Google has announced Gemini Omni, with the first model being Gemini Omni Flash. This is a new family of generative AI models that combines Gemini’s reasoning capabilities and the ability to create content from text, images, audio and video.
The first model in the lineup is Gemini Omni Flash. It focuses on video generation and editing.
Gemini Omni Flash allows users to create videos from prompts or reference materials and refine them through natural language conversations.
According to Google, Gemini Omni can understand real-world concepts such as physics, historical context and scientific principles.
Users can upload images, video clips, and voice references to guide the output while maintaining consistent characters and scenes across multiple edits.
Google is also introducing Avatars which let users create digital versions of themselves using their own voice for video generation.
To help identify AI-generated content, all videos created with Gemini Omni include Google’s invisible SynthID watermark. These can be verified through the Gemini app, Gemini in Chrome and Google Search.
Gemini Omni Flash is rolling out today to Google AI Plus, Pro and Ultra subscribers worldwide through the Gemini app and Google Flow. It is also becoming available for free in YouTube Shorts and the YouTube Create app starting this week.
Google says support for additional output formats, including images and audio, will be added in the future.
0 Comments
Leave a Reply