00:00Gemini's intelligence is the best of our genitive media models for a new level of world understanding, multi-modality, and
00:07editing.
00:09Models like Leo, Nanabunana, and Genie are able to create extremely realistic videos, images, and interactive simulations.
00:17Although not perfect, they already demonstrate some impressive notions of intuitiveness.
00:22And with Omni, we've now made even more progress.
00:26It's a step change in simulating things like kinetic energy and gravity.
00:31Previous systems would have found these concepts difficult.
00:35Gemini's world knowledge and reasoning really shine in Omni.
00:39It can translate complex ideas into highly accurate videos.
00:43So for example, you can give it a simple prompt, like make a claymation explainer a protein folding, and get
00:50this.
00:51Proteins start as chains of amino acids.
00:53They fold into patterns like the alpha helix, and flat sections called beta sheets, forming a perfect three-dimensional shape.
01:01But the initial generation is just the start.
01:04The creative process is rarely a single step. It's usually iterative.
01:09Just like Nanabunana redefined image editing, Omni gives you a more natural way to edit video with conversational language.
01:17What's really cool is you can give it your own videos, for example this selfie, and change reality in a
01:24really varnished way.
01:28You can easily adjust the details and style, or even add elements.
01:34And the whole scene ought to reflect your new idea.
01:42The simple circle turns into a black hole, or an evening stroll that comes to life.
01:48Anything becomes a canvas for creating entirely new realities.
01:52Let's take a look at what Omni can do.
02:20Let's take a look at what Omni can do.
02:21So let's take a look at what Omni can do.
02:33This's the fact that Omni can progress in ways.
Comments