Video Model

智谱技术团队今天发布并开源最新版本的视频模型 CogVideoX v1.5，相比于原有模型，CogVideoX v1.5 将包含 5/10 秒、768P、16 帧的视频生成能力，I2V 模型支持任意尺寸比例，大幅提升图生视频质量及复杂语义理解。 官方介绍，CogVideoX v1.5 也将同步上线到“清影”平台，并与新推出的 CogSound 音效模型结合，“新清影”将具备如下特性： 质量提升：在…

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…