Video Generation

32 summarised stories about Video Generation, each linking back to the original source. Browse all topics →

Sunday, 17 May 2026

Simulate real-world places with Project Genie and Street View

Google DeepMind 1 month ago

Google has connected its Genie world-generation model with Street View imagery, allowing users to create interactive virtual environments anchored in real-world locations. The capability launches today for Google AI Ultra subscribers at $200 per month, initially covering places across the U.S. with plans to expand later. Users can now generate imaginative scenes based on actual locations—such as exploring the Golden Gate Bridge underwater or the Fort Worth Stockyards in the 1920s—by selecting a real place and creative style before describing their character.

Creative AI Google Video Generation

Introducing Gemini Omni

Google DeepMind 1 month ago

Google released Gemini Omni Flash, a video generation model that accepts images, audio, video, and text as inputs and allows users to edit videos through natural language commands. The model is rolling out today to all Google AI Plus, Pro, and Ultra subscribers through the Gemini app and Google Flow, with free access launching this week on YouTube Shorts and YouTube Create. Users can now generate videos with consistent characters and realistic physics, edit specific elements conversationally, and create content from mixed input types while all outputs receive SynthID digital watermarks for verification.

Creative AI Gemini Google Video Generation