Google’s Nano Banana 2 is a faster version of Nano Banana Pro

Google has launched its new imaging model, the Nano Banana 2, which is powered by Gemini 3.1 Flash Image. The company says the new model has the capabilities, world knowledge and reasoning of the Nano Banana Pro, but can perform tasks at « lightning speed ». This allows for quick editing and quick creation of different iterations using a single prompt.

Nano Banana 2 will give more people access to capabilities previously exclusive to the Pro model. This includes the Pro’s ability to pull real-time information and images from web searches to create, say, infographics and charts. It will also be able to generate text on images for marketing materials and greeting cards.

Google says the Nano Banana 2 can support character likeness for up to five characters in a single workflow, which can be especially valuable if you’re using it to create narratives or visual stories. It can follow precise instructions and for complex queries and can generate up to 4K resolution input with richer textures and sharper details than its predecessors.

Nano Banana Pro can now generate images so realistic it’s almost impossible to tell they’re AI-generated. Google even had to limit its use due to high demand. Whether the Nano Banana 2 can generate images that are significantly better than what the Pro can produce – and whether we can still tell if an image is made by AI – remains to be seen. The new model will replace the Nano Banana Pro in the Gemini app, but Google AI Pro and Ultra subscribers will retain access to the Nano Banana Pro for specialized tasks. It will also be the default model in Search for AI Mode and Lens, as well as Google’s Flow AI creative studio.