Tag: video-generation
-
Google DeepMind team discusses Gemini Omni video model capabilities
539BGoogle introduced Gemini Omni, a model for generating content from any input, with its first release being Gemini Omni Flash, which enables video generation and editing through conversational interaction. Three Google DeepMind team members—research scientist Mohammad Babaeizadeh, product manager Anish Nangia, and research engineer Sarah Xu—discussed the model's vision and why video generation was chosen as the starting point. The team demonstrated the model's potential applications, including style transfers and object insertion.