Google has unveiled Gemini Omni at its I/O developer conference happening right now, a brand new AI model that can create high-quality video out of pretty much anything you throw at it.
The new model combines a built-in understanding of physics with real-world knowledge. Google says this means the videos you make won’t just look photorealistic, they will actually behave like the real world.
Gemini Omni is built to handle basically everything. You can combine images, audio, video, and text all at once to generate a finished video. You can even add your rough drawings which can be turned into an AI masterpiece.
You can edit your video by just prompting the changes you want to see to change the action, shift the camera’s point of view, or tweak the lighting over multiple turns. Because every new instruction builds on the last one, characters stay consistent, the physics remain, and the scene remembers what happened before.
To start, Google is releasing Gemini Omni Flash, which will be rolling out to the Gemini app (for paid AI Plus, Pro and Ultra subscribers today), Google Flow, and YouTube Shorts. Gemini Omni now replaces the previous Veo 3.1 AI video generator. Google is calling this its Nano Banana (its easy image generator) moment but for video.
Here are some video examples, which look very real it’s hard to tell they are AI:
Want to see more of our stories on Google?
P.S. Want to keep this site truly independent? Support us by buying us a beer, treating us to a coffee, or shopping through Amazon here. Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent Canadian media!
