Video Model

Wisdom Spectrum technology team today released and open-sourced the latest version of the video model CogVideoX v1.5, compared to the original model, CogVideoX v1.5 will include 5/10 second, 768P, 16 frame video generation capabilities, I2V model support for any size scale, significantly improve the quality of graphical video and complex semantic understanding. Officially, CogVideoX v1.5 will also be synchronized to the "ClearVideo" platform, and combined with the newly launched CogSound sound model, the "new ClearVideo" will have the following features: Quality Improvement: In the ...

Researchers from the Ecole des Mines de Paris and the Technion-Israel Institute of Technology jointly launched an innovative video model, Slicedit. This model can modify the main objects in a video without changing the background of the video. For example, a surfer can be turned into Iron Man, or a boy spinning a ball can be turned into NBA superstar Curry. The Slicedit model combines the diffusion model of Vincent images with the preprocessing of spatiotemporal video slices. Although the modified video may appear a little blurry and distorted, for amateurs who are not familiar with professional video editing software, Slicedit provides a…