Remember that lull in recent months when there weren’t amazing announcements of new “revolutionary” AI video models every day? Well, that lull is over as the AI wars heat up again.
But this AI revolution has been going on for months and years, and it’s clearly becoming harder to keep up with what all the models have to offer these days. We’ve also been working on generated AI video for several years, but it hasn’t yet taken off in a meaningful way.
Will this new Gemini Omni model from Google change anything? The company has a promise of “making everything out of everything,” and it wants to make sure it delivers on that promise, starting with video. But can it be done? Let’s take a look.
Google announces Gemini Omni
Now, Google’s Gemini Omni Flash has arrived as a new AI model to replace the company’s popular Nano Banana model. However, while the Nano Banana focused on image generation and editing, the new Gemini Omni model focuses on video. Or, as the company says, start with video.
The real promise of Gemini Omni is that it is an AI model that can “create anything” from any input. If this sounds a little vague to you, it is to us as well. It actually sounds like any other generative AI video model. To use this model, users input images, audio, video, or text, and the model generates high-quality videos based on real-world knowledge, Google reports.
From there, AI creators can easily edit the video through natural conversation, just like any other LLM-style video model.
Accurate physics and added effects
As far as we can tell, what makes this Gemini Omni model unique is its ability to build scenes that look more realistic than its competitors’ models.
Google is able to do this because it has a deeper knowledge of history, science, and cultural context than its competitors, which it says gives it a more intuitive understanding of physics and other forces such as gravity, kinetic energy, and fluid mechanics.
Along with conversational editing, another big selling point Google is pushing for Gemini Omni is the ability for users to define their generation’s visual language by applying styles, motion, and effects.
AI creators can also create videos that include their own voices using digital avatars, which the company claims will help protect users from harm and control the use of AI tools.
learn more
As always, if you are not interested in AI, there is obviously no obligation to explore these models and technologies further. However, if you are interested for some reason, you can learn more about how you can try Gemini Omni. Click here for Google page.
From an article on your site
Related articles on the web
