Google recently unveiled Nano Banana Pro (Gemini 3 Pro Image), a new state-of-the-art image generation and editing model based on Gemini 3 Pro. The model's standout feature is its ability to generate accurate, legible text directly within images across multiple languages—a persistent challenge in AI image generation. Users can now create detailed mockups, posters, and infographics with properly rendered typography in various fonts, textures, and calligraphic styles. This multilingual capability enables easier content localization for international audiences.

Nano Banana Pro leverages Gemini 3's advanced reasoning to produce context-rich visuals, including educational diagrams and data infographics grounded in real-world information. The model can connect to Google Search's knowledge base to generate visualizations of real-time data like weather or sports statistics.

Creative professionals gain powerful new tools including the ability to blend up to 14 images and maintain consistency across up to 5 people, studio-quality editing controls with localized adjustments, and output in resolutions up to 4K. Users can also leverage more fine-grained controls to manipulate camera angles, apply color grading, and transform lighting conditions.

Nano Banana Pro is rolling out across Google's ecosystem, including the Gemini app, Google Ads, Workspace tools, AI Studio, and Vertex AI. All generated images include SynthID watermarks for transparency, and users can now verify whether images were created by Google AI directly within the Gemini app.