Today, the Zhipu Technology team released its latest video generation model, CogVideoX v1.5, and made it open source. This version is another significant advancement in the CogVideoX series launched by the Zhipu Technology team since August. The update greatly enhances video generation capabilities, including support for 5-second and 10-second video lengths, 768P resolution, and the ability to generate 16 frames. Additionally, the I2V (Image-to-Video) model supports arbitrary aspect ratios, further improving the understanding of complex semantics.

With the rapid development of artificial intelligence technology, the image-to-video (I2V) generation technology has become a hot research topic. Recently, a team consisting of researchers Xiaoyu Shi, Zhaoyang Huang, and others has introduced a new framework called Motion-I2V. This framework achieves more consistent and controllable image-to-video generation through explicit motion modeling. This technological breakthrough not only improves the quality and consistency of video generation but als