Nano Banana image generation

Prompt to prototype fully-functional, UI-complete apps, and see Nano Banana 2 integrated with real-world tools, data, and the Gemini ecosystem. All before writing a single line of code.
  • Or build your own from prompts:
  • magazine london restore banana cafe article dog isometric
  • magazine
    Generated by Nano Banana 2
    Prompt: "A photo of a glossy magazine cover, the minimal blue cover has the large bold words Nano Banana. The text is in a serif font and fills the view. No other text. In front of the text there is a portrait of a person in a sleek and minimal dress. She is playfully holding the number 2, which is the focal point.
    Put the issue number and "Feb 2026" date in the corner along with a barcode. The magazine is on a shelf against an orange plastered wall, within a designer store."
  • london
    Generated by Nano Banana Pro
    Prompt: "Present a clear, 45° top-down isometric miniature 3D cartoon scene of London, featuring its most iconic landmarks and architectural elements. Use soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadows. Integrate the current weather conditions directly into the city environment to create an immersive atmospheric mood. Use a clean, minimalistic composition with a soft, solid-colored background. At the top-center, place the title "London" in large bold text, a prominent weather icon beneath it, then the date (small text) and temperature (medium text). All text must be centered with consistent spacing, and may subtly overlap the tops of the buildings."
  • quetzal
    Generated by Nano Banana 2
    Prompt: "Use image search to find accurate images of a resplendent quetzal bird. Create a beautiful 3:2 wallpaper of this bird, with a natural top to bottom gradient and minimal composition."
  • banana
    Generated by Nano Banana Pro
    Prompt: "Put this logo on a high-end ad for a banana scented perfume. The logo is perfectly integrated into the bottle."
  • cafe
    Generated by Nano Banana Pro
    Prompt: "A photo of an everyday scene at a busy cafe serving breakfast. In the foreground is an anime man with blue hair, one of the people is a pencil sketch, another is a claymation person"
  • article
    Generated by Nano Banana Pro
    Prompt: "Use search to find how the Gemini 3 Flash launch has been received. Use this information to write a short article about it (with headings). Return a photo of the article as it appeared in a design focused glossy magazine. It is a photo of a single folded over page, showing the article about Gemini 3 Flash. One hero photo. Headline in serif."
  • dog
    Generated by Nano Banana Pro
    Prompt: "An icon representing a cute dog. The background is white. Make the icons in a colorful and tactile 3D style. No text."
  • isometric
    Generated by Nano Banana 2
    Prompt: "Make a photo that is perfectly isometric. It is not a miniature, it is a captured photo that just happened to be perfectly isometric. It is a photo of a beautiful modern garden. There's a large 2 shaped pool and the words: Nano Banana 2."

Nano Banana is the name for Gemini's native image generation capabilities. Gemini can generate and process images conversationally with text, images, or a combination of both. This lets you create, edit, and iterate on visuals with unprecedented control.

Nano Banana refers to four distinct models available in the Gemini API:

  • Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) (gemini-3.1-flash-lite-image): Our fastest and cheapest Gemini image model, engineered for velocity and scale where speed and cost are the primary operational constraints. Not optimized for multiple reference inputs or multi-turn sequential editing.
  • Nano Banana 2 (Gemini 3.1 Flash Image) (gemini-3.1-flash-image): Serves as the most versatile model, generalist workhorse model for all tasks. It balances speed with state-of-the-art 4K generation, world knowledge, and reliable text rendering. Excelling at multiple reference image processing and consistency.
  • Nano Banana Pro (Gemini 3 Pro Image) (gemini-3-pro-image): The premium choice for the most complex visual tasks, offering the highest level of world knowledge, advanced localization, accurate brand consistency, and precision creative control.
  • Nano Banana (Gemini 2.5 Flash Image) (gemini-2.5-flash-image): The legacy pioneer of the Nano Banana series. While it has been a reliable workhorse, we strongly recommend that customers transition to Nano Banana 2 Lite to experience enhanced quality, faster generation speeds, and lower API pricing.

All generated images include a SynthID watermark.

Image generation (text-to-image)

Python

from google import genai
from PIL import Image
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
)

with open("generated_image.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

async function main() {

  const ai = new GoogleGenAI({});

  const prompt =
    "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme";

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: prompt,
  });
  const generatedImage = interaction.output_image;
  if (generatedImage) {
    const buffer = Buffer.from(generatedImage.data, "base64");
    fs.writeFileSync("gemini-native-image.png", buffer);
    console.log("Image saved as gemini-native-image.png");
  }
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"}
    ]
  }'

You can retrieve generated image data by using the interaction.output_image property, which returns the last generated image block. For details on convenience properties, see the Interactions overview.

