Google has released the Nano Banana Pro, its latest image generation model

Google has unveiled a new model called Nano Banana Pro, based on an advanced model for handling large language models. The company claims the Nano Banana Pro outperforms its predecessor, the Nano Banana, by allowing it to create more detailed images, accurate text, and generate content in a variety of styles, fonts, and languages.

The model also features a web search function, allowing you to, for example, request a recipe and get cards created from it.

Google says the Nano Banana Pro is designed for professional users who want more control over their images. It lets you control settings such as shooting angle, lighting, depth of field, focus and color correction. Unlike Nano Banana, whose resolution is limited to 1024×1024 pixels, Nano Banana Pro supports 2K or 4K image creation.

The company notes that despite the higher quality, the new model is slower and more expensive. For example, the Nano Banana’s image generation cost was $0.039 per 1024-pixel image. Whereas the Nano Banana Pro costs about $0.139 for a 1080p (2K) image and $0.24 for 4K.

The new model can combine up to six high-quality shots and up to 14 objects in a single image. It also supports creating converged images with up to five people. The company has released a demo app to try out some of these features.

Nano Banana Pro is integrated into many existing Google AI tools. The Gemini model now uses it by default to generate images, though free account users will be able to use it for a limited amount, after which the original Nano Banana will be available by default. Google AI Plus, Pro, and Ultra subscribers will get higher limits, as well as access to the model in Notebook LM.

Subscribers of Google AI Plus, Pro, and Ultra will get higher limits, as well as access to the model in Notebook LM.

The model is also available via AI search for AI Pro and Ultra subscribers in the US. Ultra users will be able to use it in the Flow video module, and in Google Slides and Vids for Workspace customers.

Developers can use Nano Banana Pro through the Gemini API, Google AI Studio, or Antigravity’s new IDE.

Google is also incorporating SynthID technology into the Gemini app, which allows users to add watermarks and recognize AI-generated images. Users will be able to upload images, and a chatbot will tell if it’s created or modified by Google’s modelers.

An AI will be able to recognize images that have been created or modified by Google’s AI.

The company plans to eventually introduce support for C2PA technology to verify and authenticate content.