Gemini Omni is “like a Nano Banana for videos” and the results were incredible

AI Video & Visuals


I use Gemini on my phone for everything from general assistant help and smart home control to creating generative AI. This app tries to be a jack-of-all-trades that lets you create text, images, audio, and video from simple prompts. Gemini Omni is Google’s latest video generation tool, announced at Google I/O 2026 and bundled with June’s Pixel Drop.

Gemini Omni’s calling cards are conversation prompts. Just as Nano Banana can generate images from simple input, Google wants to be able to do the same with Gemini Omni. I tried it on a Pixel 10 Pro, and the experience felt much more polished than any Veo model. I don’t often generate AI videos, but if I do, I’ll be using Gemini Omni from now on. There is also this method.

Gemini Omni is a new model designed for video creation

Gemini Omni on Pixel 10 Pro generates the video.

(Image credit: Brady Snyder / Android Central)

When you open the Gemini app and tap the model picker, you won’t see Gemini Omni. It has 3.1 Flash-Lite, 3.5 Flash, and 3.1 Pro (availability depends on your Google AI subscription), but not Gemini Omni. This is because Gemini Omni is designed specifically for video. In fact, Google’s Gemini Omni landing page says you should “think like a Nano Banana for video.”

from the latest video



Source link