Hands-on with Google’s Nano Banana Pro Image Generator

Corporate Artificial Intelligence Regression It feels inevitable in 2025. From banner ads on websites to outdoor billboards, I am surrounded by images generated by companies using AI tools. Hell, even the bar down the street posts flyers advertising happy hour with that unmistakable hazy amber glow of some AI graphics.

Google on Thursday launched the Nano Banana Pro, the company’s latest image generation model. Many of the updates in this release are aimed at enterprise adoption, starting with the Nano Banana Pro mode in Google Slides Commercial offers To integrate the new model with Google Ads for advertisers globally.

This “Pro” version is a repeat of the Nano Banana model released earlier this year. Nano Banana became a viral sensation after users started posting Personal action figures And other funny creations on social media.

Nano Banana Pro powers the AI ​​tool with a host of new capabilities, such as creating 4K images. You can try it for free within Google’s Gemini app, where paid Google One subscribers can access additional generations.

One specific improvement will be catnip for businesses in this release: text display. From my initial tests of generating output with text, Nano Banana Pro improves on wonky letters and weird misspellings common in many image models, including previous Google releases.

Google wants the images generated by this new model — text and all — to be more polished and production-ready for commercial use cases. “Even if you only have one letter, it’s very clear,” says Nicole Breshtova, image and video product manager at Google DeepMind. “It’s like having two hands with six fingers; it’s the first thing you see.” Part of the reason the Nano Banana Pro is able to generate cleaner text is because it switched to a more powerful base model, the Gemini 3 Pro, she says.