Gemini Omni: the text-to-video era is over

The era of merely writing text or drawing images is now behind us, making way for a completely new milestone in the AI industry—data-grounded, logical video generation where reasoning meets creation. The next-generation multimodal artificial intelligence system, Gemini Omni, has been officially announced!

This new model provides the game development, advertising, and media sectors with the ability to edit videos through natural language in a continuous, conversational manner, while creating visuals that adhere to real-world laws of physics. Furthermore, it seamlessly synchronizes static images, video templates, and audio tracks to produce professional promos in a matter of seconds, alongside digital avatars capable of speaking in hundreds of different languages.

Read more on Pivot.uz

@pivotglobaal