What is Nano Banana?

A platform powered by Gemini—Google's next-generation generative AI—that can automatically generate and edit high-quality images from text prompts. Nano Banana and Nano Banana Pro modes create images in a wide range of styles within seconds, with fine-grained control over edits. Handles everything from realistic photography to creative artistic expression via simple text instructions, streamlining visual content production.

Business problems it solves

About "Nano Banana"

How to Use

Log In with Your Google Account

Log in to your Google account in your browser or the Gemini app and launch Gemini.
Select Image Generation Mode

Choose an option such as "Create Image" to proceed to the prompt input screen.
Enter a Prompt

Describe the visual you want to create in Japanese, English, or another language (e.g., "A smiling person by the sea at sunset").
Select a Model (if needed)

Choose between the standard model (Nano Banana) and the higher-performance "Nano Banana Pro (Gemini 3 Pro Image)."
Generate

The AI generates an image based on your prompt. After generation, you can provide additional instructions for editing (e.g., adjusting composition, color tone, or adding text).
Download and Use

Download the generated image and use it in designs, presentations, social media, and more. Generated images may include a watermark indicating they are AI-generated.

Features

Text-to-Image Generation

Generates still images from natural language prompts (text, photorealistic, artistic, etc.).

Detailed Image Editing

After generation, you can provide fine-grained editing instructions for lighting, focus, composition, camera angle, and more.

Multi-Image Compositing and Style Application

Use reference images or style specifications to combine multiple elements into a single visual.

Model Selection

Choose between the accessible standard model (Nano Banana) and the high-accuracy, high-resolution Pro model (Nano Banana Pro).

Multilingual Prompt Support

Prompts can be entered in multiple languages including Japanese and English.

Resolution Support

The Pro model supports up to high-resolution generation (e.g., up to approximately 4K).

Text Rendering Support

Supports text rendering in outputs designed for logos, invitations, posters, and similar uses.

Safety and Identification

Generated content includes transparency measures such as C2PA and SynthID watermarks to indicate AI-generated origin.

Pricing

Gemini's image generation feature is available free for basic use, but paid subscriptions are offered for users who need access to more advanced models or higher usage volumes.

	Free	Google AI Pro	Google AI Ultra
Monthly Fee	¥0	~¥2,900/month	~¥36,400/month
Image Generation	○	○ (fast & high quality)	○ (highest quality)
Model Selection	Standard model	Pro model access	Pro & additional features
Daily Generation Limit	Limited	Significantly increased	Maximized
Video Generation	✗	○	○
Deep Research, etc.	✗	○	○

Free: Standard image generation and prompt responses available.
Google AI Pro: ~¥2,900/month for access to Pro models, video generation, additional credits, and more (first month free).
Google AI Ultra: A higher-tier plan for professionals requiring advanced features, higher performance, and greater usage capacity.

Pricing is based on information as of 2025 and may vary depending on contract type, region, or promotions.

Notes

Free image generation may be subject to usage limits or credit quotas (e.g., a cap on the number of generations or tokens).
With a paid plan, generation volume, resolution, editing features, and exclusive model access limits are significantly relaxed.

Overview

Gemini's image generation feature is a multimodal AI capability that creates high-quality images and visuals from natural language prompts. Even the standard model is free to get started, and paid plans (Pro and above) unlock more powerful models, expanded features, and higher usage capacity.