We haven’t even had enough time to play around with Google’s latest image-generation model, and the tech giant is already rolling out a ‘Pro’ successor that promises several upgrades.
The model I’m talking about is Nano Banana, which is now being succeeded by the Gemini 3 Pro-powered Nano Banana Pro. Gemini 3, for reference, was unveiled just two days ago!
Announced by the tech giant in a new blog post earlier today, the new image generator reportedly uses Gemini’s reasoning capabilities and real-world knowledge to be able to visualize information better than its predecessor. That’s precisely why Nano Banana Pro has a much wider design scope. “From prototypes, to representing data as infographics, to turning handwritten notes into diagrams,” the new model seems to be able to do it all.
Apart from generating visual content that’s only good to look at, the new model can focus on making said content helpful. Think context-rich infographics and diagrams with information that can directly be sourced from Google Search. The model can “connect to Google Search’s vast knowledge base to help you create a quick snapshot for a recipe or visualize real-time information like weather or sports.”
For example, with Nano Banana Pro 2, you can use prompts like “Create an infographic about X plan focusing on interesting information,” or “Create an infographic that shows how to make elaichi chai,” and get results like the images below.
You would have noticed that the examples shared above have correctly rendered and legible text directly in the image. That, too, is a specialty of Nano Banana Pro, alongside the ability to define textures, fonts and calligraphy.
“With Gemini’s enhanced multilingual reasoning, you can generate text in multiple languages, or localize and translate your content so you can scale internationally and/or share content more easily with friends and family,” suggests the tech giant.
Try Nano Banana Pro today!
Elsewhere, Nano Banana Pro can blend elements from up to 14 different images and maintain the consistency and resemblance of up to 5 people across photos, regardless of the output image’s desired complexity.
What this essentially means is that you’ll be able to give the AI tool up to 14 different images, and it can generate results with all of those elements in one shot without losing their original resemblance.
Lastly, the upgraded model brings new creative controls directly into the users’ hands. For example, users now have the option to refine and transform parts of an image with localized editing, paired with the option to adjust camera angles, change the focus, apply color grading, transform scene lighting, and more.
Nano Banana Pro is available to try out now in the Gemini app globally. Switch over to the ‘Thinking’ model first, which should move you over to Gemini 3 Pro, and then select ‘Create images.’ Free users will receive limited daily quotas (Google didn’t quantify). Google AI Plus, Pro, and Ultra users get higher quotas.
Similarly, Nano Banana Pro is also accessible via AI Mode in the US for AI Pro and Ultra subscribers.
