How to use Nano Banana in Gemini, step by step

To use Nano Banana, open Gemini, pick Images in the sidebar or just ask for a picture, and describe what you want. Nano Banana is not a separate app: it is Google’s name for the image models built into Gemini, so the same chat box that answers questions also draws and edits pictures.

This guide follows Google’s own help pages: what each Nano Banana model is, how to generate and edit images step by step, where else Google offers it, how your plan affects it, and what Google says about the SynthID watermark.

What Nano Banana is

Google’s Gemini API documentation calls Nano Banana “the name for Gemini’s native image generation capabilities” and lists three models under that name:

In the Gemini app, the Gemini Apps Help page describes which model you get:

• Nano Banana 2 Lite is used when your Gemini model is set to Flash-Lite. Google says it is for quick images and “isn’t designed for multiple image references or for multiple edits.”
• Nano Banana 2 is used when the Gemini model is set to Flash or Pro. It accepts multiple reference images.
• Nano Banana Pro is available with a Google AI plan, when the model is set to Pro, for redoing an image that needs more detail.

Requirements

According to Google’s help page:

• You must be signed in to Gemini.
• To generate images you must be 13 or over (or the applicable age in your country).
• To edit images, including your own uploaded photos, you must be 18 or over.
• Availability depends on the languages and countries the Gemini app supports.

How to create an image in the Gemini app

These are Google’s steps for a computer:

1. Go to gemini.google.com.
2. At the top left, click Open Sidebar, then Images.
3. Choose a template, or enter your prompt to generate an image with Nano Banana 2.

Google’s own example prompts include “Create an image of a dog riding a surfboard” and “Create an image of a jungle with a river in a splashy watercolor style.” Google’s tips: start with words like draw, generate or create, name a style (photorealistic, charcoal drawing, watercolor painting, cartoon illustration), and describe the subject, what it is doing and the setting.

For better results, use the templates in our Gemini AI photo prompt guide or pick a ready prompt from Nano Banana prompts by use.

How to edit a photo with Nano Banana

Google lists three kinds of edits: changing an image you generated, uploading an image and asking for changes, and uploading several images to build a new one. The steps:

1. Go to gemini.google.com.
2. At the top left, click Open Sidebar, then Library.
3. Find the image you want to edit and click it, or upload an image instead.
4. Under the image, click Chat.
5. In the text box at the bottom, describe the change.
6. Click Submit.

Keep edit prompts specific about what changes and what stays. Google’s developer guide uses wording such as “change only the blue sofa” and “Keep the rest of the room… unchanged.”

How to redo an image with Nano Banana Pro

Paid subscribers can regenerate an image with Nano Banana Pro, which Google says can add detail, “especially for images that use text rendering or for infographics”:

1. Create an image with Nano Banana 2 or Nano Banana 2 Lite.
2. At the bottom right of the image, click More, then Redo with Pro.

Google notes that if you reach your daily quota of Nano Banana 2 images, you cannot redo more images with Nano Banana Pro.

Download, share or export

Hover over an image and click Download full size. Google’s help page says you can download at 2K resolution with a Google AI plan or at 1K without one. To keep working on an image in a document, click More, then Export to Docs.

Where else you can use Nano Banana

Google’s Nano Banana 2 announcement lists these places:

• Gemini app, on web and mobile.
• Google Search, in AI Mode and Lens, through the Google app and mobile and desktop browsers.
• Google AI Studio and the Gemini API, for developers. The API documentation shows the model IDs gemini-3.1-flash-image, gemini-3-pro-image and gemini-2.5-flash-image.
• Flow, Google’s filmmaking tool. Its help page lists Nano Banana Pro, Nano Banana 2 and Nano Banana 2 Lite as Flow’s image models.

Limits by plan

Google’s limits page says Gemini Apps have “compute-based usage limits” that factor in the complexity of your prompt, the models and features you use, and the length of your chat. Limits refresh every 5 hours until you reach a weekly limit, and Google says features “like media generation or Deep Research” consume more of your usage.

Google’s table of relative limits:

To check your usage, go to gemini.google.com and, at the bottom left, select Settings, then Usage Limits. Plan details are in our tracker: Gemini free, Google AI Pro and Google AI Ultra.

SynthID and labeling

The Gemini API documentation states that “All generated images include a SynthID watermark.” Google DeepMind’s Nano Banana 2 page describes SynthID as a tool “that embeds an invisible digital watermark directly into an image, allowing it to be identified as AI generated.” Google also says it pairs SynthID with C2PA Content Credentials, and that the Gemini app can check an uploaded file for SynthID when you ask whether it was made with Google AI.