Google Starts Rolling Out Nano Banana 2 Image Generation Model Across its Services

Google is releasing today Nano Banana 2, its latest image generation model that is now rolling out to the Gemini app, Google Search, Flow, and other products. The new model, also known as Gemini 3.1 Flash Image, can create images faster and with the same quality and reasoning capabilites as Google’s Nano Bana Pro model released in November.

“Nano Banana 2 brings the high-speed intelligence of Gemini Flash to visual generation, making rapid edits and iteration possible. It makes once-exclusive Pro features accessible to a wider audience,” Google said today.

Compared to its predecessor, Nano Banana 2 has access to real-time information from the web and Gemini’s real-world knowledge base, and it can also render and translate text with greater precision. The new model can also render up to 14 different objects in an image, which can now go from 512px to 4K. All images generated with Nano Banana 2 are still labeled with a Synth ID marker.

Nano Banana 2 is replacing Google’s Nano Banana Pro model across the Fast, Thinking, and Pro modes in the Gemini app. It’s also coming to the AI Mode in Search, as well as the Lens feature in the Google mobile app. The Nano Banana Pro model will remain available for specialized tasks for Google AI Pro and Ultra subscribers.