Image editing (text-and-image-to-image)

Reminder: Make sure you have the necessary rights to any images you upload. Don't generate content that infringe on others' rights, including videos or images that deceive, harass, or harm. Your use of this generative AI service is subject to our Prohibited Use Policy.

Provide an image and use text prompts to add, remove, or modify elements, change the style, or adjust the color grading.

The following example demonstrates uploading base64 encoded images. For multiple images, larger payloads, and supported MIME types, check the Image understanding page.

Python

from google import genai
from PIL import Image
import base64

client = genai.Client()

with open("/path/to/cat_image.png", "rb") as f:
    image_bytes = f.read()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
          "type": "text",
          "text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        }
    ],
)

with open("generated_image.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

async function main() {

  const ai = new GoogleGenAI({});

  const imagePath = "path/to/cat_image.png";
  const imageData = fs.readFileSync(imagePath);
  const base64Image = imageData.toString("base64");

  const prompt = [
    { type: "text", text: "Create a picture of my cat eating a nano-banana in a" +
            "fancy restaurant under the Gemini constellation" },
    {
      type: "image",
      mime_type: "image/png",
      data: base64Image
    },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: prompt,
  });
  const generatedImage = interaction.output_image;
  if (generatedImage) {
    const buffer = Buffer.from(generatedImage.data, "base64");
    fs.writeFileSync("gemini-native-image.png", buffer);
    console.log("Image saved as gemini-native-image.png");
  }
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"model\": \"gemini-3.1-flash-image\",
      \"input\": [
        {\"type\": \"text\", \"text\": \"Create a picture of my cat eating a nano-banana in a fancy restaurant under the Gemini constellation\"},
        {
          \"type\": \"image\",
          \"mime_type\": \"image/jpeg\",
          \"data\": \"<BASE64_IMAGE_DATA>\"
        }
      ]
    }"

Multi-turn image editing

Keep generating and editing images conversationally. Multi-turn conversation is the recommended way to iterate on images. The following example shows a prompt to generate an infographic about photosynthesis.

Python

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
    tools=[{"type": "google_search"}],
)

with open("photosynthesis.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
    tools: [{"type": "google_search"}],
  });

  const generatedImage = interaction.output_image;
  if (generatedImage) {
    const buffer = Buffer.from(generatedImage.data, "base64");
    fs.writeFileSync("photosynthesis.png", buffer);
    console.log("Image saved as photosynthesis.png");
  }
}

await main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plants favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids cookbook, suitable for a 4th grader."}
    ],
    "tools": [{"type": "google_search"}]
  }'
AI-generated infographic about photosynthesis
AI-generated infographic about photosynthesis

You can then use the previous_interaction_id to change the language on the graphic to Spanish.

Python

interaction_2 = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Update this infographic to be in Spanish. Do not change any other elements of the image.",
    previous_interaction_id=interaction.id,
    response_format={
        "type": "image",
        "mime_type": "image/jpeg",
        "aspect_ratio": "16:9",
        "image_size": "2K"
    },
)

generated_image = interaction_2.output_image
if generated_image:
    with open("photosynthesis_spanish.png", "wb") as f:
        f.write(base64.b64decode(generated_image.data))

JavaScript

const interaction2 = await ai.interactions.create({
  model: "gemini-3.1-flash-image",
  input: "Update this infographic to be in Spanish. Do not change any other elements of the image.",
  previous_interaction_id: interaction.id,
  response_format: {
    type: "image",
    mime_type: "image/png",
    aspect_ratio: "16:9",
    image_size: "2K"
  },
});

const generatedImage = interaction2.output_image;
if (generatedImage) {
  const buffer = Buffer.from(generatedImage.data, "base64");
  fs.writeFileSync("photosynthesis_spanish.png", buffer);
}

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "Update this infographic to be in Spanish. Do not change any other elements of the image.",
    "previous_interaction_id": "<PREVIOUS_INTERACTION_ID>",
    "response_format": {
      "type": "image",
      "mime_type": "image/jpeg",
      "aspect_ratio": "16:9",
      "image_size": "2K"
    }
  }'
AI-generated infographic of photosynthesis in Spanish
AI-generated infographic of photosynthesis in Spanish

New with Gemini 3 image models

Gemini 3 offers state-of-the-art image generation and editing models. Gemini 3.1 Flash Image is optimized for speed and high-volume use-cases, and Gemini 3 Pro Image is optimized for professional asset production. Designed to tackle the most challenging workflows through advanced reasoning, they excel at complex, multi-turn creation and modification tasks.

