Google Introduces Gemini Omni: Any-to-Any Video Generation in Consumer Products

Google DeepMind

видео офиц. + СМИ 3 ист. ~1 мин

Google launched Gemini Omni at I/O 2026 — a multimodal model that generates and edits video from any combination of text, images, audio, and video inputs. Gemini Omni Flash is rolling out immediately to Google AI Plus/Pro/Ultra subscribers via the Gemini app and to YouTube Shorts users at no cost. All outputs embed SynthID watermarks.

Почему это важно

First production-grade any-to-any video generation model from a major platform, directly integrated into consumer Google products and YouTube at launch

Важность: 4/5

Any-to-any video gen model GA in consumer Gemini app and YouTube Shorts simultaneously — massive distribution for a new video generation paradigm

gemini text-to-video video-editing multimodal google-io

Связанные пункты

Google I/O 2026: Gemini 4, Jules V2, Firebase Studio GA, Android XR и Aluminium OS — Google DeepMind

Источники

официальный Introducing Gemini Omni — Google Blog

СМИ Google's Gemini Omni turns images, audio, and text into video — TechCrunch

СМИ Google unveils Gemini Omni 'any-to-any' AI model — VentureBeat