Google представляет усовершенствованную Pro-версию генератора изображений Nano Banana с новейшими функциями English Translation: Google unveils enhanced Pro version of the Nano Banana image generator with cutting-edge features

Google has launched a new version of its AI image generation model, called Nano Banana Pro. This update includes enhanced editing features, higher resolution capabilities, precise text rendering, and internet search functionality.

The neural network is built on the flagship LLM Gemini 3, which was introduced in November. The company claims that the Pro version surpasses its predecessor, Nano Banana, by offering the ability to create more detailed images and accurate text in various styles, fonts, and languages.

The model now supports web searches, allowing users to request recipes and receive cards with corresponding descriptions.

Google stated that Nano Banana Pro is designed to provide professionals with greater control over their images. It enables users to manage various aspects such as camera angle, scene lighting, depth of field, focus, and color gradient correction.

Nano Banana supports images with resolutions up to 1024×1024 pixels, while the Pro version offers 2K and 4K options.

On the downside, the new model comes at a higher price and operates at a slower speed. The previous version charged $0.039 for a 1024px image, while the new model costs $0.139 for 1080p or 2K and $0.24 for 4K.

Nano Banana Pro can handle up to 14 objects in a single image while maintaining consistency. The tool is being integrated into many existing Google products.

Gemini now uses this new image generation model by default, but users without a paid subscription face limits on usage. Once the limit is reached, the system automatically reverts to the Nano Banana model.

Subscribers to Google AI Plus, Pro, and Ultra will experience higher limits and access to the model within NotebookLM.

Nano Banana Pro will be accessible in search through the AI Mode for Pro and Ultra users in the U.S. Those on the highest plan will be able to utilize the model’s capabilities within Google’s video service, Flow.

Developers can access the new tool via the Gemini API, Google AI Studio, and Antigravity.

The corporation is also integrating a technology called SynthID for watermarking within the Gemini application. Users will be able to upload an image to a chatbot, which will inform them whether AI was used to create or edit it.

Support for C2PA content authentication will be added in the future.

It’s worth noting that in September, the popularity of Nano Banana propelled Gemini to the top of download charts.