Substrate
Topic

multimodal-models

1 stories related to this topic, newest first.

Google Introduces Gemini Omni Model for Video Generation and EditingEngadget
technology13 days ago

Google Introduces Gemini Omni Model for Video Generation and Editing

Google announced Gemini Omni, a multimodal AI model that processes text, images, audio, and video to create and edit video content. The first version, Gemini Omni Flash, is available today in the Gemini app, YouTube Shorts, and Flow.

TechCrunch
1 source