Diffusion Transformers (DiTs) have recently improved video generation quality. However, their heavy computational cost makes real-time or on-device generation infeasible. In this work, we introduce S2DiT, a Streaming Sandwich Diffusion Transformer designed for efficient, high-fidelity, and streaming video generation on mobile hardware. S2DiT generates more tokens but maintains efficiency with novel efficient attentions: a mixture of LinConv Hybrid Attention (LCHA) and Stride Self-Attention (SSA). Based on this, we uncover the sandwich design via a budget-aware dynamic programming search, achieving superior quality and efficiency. We further propose a 2-in-1 distillation framework that transfers the capacity of large teacher models (e.g., Wan 2.2-14B) to the compact few-step sandwich model. Together, S2DiT achieves quality on par with state-of-the-art server video models, while streaming at over 10 FPS on an iPhone.
@article{arxiv.2601.12719,
title = {S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation},
author = {Lin Zhao and Yushu Wu and Aleksei Lebedev and Dishani Lahiri and Meng Dong and Arpit Sahni and Michael Vasilkovsky and Hao Chen and Ju Hu and Aliaksandr Siarohin and Sergey Tulyakov and Yanzhi Wang and Anil Kag and Yanyu Li},
journal= {arXiv preprint arXiv:2601.12719},
year = {2026}
}