Nano Banana 2 Brings Pro-Level Image Generation at Flash Speed

Google DeepMind is doubling down on its quirky naming strategy. The company launched Nano Banana 2, its latest image generation model that combines the advanced features of Nano Banana Pro with the speed of Gemini Flash.

Announced February 26, 2026, Nano Banana 2 (also known as Gemini 3.1 Flash Image) delivers "Pro-level image generation and editing, at Flash speed," according to the company. The model brings Gemini Flash's rapid processing to visual creation, making rapid edits and iteration possible for more users.

The model includes several Pro-level features now accessible at speed: advanced world knowledge pulled from Gemini's real-time information and web search; precision text rendering for marketing mockups and localized content; subject consistency maintaining up to five characters and 14 objects in a single workflow; and production-ready specs with aspect ratios from 512px to 4K.

"We're bringing the best of both worlds to users across Google," wrote product manager Naina Raisinghani in the announcement.

Nano Banana 2 is rolling out across Google products including the Gemini app (replacing Nano Banana Pro across Fast, Thinking, and Pro models), Search (AI Mode and Lens), AI Studio and the Gemini API, Google Cloud's Vertex AI, Flow, and Google Ads. Google AI Pro and Ultra subscribers can still access Nano Banana Pro for specialized tasks via the regenerate menu.

On the provenance front, DeepMind continues to expand SynthID, its AI image watermarking technology. Since launching in November, the SynthID verification feature in the Gemini app has been used over 20 million times. Google is also coupling SynthID with C2PA Content Credentials to provide more comprehensive provenance tracking.

The original Nano Banana went viral in August 2025, and Nano Banana Pro launched in November 2025—making this the third iteration in less than a year.