Google's new AI model can "create anything"

本站添加: 2026-05-26

[00:00:05]A new model that can create anything from any input. It combines Gemini's intelligence with the best of our generative media models for a new level of world understanding, multimodality, and editing.

[00:00:19]Models like Veo, Phenaki, and Genie are able to create extremely realistic videos, images, and interactive simulations.

[00:00:27]Although not perfect, they already demonstrate some impressive notions of intuitive physics.

[00:00:33]And with Omni, we've now made even more progress.

[00:00:36]It's a step change in simulating things like kinetic energy and gravity.

[00:00:41]Previous systems would have found these concepts difficult.

[00:00:45]Gemini's world knowledge and reasoning really shine in Omni.

[00:00:49]It can translate complex ideas into highly accurate videos.

[00:00:54]So, for example, you can give it a simple prompt like make a claymation explainer on protein folding and get this. Proteins start as chains of amino acids. They fold into patterns like the alpha helix and flat sections called beta sheets, forming a perfect three-dimensional shape.

[00:01:12]But the initial generation is just the start. The creative process is rarely a single step. It's usually iterative.

[00:01:19]Just like Phenaki redefined image editing, Omni gives you a more natural way to edit video with conversational language.

[00:01:27]What's really cool is you can give it your own videos. For example, this selfie, and change reality in a really fun way.

[00:01:39]You can easily adjust the details and style or even add elements.

[00:01:44]And the whole scene warps to reflect your new idea.

[00:01:53]A simple circle turns into a black hole or an evening stroll comes to life.

[00:01:58]Anything becomes a canvas for creating entirely new realities. Let's take a look at what Omni can do.

[00:02:07]>> [music] [music] [music] [music] [music]