Cite
Notes
Only stored in your browser.
Attribution
StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation
arXiv 2025
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
from 3 papers
Chong Luo
Qi Dai
Shuyuan Tu
Xintong Han
Yinming Huang
Zhen Xing
Zuxuan Wu
Kai Qiu
Mingyu Guo
Nanning Zheng