Loading...
Browse Models
CogVideoX
Model Family Report
Compatible Apps
Generate images and videos using a powerful low-level workflow graph builder - the fastest, most flexible, and most advanced visual generation UI.
Browse Models
Generate images and videos using a powerful low-level workflow graph builder - the fastest, most flexible, and most advanced visual generation UI.
The CogVideoX family consists of open-weight diffusion transformer models developed by THUDM and Zhipu AI for text-to-video and image-to-video generation. The models utilize a 3D causal variational autoencoder and 3D full attention mechanisms to generate coherent videos up to 10 seconds long at resolutions up to 1360×768, trained on 35 million video clips and 2 billion images.