MANILA — Google unveiled Nano Banana 2, the latest iteration of its viral AI image generation tool, promising faster performance and improved instruction-following capabilities.

The company said the model is being rolled out across its Gemini app, AI Mode and Lens features on Search, and Flow, its AI-powered video tool. Nano Banana 2 builds on Gemini’s Flash models, allowing quicker image generation and editing while delivering sharper image details.

Google first released the Nano Banana AI image editor in August, which quickly went viral, drawing 13 million first-time users to the Gemini app in just four days. By mid-October, the app had generated over 5 billion images. An upgraded Nano Banana Pro followed in November.

The launch is part of Google’s broader push to compete with OpenAI, whose internal teams reportedly issued a “code red” after the success of Google’s Gemini 3 model, which helped the Gemini app reach over 750 million monthly active users by December.