Gemini Omni Flash generates and edits video with physics-aware prompts

Google DeepMind introduced Gemini Omni Flash at I/O 2026. The model accepts combinations of text, images, audio, and video and can represent gravity, kinetic energy, and fluid dynamics. It supports successive edits in conversation and applies SynthID watermarks and C2PA credentials to generated video. It is available in the Gemini app, Google Flow, and YouTube Shorts, with free access in Shorts.

Visit original source