  • High-resolution output: Built-in generation capabilities for 1K, 2K, and 4K visuals.
    • Gemini 3.1 Flash Image adds the smaller 512px (0.5K) resolution.
    • Gemini 3.1 Flash Lite Image only supports 1K resolution.
  • Advanced text rendering: Capable of generating legible, stylized text for infographics, menus, diagrams, and marketing assets.
  • Grounding with Google Search: The model can use Google Search as a tool to verify facts and generate imagery based on real-time data (e.g., current weather maps, stock charts, recent events).
    • Not supported by Gemini 3.1 Flash Lite Image model.
    • Gemini 3.1 Flash Image adds the integration of Google Image Search Grounding alongside Web Search.
  • Thinking mode: The model utilizes a "thinking" process to reason through complex prompts. It generates interim "thought images" (visible in the backend but not charged) to refine the composition before producing the final high-quality output.
  • Up to 14 reference images: You can now mix up to 14 reference images to produce the final image.
  • New aspect ratios: Gemini 3.1 Flash Lite Image adds 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 aspect ratios.

Use up to 14 reference images

Gemini 3 image models let you to mix up to 14 reference images. These 14 images can include the following:

Gemini 3.1 Flash Lite Image Gemini 3.1 Flash Image Gemini 3 Pro Image
Up to 14 images of objects with high-fidelity to include in the final image Up to 10 images of objects with high-fidelity to include in the final image Up to 6 images of objects with high-fidelity to include in the final image
N/A Up to 4 images of characters to maintain character consistency Up to 5 images of characters to maintain character consistency
N/A N/A Up to 3 images to be used as style references

Python

from google import genai
from google.genai import types
from PIL import Image
import base64

prompt = "An office group photo of these people, they are making funny faces."

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
            "type": "text",
            "text": prompt,
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
    ],
    response_format={
        "type": "image",
        "aspect_ratio": "5:4",
        "image_size": "2K"
    },
)

with open("office.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const input = [
    {
      type: "text",
      text: "An office group photo of these people, they are making funny faces.",
    },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile1 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile2 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile3 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile4 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile5 },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: input,
    response_format: {
      type: "image",
      aspect_ratio: "5:4",
      image_size: "2K",
    },
  });

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('office.png', buffer);
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"model\": \"gemini-3.1-flash-image\",
      \"input\": [
        {\"type\": \"text\", \"text\": \"An office group photo of these people, they are making funny faces.\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_1>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_2>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_3>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_4>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_5>\"}
      ],
      \"response_format\": {
        \"type\": \"image\",
        \"aspect_ratio\": \"5:4\",
        \"image_size\": \"2K\"
      }
    }"
AI-generated office group photo
AI-generated office group photo

Grounding with Google Search

Use the Google Search tool to generate images based on real-time information, such as weather forecasts, stock charts, or recent events.

Note that when using Grounding with Google Search with image generation, image-based search results are not passed to the generation model and are excluded from the response (see Grounding with Google Image Search)

Python

from google import genai
from google.genai import types
import base64
prompt = "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=prompt,
    tools=[{"type": "google_search"}],
    response_format={
        "type": "image",
        "mime_type": "image/jpeg",
        "aspect_ratio": "16:9"
    },
)

with open("weather.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day",
    tools: [{"type": "google_search"}],
    response_format: {
      type: "image",
      mime_type: "image/png",
      aspect_ratio: "16:9",
      image_size: "2K"
    },
  });

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('weather.png', buffer);
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"}
    ],
    "tools": [{"type": "google_search"}],
    "response_format": {
      "type": "image",
      "mime_type": "image/jpeg",
      "aspect_ratio": "16:9"
    }
  }'
AI-generated five day weather chart for San Francisco
AI-generated five day weather chart for San Francisco

The response includes google_search_call and google_search_result steps, along with inline url_citation annotations on the text step:

  • google_search_result: Contains search_suggestions, an HTML snippet for rendering search suggestions in your UI.
  • url_citation annotations: Inline citations on the text step linking parts of the response to their web sources.

Grounding with Google Image Search allows models to use web images retrieved via Google Image Search as visual context for image generation. Image Search is a new search type within the existing Grounding with Google Search tool, functioning alongside standard Web Search.

