Google улучшила генератор изображений, выпустив Pro-версию Nano Banana с новыми возможностями Translation: Google Enhances Image Generator by Releasing Pro Version of Nano Banana with New Features

Google has introduced a new version of its AI image generation model called Nano Banana Pro. This release includes new editing features, enhanced resolution, accurate text rendering, and internet search capabilities.

The neural network is based on the flagship LLM, Gemini 3, which was unveiled 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 allows web searches, enabling users to request recipes and receive cards with descriptions.

Google has stated that Nano Banana Pro is designed to give professionals greater control over their images. It enables customization of various elements 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 options available in 2K and 4K.

However, there are some drawbacks, including a higher price point and slower processing speed. The previous version charged $0.039 per 1024px image, while the new version costs $0.139 for 1080p or 2K and $0.24 for 4K.

Nano Banana Pro can arrange up to 14 objects within a single image and maintain consistency. This tool is being integrated into various existing Google products.

Gemini now defaults to using the new image generation model, but users without a paid subscription will face limits on the number of images they can generate. Once this limit is reached, the system automatically reverts to the Nano Banana model.

Subscribers to Google AI Plus, Pro, and Ultra will benefit from higher limits and access to the model in NotebookLM.

Nano Banana Pro will be available in search via AI Mode for Pro and Ultra users in the United States. Subscribers of the latter plan will also be able to utilize the model’s capabilities within the company’s video service, Flow.

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

Additionally, the corporation is implementing watermarked technology, SynthID, into the Gemini app. Users can upload an image to the chatbot, which will inform them whether AI was used in its creation or editing.

In the future, support for C2PA will be introduced to verify the authenticity of content.

It’s worth mentioning that in September, the popularity of Nano Banana propelled Gemini into the top downloaded applications.