Google unveils Nano Banana Pro for advanced image generation

Investing.com -- Google has launched Nano Banana Pro, a new state-of-the-art image generation and editing model built on its Gemini 3 Pro technology.

The new model, announced Thursday, offers enhanced capabilities over the original Nano Banana released earlier this year, including improved text rendering and expanded creative controls.

Nano Banana Pro leverages Gemini’s reasoning abilities and real-world knowledge to create more accurate, context-rich visuals. The model can generate educational explainers, infographics, and diagrams based on provided content or real-world facts. It can also connect to Google Search to visualize real-time information like weather or sports data.

A key improvement is the model’s ability to render legible text directly in images, supporting multiple languages and a variety of textures, fonts, and calligraphy styles. This feature enables users to create detailed text in mockups or posters and translate content across languages.

The new model also offers enhanced creative capabilities, maintaining consistency across up to 14 input images and preserving the resemblance of up to five people in a single composition. Users can blend multiple elements, transform sketches into products, or convert blueprints into photorealistic 3D structures.

Studio-quality controls allow for localized editing, adjustment of camera angles, sophisticated color grading, and scene lighting transformations. The model supports various aspect ratios and offers 2K and 4K resolution options.

Google is rolling out Nano Banana Pro globally in the Gemini app when users select "Create images" with the "Thinking" model. Free-tier users will receive limited quotas before reverting to the original Nano Banana model, while Google AI Plus, Pro, and Ultra subscribers get higher quotas.

The company is also upgrading image generation in Google Ads to Nano Banana Pro and rolling it out to Workspace customers in Google Slides and Vids. Developers can access the technology through the Gemini API, Google AI Studio, and Vertex AI.

To address concerns about AI-generated content, all media created with Google’s tools include the company’s SynthID digital watermark. Users can now upload images to the Gemini app to verify if they were generated by Google AI. While free and Google AI Pro tier users will see a visible watermark (the Gemini sparkle) on generated images, this visible marker will be removed for Google AI Ultra subscribers and users of the Google AI Studio developer tool.

This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.