Google Releases Nano Banana Pro, Its Latest Image Generation Model
Google has announced the release of Nano Banana Pro, a significantly enhanced image generation model that boasts improved editing capabilities, higher resolutions, and more accurate text rendering. This new tool is built on top of Google’s recent large language model, Gemini 3, which debuted just this week.
According to Ivan Mehta, TechCrunch’s global consumer tech developer, the latest Nano Banana Pro offers a plethora of innovative features that are bound to revolutionize image generation and editing processes. Some of these key upgrades include the ability to create more detailed images, generate text in various styles, fonts, and languages, as well as seamlessly search the web.
In contrast to its predecessor, Nano Banana Pro is specifically designed for professionals who require a high degree of control over their images. This includes capabilities such as controlling camera angles, scene lighting, depth of field, focus, and color grading – all of which can be done without leaving the Google workspace.
Furthermore, this new model paves the way for increased collaboration between developers and designers. Notably, it allows users to generate 2K or even 4K images, significantly surpassing Nano Banana’s cap of 1024 x 1024px.
However, these upgraded capabilities come at a cost. The company announced that Google AI Plus, Pro, and Ultra subscribers will gain access to higher generation thresholds, but failed to specify the exact limits. These users will also be granted instant access to the model within Notebook LM. In addition, these subscribers can utilize the new Nano Banana Pro through Gemini API, Google AI Studio, and Antigravity.
The company has also made Nano Banana Pro available in search mode for its AI Pro and Ultra subscribers residing in the United States, along with access to Flow for Ultra subscribers and Google Slides and Vids for Workspace customers.
Source: techcrunch.com