Google rolls out Gemini Omni Flash for autonomous video creation across apps
SMRTR summary
Google has launched Gemini Omni Flash, a multimodal AI model that lets users create and edit videos through simple conversational prompts, combining text, images, audio, and video inputs into one system. Available now in the Gemini app, Google Flow, and YouTube Shorts, the model maintains visual consistency across multiple edits and watermarks all AI-generated content using SynthID. Google plans to expand output formats and access over time.
SMRTR provides this summary for quick context. The original article belongs to Interesting Engineering.
Read the original article