Cite
Notes
Only stored in your browser.
Attribution
CascadeV: An Implementation of Wurstchen Architecture for Video Generation
arXiv 2025
EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
from 3 papers
Mingyu Guo
Boyuan Liu
Jiangchuan Wei
Shiyue Yan
Chong Luo
Nanning Zheng
Qi Dai
Renjie Chen
Ruoyu Feng
Yichen Zhang