Google Introduces Nano Banana Pro, Its Most Advanced Image Creation Model Yet

Google has announced Nano Banana Pro, an upgraded image generation and editing system powered by Gemini 3 Pro. The new model builds on the earlier Nano Banana release, adding stronger reasoning abilities, a deeper understanding of real-world information, and noticeably improved visual accuracy.

According to Google, Nano Banana Pro is designed to help users transform ideas, sketches, notes, or live information into clear visuals. The system can also tap into Google Search’s knowledge base, allowing creators to produce more factual and context-aware content.

Google said the new model is not limited to image production alone. It can assist users in generating infographics, diagrams, recipes, mockups, and other visual materials grounded in reliable information. One of its standout upgrades is the ability to render text within images more precisely across a wide range of languages—covering longer passages, stylized fonts, localized designs, and detailed mockups.

The company highlighted further improvements in how the tool merges different visual elements. Nano Banana Pro can blend up to 14 images simultaneously and preserve the likeness of as many as five individuals when generating composite visuals.

Creators will also gain access to expanded editing tools, including localized adjustments, custom camera angles, lighting controls, and depth-of-field settings. The system supports multiple output formats and can export at resolutions up to 2K and 4K.

The rollout will span both consumer and professional Google services. Within the Gemini app, Nano Banana Pro can be found under the “Thinking” option while generating images. Free users will get limited access and then return to the standard Nano Banana, while AI Plus, Pro, and Ultra subscribers will receive larger usage limits. In Search’s AI Mode, US users with Google AI Pro or Ultra subscriptions will also be able to access the model.

For enterprise and creative professionals, Nano Banana Pro will be integrated into Google Ads, Slides, Vids, Flow for video production, and developer platforms such as Gemini API, Google AI Studio, Antigravity, and Vertex AI.

Alongside the model’s release, Google introduced additional features for verifying AI-generated images. All visuals created with Google tools will continue to include SynthID watermarking, and users can now upload an image in the Gemini app to check whether it was generated by Google AI. Images created under the Free and Pro tiers will carry a visible Gemini watermark, while Ultra subscribers and Google AI Studio developers will receive clean, watermark-free outputs.

Google said these steps are part of its commitment to transparency, emphasizing that identifying AI-generated content is essential for user trust.

For a deeper look at all the new capabilities introduced with Nano Banana Pro, you can check out the original coverage from our source.