Google Debuts New Omni World Model with Advanced AI Video Capabilities at Google I/O

AI Video & Visuals


Google announced a brand new AI world model called Gemini Omni at Google I/O 2026.

Google calls Gemini Omni “a new model that can create anything from any output,” but the showcase focused on the AI ​​model’s video generation capabilities.

The first release within the Omni AI model family is called Gemini Omni Flash.

gemini omni


Credit: Google

So what’s special about Gemini Omni Flash compared to other AI video tools and Google’s Genie world model?

In a presentation at Google I/O, Google DeepMind CEO Demis Hassabis described Omni as an important step toward AGI. Hassabis said that in the future, Omni will be able to output “anything” a user wants. Unlike text-to-video tools like Google Veo, Gemini Omni is multimodal in both input and output. This means users can input text, audio, images, and video into the model, and Omni leverages Gemini’s “real-world knowledge” to generate unique, interactive worlds.

Google says Omni will now be able to generate videos using more accurate physics, resulting in more realistic-looking content. Gemini can also understand the context of prompts, such as historical facts, to generate more accurate video content.

Screenshot of a Google IO presentation showing the Google Omni World model


Credit: Google

In addition to generating videos, users can also edit videos through conversations with the Omni model, according to Google. At I/O, Google showed some samples of what you can edit with Omni. For example, users can shoot self-recorded or AI-generated videos and edit specific parts of the clip. If a user likes the shot but wants to change the background, they can do so using Omni. Omni shoots video and allows you to change the style, angle, scenery, and even certain details within the clip.

gemini omni


Credit: Google

Gemini Omni Flash allows users to create their own digital portraits through avatars. However, Google says it is still testing this feature to ensure a responsible release.

All Omni-generated videos are embedded with a SynthID watermark to ensure they’re AI-generated.

Google is rolling out Gemini Omni Flash today to paid Google AI Plus, Pro, and Ultra subscribers within the Gemini app and Google Flow. Later this week, Gemini Omni Flash will also be available for free on YouTube Shorts and the YouTube Create app.

Looking for more Google I/O announcements? Follow the Mashable Google I/O live blog Check out all the latest news on Gemini, Chrome, and Android.



Source link