TL;DR
- Google has launched Nano Banana Pro, its latest image model, built on Gemini 3 Pro Image.
- It features state-of-the-art reasoning, excellent legible and multilingual text rendering, and the ability to use real-time data from Google Search.
- You can try out Nano Banana Pro globally via the Gemini app with quotas based on subscription tiers.
Back in August, Google launched Nano Banana, its Gemini 2.5 Flash Image model that went viral for doing a great job with human subjects and making it easier to tweak generated images (mostly). People used it for all sorts of creations, such as making mini-figurines for themselves and restoring old photos. Today, Google is introducing Nano Banana Pro based on Gemini 3 Pro Image, making its image model better than ever before.
Don’t want to miss the best from Android Authority?
Nano Banana Pro is built on Gemini 3 Pro, so it packs in all the goodness that comes along with it, like state-of-the-art reasoning and real-world knowledge. Nano Banana Pro goes beyond creating beautiful images, as it can help you create more helpful content, such as explainers, infographics, and diagrams. It can also tap into Google Search’s knowledge base to access real-time information, such as weather and sports, and incorporate it into your designs as needed.
Google’s Prompt for this infographic: Create an infographic that shows how to make elaichi chai
Google also claims that Nano Banana Pro is the best model for creating images with correctly rendered and legible text directly in the image. Since Gemini 3 is excellent at understanding depth, nuance, and multilingual reasoning, you can generate text in multiple languages.
Nano Banana Pro can also blend more elements than before. Users can use up to 14 images and maintain consistency and resemblance of up to five people.
Google’s Prompt: A medium shot of the 14 fluffy characters sitting squeezed together side-by-side on a worn beige fabric sofa and on the floor. They are all facing forwards, watching a vintage, wooden-boxed television set placed on a low wooden table in front of the sofa. The room is dimly lit, with warm light from a window on the left and the glow from the TV illuminating the creatures’ faces and fluffy textures. The background is a cozy, slightly cluttered living room with a braided rug, a bookshelf with old books, and rustic kitchen elements in the background. The overall atmosphere is warm, cozy, and amused.
Google is also enhancing the editing capabilities with improved localized editing, which users can use to adjust camera angles, focus, and even transform scene lighting.
Finally, if you’ve ever torn your hair out trying to get Nano Banana to generate an image of a specific size or aspect ratio, Nano Banana Pro fixes it so that you can generate across a range of available aspect ratios and available 2K and 4K resolutions.
Where can you try out Nana Banana Pro?
Google is rolling out Nano Banana Pro globally in the Gemini app when you select “Create images” with the “Thinking” model. Free-tier users get limited free quotas to try out the new model, after which they will revert to the original Nano Banana model. Google AI Plus, Pro, and Ultra subscribers will get higher quotas.
Do you have Gemini’s new Nano Banana Pro image generator?
104 votes
For AI Mode in Search, Nano Banana Pro is available in the US for Google AI Pro and Ultra subscribers.
For NotebookLM, Nano Banana Pro is available for subscribers globally.
Users across relevant products will retain the option to choose between Nano Banana for fast editing and Nano Banana Pro for more complex compositions.
Google is also bringing Nano Banana Pro to its other services:
- Workspace customers in Google Slides and Vids
- Google Ads
- Gemini API and Google AI Studio
- Google Antigravity
- Vertex AI
- Google Flow for Google AI Ultra subscribers
- Coming soon to Gemini Enterprise
Using AI to check for AI-generated images
With such a significant boost to AI image generation, Google is also upgrading the Gemini app to allow it to identify images generated with Google AI, thanks to SynthID technology. The feature will soon expand to identify AI-generated audio and video as well. Google will also retain the visible Gemini sparkle watermark on images generated by users on the free and Google AI Pro tiers. However, Google AI Ultra subscribers will receive (visible) watermark-free images.
Thank you for being part of our community. Read our Comment Policy before posting.
