Google Flow Expands With Gemini Omni Model and New Mobile Apps
Google enhances its AI creative studio with the Gemini Omni model for precise video editing and new mobile applications for on-the-go creation. The update also introduces an intelligent agent to assist creators at every stage of their projects.
Google unveils major updates for its Google Flow creative studio, introducing the Gemini Omni Flash model to transform video generation and editing. This new model combines Gemini's intelligence with generative media capabilities, allowing users to blend real-world inspiration with generated content and maintain strict character consistency across scenes.
The company also launches Google Flow Agent, an AI assistant designed to collaborate with creators throughout the entire production process. Built on Gemini models, this agent helps brainstorm dialogue, recommend plot points, and perform batch edits to streamline complex creative workflows.
In addition to these desktop advancements, Google releases dedicated mobile applications for on-the-go creation and expands Google Flow Music with the powerful Lyria 3 Pro model. These new capabilities are available globally to Google AI subscribers, further cementing Flow as a comprehensive AI toolkit for filmmakers and musicians.