Google's newest Gemini Omni model can turn real videos into surreal fever dreams

Video generation has been one of the most compelling creative uses of AI. Among the platforms that have helped fuel the phenomenon is Google’s Veo, especially Gen 3, which has proven incredibly powerful at creating entire scenes with consistent elements and nearly perfect lip-syncs. While Veo 3 (and newer 3.1) has been limited to creating purely AI-generated videos with text and audio, Google is introducing a new model at Google I/O 2026 that goes a step further by letting you modify real-life footage into spectacular clips.

Gemini Omni is Google’s new class of multimodal models that can reform actual footage into something that would probably only exist in your head if it weren’t for AI. It’s arriving first in the form of Omni Flash, which, Google says, can combine multiple forms of input — text, audio, statics, and video — to generate something radically different in any of these formats. However, it’s starting with video, where users will be able to create videos as wild as their wildest fever dreams, while ensuring character consistency across multiple frames.

Gemini Omni not only generates video, but it also essentially thinks the story through by analyzing multiple aspects together. What’s even better is that you can refine the videos it creates using natural language prompts until you get what matches your vision (or something even better).

With Gemini Omni, you can get started by adding your references for images, audio, or video, or just use text to describe your vision. You can also upload your own digital version and use Avatars to create videos featuring characters that look and sound like you.

Google also emphasizes that videos will follow real-life physics, thanks to the model’s understanding of gravity, kinetic energy, and even fluid dynamics. We’ll have to wait to see whether that truly holds in real-life output.

Google has shared two examples, one featuring comedian Adam Waheed and another featuring YouTuber Happy Kelli, to demonstrate Gemini Omni’s capabilities. Along with Adam Waheed’s video at the top, here’s the one featuring Happy Kelli:

Gemini Omni is rolling out with its new Flash model in the Gemini app and will be available to all paying subscribers across Google AI Plus, Pro, and Ultra tiers. Omni will also be available through Flow, Google’s AI film-making tool.

If you want to try it for free, Omni will also be accessible through YouTube, where you can create Remixes of existing Shorts. In addition to the regular YouTube app, it will also be available in YouTube Create. However, Google has yet to confirm whether creators will be able to limit or restrict the remixing of their content using AI.