Google has introduced a more advanced version of its AI image generator. The new tool, aptly called Nano Banana Pro, is powered by the recently announced Gemini 3 Pro intelligence model.
The upgrade aims to provide a more powerful assistant for visual design. Users can now generate prototypes, infographics, and convert simple sketches into structured diagrams more effectively.
The major focus of the Nano Banana Pro model is delivering smarter, more context-aware visuals. It taps into real-time data through Google Search to create snapshots of information, like a recipe guide or a live sports score graphic. The tool also helps with learning by producing detailed educational diagrams on complex topics.
- How to turn yourself or any object into an action figure with Google Gemini
- 90s AI Yearbook: How to generate your own retro-themed images
Google also claims a massive leap in the AI’s ability to work with text inside images. It can now produce a variety of clear, readable fonts and calligraphy on creations like posters and mockups. This text capability also extends to multiple languages for translation tasks.
For complex edits, Nano Banana Pro can merge as many as 14 separate images. It also does a better job at keeping the look of up to five people consistent across different generated pictures. Users have finer control to alter specific sections of an image or change artistic elements like lighting and color with simple text commands. All images can be saved in 2K or 4K quality.
The feature is now available globally within the Gemini app. To access it, users must select the “Thinking” model and then choose the “Create images” option.