Google introduces Nano Banana Pro built on Gemini 3 Pro

Google has launched Nano Banana Pro, its latest image generation and editing model built on Gemini 3 Pro. The company stated that the new system provides enhanced reasoning, contextual understanding, and multilingual capabilities for creating and editing visuals.

Nano Banana Pro follows the release of its earlier version earlier this year, which was designed for lightweight photo editing tasks such as restoring images or generating figurines. The new version introduces more advanced tools aimed at users needing higher-quality and more complex visual outputs.

According to the company, the model can generate visuals for prototypes, infographics, diagrams and other design needs. It uses Gemini 3 Pro’s reasoning and access to real-world knowledge, including information from Google Search, to produce context-rich images such as educational explainers, snapshots of real-time data and recipe representations.

The model begins rolling out across the search engine's consumer, professional and enterprise products. In the Gemini app, consumers and students can access it under the ‘Create images’ option using the ‘Thinking’ model.

Free-tier users will have limited access, while paid AI Plus, Pro and Ultra subscribers will receive higher usage quotas. It is also available in AI Mode in Search for Pro and Ultra subscribers in the U.S., and in NotebookLM for subscribers globally.

For professional users, Google Ads will adopt the pro version for image generation, and it is also being introduced in Google Slides and Vids for Workspace customers.

Developers can access the model through the Gemini API, Google AI Studio and Vertex AI, with availability also planned for Gemini Enterprise. In Flow, Google’s AI filmmaking tool, the model is being rolled out to Google AI Ultra subscribers.

The company is expanding tools to verify AI-generated images. All media created using its AI systems includes an invisible SynthID watermark. Users can now upload images into the Gemini app and ask whether they were generated by Google AI. It plans to extend the verification tool to audio and video.

A visible watermark, the Gemini ‘sparkle’, will remain on images generated by free and Google AI Pro tiers. For professional use, the visible watermark will be removed for Google AI Ultra subscribers and images created through Google AI Studio.