Google Unveils “Nano Banana Pro” — a More Advanced Version of Its AI Visual Tool

Google has launched an enhanced version of its popular AI-based image creation and editing tool “Nano Banana,” named Nano Banana Pro. The updated version is built on Google’s newly announced Gemini 3 Pro model, enabling users to generate more accurate, detailed, and context-aware visuals, according to GSM Arena.

Google claims that Nano Banana Pro can be used to easily create nearly any type of visual content—prototypes, infographics, diagrams from handwritten notes, and more.

The new version can generate educational explanations, context-rich diagrams, and real-time illustrations by applying improved reasoning capabilities and fact-based analysis. Integrated with Google Search, it can also provide quick visual summaries of weather updates, sports info, or cooking recipes.

According to Google, Nano Banana Pro is currently the most capable model for generating images with correct and clear text. Whether posters, mockups, or calligraphy—its detailed text rendering has become far more accurate. Thanks to Gemini’s multilingual reasoning capabilities, users can generate, translate, or localize text in multiple languages.

Nano Banana Pro can blend up to 14 images and can consistently maintain the likeness of up to five individuals. Using advanced localized editing, users can select and refine specific areas of an image, change camera angles, adjust color balance, control lighting, and more. It also supports generating visuals in various aspect ratios, including 2K and 4K.

The feature is now available globally under the “Create Images” option in the “Thinking” model of the Gemini app. Free users will get limited access to Pro capabilities, after which the system will revert to the non-Pro version. Google AI Plus, Pro, and Ultra subscribers will receive higher usage quotas. In the U.S., the feature has also been enabled for users in Google Search’s AI mode and NotebookLM.

DBTech/BMT/OR