people · May 20, 2026
Google DeepMind Launches Gemini Omni Video Generation Model at Google I/O
Share the canonical public link.
Google DeepMind launched Gemini Omni, its first step toward a model that can create anything from anything starting with video. The release at Google I/O on May 19, 2026 combines Gemini intelligence with generative media systems for world understanding, multimodality and editing. CEO Demis Hassabis stated the end goal enables people to create anything from any input, with initial focus on video generation and text-based photo editing. Google plans future expansions to audio-from-video and image-from-audio generation.
Below validation threshold — auto-passed without scoring