Few-step autoregressive (AR) video diffusion models generate videos chunk by chunk and have made efficient video generation practical. However, further accelerating these models toward real-time generation remains challenging, as few-step distillation leaves little cross-step redundancy for existing training-free cachi...
Jia Li, Xu-Rui Peng, Xing Wang et al.· 0 citations
Autoregressive (AR) video diffusion has emerged as a leading paradigm for efficient video generation, yet its practical deployment remains bottlenecked by the trade-off between generation quality and inference efficiency. We attribute this bottleneck to three error sources in AR rollouts: the base model error, the trai...
Jia Li, Xu-Rui Peng, Hao-Wei Zhu et al.· 1 citation
SelfLift is introduced, a self-recovering progressive-resolution framework that derives both transition-repair signals and trajectory-aligned supervision from the generative model itself and reduces end-to-end latency across FLUX, establishing a stronger speed-quality frontier for few-step diffusion.
Ting-Yan Wen, Chen-Qian Yan, Xu-Rui Peng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.