AI RESEARCH
Latent-Compressed Variational Autoencoder for Video Diffusion Models
arXiv CS.CV
•
ArXi:2604.16479v1 Announce Type: new Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive number of latent channels can impede the convergence of latent diffusion models and deteriorate their generative performance, even when reconstruction quality remains high.