The useful question is what changes for users, developers or buyers, and whether the announcement stays industry context or becomes something people can actually use.

Google introduced Gemini Omni, a model designed to simplify video editing and creation by interpreting conversational instructions. It allows users to adjust camera angles, replace objects, or animate sketches into realistic videos. The model combines an understanding of physics with real-world knowledge to produce natural-looking outputs. Developers gained access to Omni, leading to early demonstrations of its capabilities across various projects.

Builder Leon Lin captured a single subject from multiple perspectives using Omni, demonstrating its ability to generate varied camera angles and environments. The model maintained scene coherence while shifting backgrounds, including sidewalks, streets, and buildings. Omni’s precision in adjusting perspectives and maintaining continuity highlights its potential for professional and creative video production.

Carlos Santana used Omni to transform an outdoor scene through voice commands, altering lighting, weather, and seasonal elements. The model seamlessly transitioned between day and night, added rain and snow, and adjusted foliage colors. This showcases Omni’s capacity to edit complex environmental changes without manual intervention, streamlining creative workflows.

Pan utilized Omni in Google Flow to animate hand-drawn sketches, turning everyday objects into whimsical scenes. Examples include a lemon as a submarine and scissors as a shark. Jerrod Lew applied Omni to render a single video in multiple animation styles, from live-action to claymation. Hyperagent demonstrated Omni’s versatility by visualizing design proposals, personifying data, and gamifying task lists.