Google has upgraded its image creation capabilities with Nano Banana Pro, which is powered by the Gemini 3 Pro model.

Google is launching its most advanced image generation model, Nano Banana Pro, across multiple platforms, providing users and professionals with high-quality creative tools and better transparency features. This new model seeks to deliver exceptional control and quality to AI-created images, marking a significant advancement in image generation technology.

Nano Banana Pro, based on Gemini 3 Pro, is a powerful new image generation and editing tool. Google emphasizes that this model is more than a simple upgrade from the original Nano Banana model (based on Gemini 2.5 Flash). It aims to transform ideas into studio-quality designs with superior control, perfect text rendering, and improved knowledge of the world.

The model focuses on quality and utility. Nano Banana Pro utilizes Gemini 3 Pro's enhanced reasoning to produce more accurate, context-aware visuals, such as infographics derived from real data or recipes. Text rendering is another significant improvement. The model is designed to create legible text directly within images, supporting multiple languages and translations.

Nano Banana Pro is available to different users in various ways:

Everyday creators: Accessible in the Gemini app's 'Create images' feature by selecting the 'Thinking' model. Free users have a limited quota before reverting to the original model.

Professionals and businesses: Integrated into Google Ads for advertisers and rolling out to Workspace users in Google Slides and Vids.

Developers: Available through the Gemini API and Google AI Studio, with a Vertex AI rollout for scaled enterprise creation.

Ultra creatives: Google AI Ultra subscribers can access it in Flow, the AI filmmaking tool, for enhanced frame and scene control.

This launch prioritizes content transparency. Google is introducing a verification tool in the Gemini app, allowing users to upload any image to check if it was created by Google AI, using SynthID digital watermarking tech that inserts an imperceptible signal into AI-generated media.

Initially for images, Google intends to extend this technology to video and audio. Also, the visible "Gemini sparkle" watermark is being removed for Google AI Ultra subscribers, to provide a clean canvas for expert work. This dedication to open verification and professional application signals Google's leadership in this field.