only prompts at this time and the following parameters:

  • numberOfImages: The number of images to generate, from 1 to 4 (inclusive). The default is 4.
  • imageSize: The size of the generated image. This is only supported for the Standard and Ultra models. The supported values are 1K and 2K. Default is 1K.
  • aspectRatio: Changes the aspect ratio of the generated image. Supported values are "1:1", "3:4", "4:3", "9:16", and "16:9". The default is "1:1".

  • personGeneration: Allow the model to generate images of people. The following values are supported: