Skip to content

CreativeGoogle DeepMind

Google DeepMind releases Nano Banana Pro image model built on Gemini 3 Pro

Nano Banana Pro at a glance

Nano Banana Pro (Gemini 3 Pro Image) improves in-image text, fact-grounded infographics and multi-image editing, with 2K and 4K output and SynthID watermarking.

What changed with Nano Banana Pro

Nano Banana Pro is Google's image generation and editing model built on Gemini 3 Pro. It can render legible text in several languages, build diagrams from supplied content or Google Search data, blend up to 14 input images and keep up to 5 people consistent, with controls for lighting, camera angle and aspect ratio.

It rolled out in the Gemini app, AI Mode in Search for US subscribers, NotebookLM, Google Ads, Slides and Vids, and for developers in the Gemini API, AI Studio, Antigravity and Vertex AI. All outputs carry an invisible SynthID watermark.

Where to compare Nano Banana Pro

Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.

Why Nano Banana Pro matters for businesses

For small businesses, readable text and brand-consistent edits make AI images more usable for flyers, social posts and product mockups, though human review is still needed before publishing.

Sources for this story

  1. Official
  2. Gemini API changelog (opens in a new tab)

    Google · aistudio.google.com

    Official

Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.

  • #image-generation
  • #google
  • #gemini
  • #nano-banana
  • #synthid

Want this working in your business?

We turn new AI capabilities into agents, voice receptionists, and automations you can actually use.