Google is upgrading its image-generation model with new editing chops, higher resolutions, more accurate text rendering, and the ability to search the web.
Dubbed Nano Banana Pro, the new model is built on Google’s latest large language model, Gemini 3, released earlier this week. The company claims Nano Banana Pro improves on its predecessor, Nano Banana, with the ability to create more detailed images and accurate text, and generate text in different styles, fonts, and languages.
The model also has web-searching capabilities, so you can do things like ask it to look up a recipe and generate flash cards.
Google says Nano Banana Pro is geared toward giving professionals more control over images, and lets users control aspects like camera angles, scene lighting, depth of field, focus, and color grading. And compared to Nano Banana’s resolution cap of 1024 x 1024px, users can generate 2K or 4K images with Nano Banana Pro.
The company noted that while Nano Banana Pro can generate images at a higher quality, it is slower and costlier than the original model, which cost $0.039 per 1024px image. Comparatively, the new model costs $0.139 for each 1080p or 2K image, and $0.24 for every 4K image.
The new model can use six high-fidelity shots or blend up to 14 objects within an image. It can also maintain consistency and resemblance of up to five people. The company has released a demo app where you can try some of these capabilities.
Nano Banana Pro is being rolled out across many of Google’s existing AI tools. The Gemini app will now use the new model to generate images by default, though users on the free subscription tier will be able to use the model to generate a limited number of images, after which they will be defaulted to the original Nano Banana model.
Techcrunch event
San Francisco
|
October 13-15, 2026
Google AI Plus, Pro, and Ultra subscribers will get higher-generation thresholds, though the company did not disclose the exact limits. These subscribers will also get access to the model within NotebookLM.
Google is also making the model available in search through AI mode for AI Pro and Ultra subscribers in the U.S. Ultra subscribers can access the model in the company’s video tool, Flow, and it is available to Workspace customers in Google Slides and Vids, too.
Developers can tap Nano Banana Pro through the Gemini API, Google AI Studio, and the company’s new IDE, Antigravity.
The company is also baking SynthID, its tech to watermark and detect AI-generated images, into the Gemini app. Users can upload an image, and the chatbot will tell them if the image has been created or modified by the company’s image models.
Google said that over time, it will include support for C2PA content credential detection for content verification.
The story has been updated to reflect Google’s approach to support C2PA.
