Minute-Long Videos with Dual Parallelisms

Zeqing Wang; Bowen Zheng; Xingyi Yang; Zhenxiong Tan; Yuecong Xu; Xinchao Wang

AAAI 2026technical0 citations

Minute-Long Videos with Dual Parallelisms

Zeqing Wang, Bowen Zheng, Xingyi Yang, Zhenxiong Tan, Yuecong Xu, Xinchao Wang

Abstract

Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos. To address this, we propose a novel distributed inference strategy, termed DualParal. The core idea is that, instead of generating an entire video on a single GPU, we parallelize computation by partitioning both video frames and model layers across multiple GPUs. However, a naive parallel implementation is not feasible. Because all frames need to share the same noise level, they can

BibTeX

@inproceedings{aaai2026_minutelongvideos,
  title = {Minute-Long Videos with Dual Parallelisms},
  author = {Zeqing Wang and Bowen Zheng and Xingyi Yang and Zhenxiong Tan and Yuecong Xu and Xinchao Wang},
  booktitle = {AAAI 2026},
  year = {2026}
}