Google launches Nano Banana Pro image model, adds AI image detection in Gemini app

Google has introduced an upgraded version of its popular Nano Banana image-generation model, now dubbed Nano Banana Pro. This enhanced model boasts improved capabilities in reasoning and instruction adherence, allowing users to craft more precise images featuring clear text and execute detailed edits on existing visuals. Accessible through the Gemini app, Nano Banana Pro is available to all users, although free accounts may encounter usage restrictions relatively quickly. This new model is part of the recently launched Gemini 3 Pro, officially known as Gemini 3 Pro Image, a continuation of the quirky naming convention that started with Gemini 2.5 Flash Image. With its advanced features, the Nano Banana Pro can handle intricate prompts, generating high-quality images without the typical AI distortions. Users can even create full infographics seamlessly in a single generation. The model excels in maintaining visual consistency, allowing for the blending of up to 14 images while accurately depicting the features of up to five individuals in the output. In addition to image generation, Google has emphasized enhanced editing capabilities. Users can either refine AI-generated images or upload their own photos for localized adjustments, all while minimizing glitches common in AI outputs. Notably, Nano Banana Pro can modify essential aspects of an image, such as camera angles, color grading, and lighting, without disrupting other elements. Targeting professional users, this new model offers significantly improved resolution options, enabling creations to be rendered at an impressive 4K quality. With these advancements, Google aims to redefine the landscape of digital image creation and editing.