To enable Image Search, configure the google_search tool in your API request and specify image_search within the search_types array. Image Search can be used independently or together with Web Search.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A detailed painting of a Timareta butterfly resting on a flower",
    tools=[{
      "type": "google_search",
      "search_types": ["web_search", "image_search"]
    }]
)

JavaScript

import { GoogleGenAI } from "@google/genai";

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A detailed painting of a Timareta butterfly resting on a flower",
    tools: [{
      "type": "google_search",
      "search_types": ["web_search", "image_search"]
    }]
  });
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A detailed painting of a Timareta butterfly resting on a flower",
    "tools": [{"type": "google_search", "search_types": ["web_search", "image_search"]}]
  }'

Display requirements

When you use Image Search within Grounding with Google Search, you must display the search_suggestions from the google_search_result step. Full usage requirements are detailed in the Terms of Service.

Response

For grounded responses using image search, the API returns inline citations and attribution metadata as part of the response steps:

  • url_citation annotations: Inline citations on the text content block within model_output, linking the generated content to its source.

  • google_search_result: Contains search_suggestions, an HTML snippet for rendering search suggestions in your UI.

Video-to-image generation (3.1 Flash)

Video-to-image generation allows you to generate new images using a video's context as a multimodal reference. This is useful for creating high-quality video thumbnails, cinematic posters, summary infographics, or new artwork inspired by a video scene.

During generation, the model analyzes the video frames in context to extract visual themes and key events, then uses them alongside your text prompt to synthesize the output image.

You can pass public YouTube URLs directly in your API request or upload local video files using the Files API.

Python

from google import genai
from google.genai import types
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
            "type": "video",
            "uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
            "mime_type": "video/mp4"
        },
        {"type": "text", "text": "Generate a poster image that captures the key themes of this video."}
    ],
    response_format={"type": "image", "aspect_ratio": "16:9"}
)

# Save the generated image part
for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("video_poster.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))
                print("Image saved as video_poster.png")

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: [
      {
        type: "video",
        uri: "https://www.youtube.com/watch?v=UTdfxFyOQTI",
        mime_type: "video/mp4"
      },
      { type: "text", text: "Generate a poster image that captures the key themes of this video." }
    ],
    response_format: {
      type: "image",
      aspect_ratio: "16:9"
    }
  });

  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("video_poster.png", buffer);
          console.log("Image saved as video_poster.png");
        }
      }
    }
  }
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {
        "type": "video",
        "uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
        "mime_type": "video/mp4"
      },
      {
        "type": "text",
        "text": "Generate a poster image that captures the key themes of this video."
      }
    ],
    "response_format": {
      "type": "image",
      "aspect_ratio": "16:9"
    }
  }'
AI-generated infographic from a youtube video
AI-generated infographic from a youtube video

Generate images up to 4K resolution

Gemini 3 image models generate 1K images by default but can also output 2K, 4K, and 512px (05.K) (Gemini 3.1 Flash Image only) images. To generate higher resolution assets, specify the image_size in the response_format.

You must use an uppercase 'K' (e.g. 512px (05.K), 1K, 2K, 4K). Lowercase parameters (e.g., 1k) will be rejected.

Python

from google import genai
from google.genai import types
import base64

prompt = "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=prompt,
    response_format={
        "type": "image",
        "mime_type": "image/jpeg",
        "aspect_ratio": "1:1",
        "image_size": "1K"
    },
)

print(interaction.output_text)

with open("butterfly.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
    response_format: {
      type: "image",
      mime_type: "image/png",
      aspect_ratio: "1:1",
      image_size: "1K",
    },
  });

  console.log(interaction.output_text);

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('butterfly.png', buffer);
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
    "response_format": {
      "type": "image",
      "mime_type": "image/jpeg",
      "aspect_ratio": "1:1",
      "image_size": "1K"
    }
  }'

The following is an example image generated from this prompt:

AI-generated Da Vinci style anatomical sketch of a dissected Monarch butterfly.
AI-generated Da Vinci style anatomical sketch of a dissected Monarch butterfly.

Thinking process

Gemini 3 image models are thinking models that use a reasoning process ("Thinking") for complex prompts. This feature is enabled by default and cannot be disabled in the API. To learn more about the thinking process, see the Gemini Thinking guide.

The model generates up to two interim images to test composition and logic. The last image within Thinking is also the final rendered image.

You can check the thoughts that lead to the final image being produced.

