Google has introduced Nano Banana Pro, an upgraded AI image-generation model powered by Gemini 3 Pro, offering improved accuracy and editing capabilities. The tool is now available globally in the Gemini app, though with usage limits for free users. It also includes enhanced features for detecting AI-generated content.
On November 20, 2025, Google rolled out Nano Banana Pro, an enhanced version of its meme-inspired image-generation model. Built on Gemini 3 Pro—formally known as Gemini 3 Pro Image—this update improves reasoning and instruction following, enabling users to create more accurate images with legible text and perform precise edits on existing photos. The model excels at generating usable infographics in a single prompt without typical AI artifacts, and it maintains consistency when blending up to 14 images or preserving the appearance of up to five people.
Access is straightforward in the Gemini app: users select Gemini 3 Pro and enable the "Create images" option. Professional features include localized edits, adjustments to camera angles, color grading, and lighting without affecting other elements, with resolutions up to 4K. However, free users face quick usage limits, while AI Ultra subscribers get the highest allowances and no visible watermarks—though embedded SynthID remains for detection.
To address AI identification challenges, Nano Banana Pro embeds SynthID watermarks and adds C2PA metadata. The Gemini app now allows users to upload images and query, such as "Is this AI?" to check for Google-generated content via SynthID. Early reviews note the model's vast improvement in rendering text within images, potentially leading to wider corporate adoption for designs and advertisements.
This launch builds on previous models like Gemini 2.5 Flash Image, emphasizing professional and creative applications amid growing realism in AI visuals.
