Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-context inconsistency. In this work, we revisit discrete generative modeling and present Uniform discRete diffuSion with metric pAth (URSA), a simple yet powerful framework that bridges the gap with continuous approaches for the scalable video generation. At its core, URSA formulates the video generation task as an iterative global refinement of discrete spatiotemporal tokens. It integrates two key designs: a Linearized Metric Path and a Resolution-dependent Timestep Shifting mechanism. These designs enable URSA to scale efficiently to high-resolution image synthesis and long-duration video generation, while requiring significantly fewer inference steps. Additionally, we introduce an asynchronous temporal fine-tuning strategy that unifies versatile tasks within a single model, including interpolation and image-to-video generation. Extensive experiments on challenging video and image generation benchmarks demonstrate that URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods. Code and models are available at https://github.com/baaivision/URSA
@article{arxiv.2510.24717,
title = {Uniform Discrete Diffusion with Metric Path for Video Generation},
author = {Haoge Deng and Ting Pan and Fan Zhang and Yang Liu and Zhuoyan Luo and Yufeng Cui and Wenxuan Wang and Chunhua Shen and Shiguang Shan and Zhaoxiang Zhang and Xinlong Wang},
journal= {arXiv preprint arXiv:2510.24717},
year = {2025}
}