← Back to AI Tools

Nano Banana Pro Image Generation & Editing Model

Google's image generation and editing model built on Gemini 3 Pro, officially named Gemini 3 Pro Image: best-in-class at rendering legible text inside an image, from a short tagline to a full paragraph, and it uses Gemini 3's reasoning and real-world knowledge to make infographics, mockups and posters more reliable

Tool Interface

Interactive tool will be available soon

Features

  • ✓ Text rendering inside images is the headline capability: short taglines or long paragraphs come out legible, with a wider variety of textures, fonts and calligraphy
  • ✓ Built on Gemini 3 Pro, it uses the model's reasoning and world knowledge to visualise information better, suiting infographics, diagrams and data visualisation
  • ✓ Stronger editing: refine specific parts of an image with text prompts, adjust aspect ratios, boost resolution and shift camera angle and lighting
  • ✓ Multilingual capability rides on Gemini's enhanced multilingual reasoning, so visuals can be localised with translated text
  • ✓ Available across Google products including the Gemini app, Google Ads and Google AI Studio, and also integrated into Adobe Firefly and Photoshop

How to Use

  1. Read the official launch page at https://blog.google/innovation-and-ai/products/nano-banana-pro for capabilities and availability
  2. Pick Nano Banana Pro (Gemini 3 Pro Image) in the Gemini app or Google AI Studio
  3. Generate a first draft from one clear description, and if the image needs text, put the exact wording in the prompt
  4. Refine with text instructions: change specific text, adjust ratio or resolution, and shift camera angle and lighting until it matches

FAQ

What is Nano Banana Pro?

It is Google's image generation and editing model, officially named Gemini 3 Pro Image; the official page is https://blog.google/innovation-and-ai/products/nano-banana-pro . Google describes it as built on Gemini 3 Pro, using Gemini's reasoning and real-world knowledge to visualise information, and as the best model for creating images with correctly rendered and legible text.

How is it different from the earlier Nano Banana?

Per Google, Nano Banana Pro is built on Gemini 3 Pro, fusing image generation and editing with Gemini 3's reasoning and world knowledge. Google singles out text rendering: short taglines or long paragraphs come out clearly, with a wider variety of textures, fonts and calligraphy, plus multilingual reasoning for localised visuals.

Can it write Chinese text inside an image?

Google states the model supports multiple languages and relies on Gemini's enhanced multilingual reasoning for in-image text and localisation. In practice, put the exact copy in the prompt and specify the language explicitly. Check Google's official docs and your own tests for coverage and quality per language.

What kinds of edits can it do?

Google and Adobe both describe prompt-based refinement of specific parts of an image, adjusting aspect ratio, increasing resolution and even shifting camera angle and lighting, along with clean, well-integrated text inside the image. Describing exactly what should change is more controllable than asking for a full redraw.

Where can I use it?

Google says Nano Banana Pro is available across Google products such as the Gemini app, Google Ads and Google AI Studio, with developer access through the Gemini API (model docs at https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image ) and Google Cloud's agent platform. Adobe has also integrated it into Firefly and Photoshop's Generative Fill.

Is it free or paid?

Availability and quotas vary by product and plan: on Google's side the Gemini app and AI Studio each have their own free and paid tiers, the API is billed per Google's pricing, and Adobe access follows your subscription. Check Google's official pricing page and Adobe's documentation for the latest.