Last year, Nano Banana used Gemini’s intelligence to generate and edit images. Since then, it has helped millions of people restore ancient photos, design from sketches, and visualize ideas in ways that weren’t possible before. We’ve been building Gemini from the ground up to be natively multimodal, and now we’re taking the next step.
Introducing Gemini Omni, where the Gemini’s ability to reason is combined with the ability to create. Omni is our novel model that can create anything from any source – starting with video. With Omni, you can combine images, audio, video and text as input and generate high-quality videos based on Gemini’s real-world knowledge. You can also easily edit your videos by chatting.
Today we are introducing the first model in the Omni family: Gemini Omni Flash, for Gemini apps, Google Flow and YouTube Shorts. Over time, we will support output formats such as video and audio. Here are some of the features that make Omni stand out:
Edit your videos by chatting
Gemini Omni makes video editing easier – using natural language. Each statement builds on the last one. Your characters stay consistent, the physics don’t change, and the scene remembers what came before.
Transform the world around you. Change specific things or change everything. Your film becomes a starting point for something you would never film on your own.