Python

for step in interaction.steps:
    if step.type == "thought":
        for content_block in step.summary:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                image = Image.open(io.BytesIO(base64.b64decode(content_block.data)))
                image.show()

JavaScript

for (const step of interaction.steps) {
  if (step.type === "thought") {
    for (const contentBlock of step.summary) {
      if (contentBlock.type === "text") {
        console.log(contentBlock.text);
      } else if (contentBlock.type === "image") {
        const buffer = Buffer.from(contentBlock.data, 'base64');
        fs.writeFileSync('thought_image.png', buffer);
      }
    }
  }
}

Interleaved text and images

While standard image generation models only output images, some advanced Gemini 3 models (such as gemini-3-pro-image) can generate interleaved content—like stories or instructional guides containing both text blocks and illustrations inside the same response.

Because the output is complex and interleaved, convenience properties like .output_image or .output_text will not capture the full sequence. To access and save interleaved content, you must manually iterate over steps:

Python

interaction = client.interactions.create(
    model="gemini-3-pro-image",
    input="Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
)

image_counter = 1
for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                filename = f"butterfly_lifecycle_{image_counter}.png"
                with open(filename, "wb") as f:
                    f.write(base64.b64decode(content_block.data))
                print(f"\n[Saved illustration: {filename}]\n")
                image_counter += 1

JavaScript

const interaction = await ai.interactions.create({
    model: "gemini-3-pro-image",
    input: "Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
});

let imageCounter = 1;
for (const step of interaction.steps) {
  if (step.type === "model_output") {
    for (const contentBlock of step.content) {
      if (contentBlock.type === "text") {
        console.log(contentBlock.text);
      } else if (contentBlock.type === "image") {
        const buffer = Buffer.from(contentBlock.data, "base64");
        const filename = `butterfly_lifecycle_${imageCounter}.png`;
        fs.writeFileSync(filename, buffer);
        console.log(`\n[Saved illustration: ${filename}]\n`);
        imageCounter++;
      }
    }
  }
}

Controlling thinking levels

With Gemini 3.1 Flash Image, you can control the amount of thinking the model uses to balance quality and latency. The default thinking_level is minimal, and the supported levels are minimal and high.

Python

from google import genai
from PIL import Image
import base64
import io

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A futuristic city built inside a giant glass bottle floating in space",
    generation_config={"thinking_level": "high"},
)

print(interaction.output_text)

image = Image.open(io.BytesIO(base64.b64decode(interaction.output_image.data)))

image.show()

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A futuristic city built inside a giant glass bottle floating in space",
    generation_config: { thinking_level: "high" },
  });

  console.log(interaction.output_text);

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('image.png', buffer);
}
main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A futuristic city built inside a giant glass bottle floating in space",
    "generation_config": {
      "thinking_level": "high"
    }
  }'

Note that thinking tokens are billed by default for thinking models, as the thinking process always happens by default whether you view the process or not.

Other image generation modes

Although Nano Banana image generation models are recommended for most use cases, you can also explore dedicated image generation models:

  • Imagen: Google's text-to-image models optimized for generating high-quality images.
  • Veo: Google's video generation model.

Generate images in batch

All of the image generation capabilities described on this page can also be run as batch jobs using the Batch API, which is ideal if you need to generate many images.You get higher rate limits in exchange for a turnaround of up to 24 hours.

Prompting guide and strategies

This section provides prompt examples and templates for common image generation and editing workflows. Each example includes a re-usable template and a sample prompt for the Interactions API.

Prompts for generating images

The following examples show how to use text prompts to generate various types of images.

1. Photorealistic scenes

Describe a scene in rich detail. The more specific you are, the more control you have over the results.

Template

A photorealistic [type of shot] of a [subject description] in a [setting
description]. [Description of the light]. Shot from a [camera angle]
with a [lens type].

Prompt

A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.

Python

from google import genai
from google.genai import types
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
    response_format=[
        {
            "type": "image",
            "mime_type": "image/jpeg",
            "aspect_ratio": "16:9",
        }
    ],
)

print(interaction.output_text)

with open("coral_reef.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
    response_format: [
      {
        type: "image",
        mime_type: "image/jpeg",
        aspect_ratio: "16:9",
      }
    ],
  });
  console.log(interaction.output_text);

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('coral_reef.png', buffer);
}

main();

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
    "response_format": {
      "type": "image",
      "mime_type": "image/png",
      "aspect_ratio": "16:9"
    }
  }'

2. Stylized illustrations & stickers

Describe the artistic style, subject, and medium. Be specific about the visual detail (bold lines, colors, etc.) for consistent results.

Template

A [style] of a [subject, with details about accessories or actions]
doing [activity]. The design features [visual qualities, e.g., bold outlines,
cel-shading, etc.] and [color/background preference].

Prompt

A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.

Python

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("red_panda_sticker.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

JavaScript

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
  });
  for (const step of interaction.steps) {
    if (step