technology
Google DeepMind Develops Omni Models for Video Generation
Google DeepMind is preparing to release Omni models that generate video from various inputs. The system will also allow users to edit photos using text commands. Further capabilities for audio and image generation are planned after the initial launch.
Audio version
Tap play to generate a narrated version.
Developing·Limited corroboration so far. This page will refresh as more sources emerge.
Google DeepMind is developing a set of models called Omni that will generate video from different types of input. The company plans to focus first on video generation and text-based photo editing. Google DeepMind CEO Demis Hassabis said at the Google I/O conference that the long-term goal for Omni is to let users create any type of media from any type of input.
Post by @techcrunch on X
Omni will generate video and allow users to edit photos through text commands. The company has not announced a release date for this initial version.
Later versions are expected to generate audio from video and images from audio. Google has not provided details on when these additional features will be released. The announcement comes as multiple technology companies continue to develop systems that create media from text or other inputs.
Transparency
1 source · single source
CorroborationModerate · 1 source
