In a company blog post, Google said the new model enables users to create detailed visual content ranging from prototypes and infographics to diagrams derived from handwritten notes.

The tool is designed to generate context-rich images using improved world knowledge and real-time information.

Google said Nano Banana Pro can produce educational explainers, infographics and diagrams based on user inputs or verified real-world data.

The model can also draw on Google Search to build visuals such as recipe snapshots and real-time weather or sports information.

The company described Nano Banana Pro as its most capable model for generating images with correctly rendered and legible text.

Josh Woodward, vice president of Google Labs and Gemini, told CNBC that the upgraded model offers expanded functionality, including character consistency across multiple images and the ability to incorporate up to 14 visuals in a single workflow. 

He said the tool’s ability to convert traditionally non-visual concepts into graphic formats has been a key attraction for users.

The earlier Nano Banana app had gone viral for its ability to turn user photos into hyperrealistic 3D figurines.

Woodward said in September that the product contributed to the Gemini app gaining 13 million users in four days.