Google debuts new Omni world model at Google I/O with advanced AI video capabilities

Google unveiled Gemini Omni, a new multimodal world model, and Gemini Omni Flash, its first version focused on AI video generation and editing.

The model can create more realistic videos, understand context-rich prompts, edit clips conversationally, and generate user avatars.

Google is adding SynthID watermarks for provenance and rolling the feature out first to paid Gemini subscribers.

After Gemini users, Google plans to expand the technology to YouTube Shorts and YouTube Create.