Google’s Nano Banana 2.1: Faster, Smarter AI Images

Google has introduced Nano Banana 2.1, its latest model for generating and editing images. The company says it offers better image quality, stronger instruction-following and lower costs.

Users can create visuals by simply describing what they want in a text prompt. The model is designed to understand detailed instructions and keep important image elements consistent.

Nano Banana 2.1 supports up to 14 reference images in a single creation. It can maintain consistency across up to four characters and 10 objects, useful for visual series.

Users can change clothing, replace backgrounds, add or remove objects and alter image styles. These edits can be made without recreating the entire image from scratch.

Google says the model handles text inside images better, helping with posters, diagrams and infographics. It supports 1K, 2K and 4K image generation, with different reasoning levels available.

Nano Banana 2.1 can use information from Google Search and Image Search while generating visuals. The feature can help create images based on real-world information and references.

A 1K image costs about $0.0336, while a 4K image costs around $0.0756 through the API. Google says the lower pricing could make large-scale AI image generation more affordable for developers and businesses.