AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
Wenhao Sun, Rong-Cheng Tu, Jingyi Liao, Zhao Jin, Dacheng Tao
Abstract
HunyuanVideo +AsymRnR (30% faster) (original) avg. latency -703s avg. latency -913s prompt: A person is knitting ... FastVideo-Hunyuan +AsymRnR (24% faster) (original) avg. latency -128s avg. latency -159s prompt: A teddy bear is swimming in the ocean ... Figure 1. Quality and speed comparison between baseline models, HunyuanVideo (Team, 2024c) and FastVideo-Hunyuan (Team, 2024a), with our AsymRnR. Our approach enables training-free, lossless acceleration for state-of-the-art video diffusion transformers.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Lune answers from
the full paper · 5 top-tier papers that cite it · related work
Free to start. No credit card required.
Cited by top-tier papers5
- VORTA: Efficient Video Diffusion via Routing Sparse AttentionWenhao Sun, Rong-Cheng Tu, Yifu Ding, Jingyi Liao et al.NeurIPS 2025 · 25 citations
- DDiT: Dynamic Patch Scheduling for Efficient Diffusion TransformersDahye Kim, Deepti Ghadiyaram, Raghudeep GaddeCVPR 2026 · 3 citations
- Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion ModelsLiang Peng, Boxi Wu, Haoran Cheng, Yibo Zhao et al.NeurIPS 2025 · 2 citations
- Dlfr-Gen: Diffusion-Based Video Generation With Dynamic Latent Frame RateZhihang Yuan, Rui Xie, Yuzhang Shang, Hanling Zhang et al.ICCV 2025 · 1 citation
- SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion TransformerTong Shao, Yusen Fu, Guoying Sun, Jingde Kong et al.CVPR 2026 · 1 citation
Builds on29
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari et al.ICML 2024 · 3,620 citations
Related papers
- LESA: Learnable Stage-Aware Predictors for Diffusion Model AccelerationPeiliang Cai, Jiacheng Liu, Haowen Xu, Xinyu Wang et al.CVPR 2026 · 4 citations
- ScalingCache: Extreme Acceleration of DiTs through Difference Scaling and Dynamic Interval CachingLihui Gu, Jingbin He, Lianghao Su, Kang He et al.ICLR 2026
- AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video GenerationHaoyue Tan, Shengnan Wang, Yulin Qiao, Juncheng Zhang et al.CVPR 2026 · 5 citations
- Video-SVD: Efficient Video Diffusion via Orthogonal Basis CompositionZhang Wan, Yu Li, Tianze Huang, Haochen Li et al.ICML 2026
- QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video GenerationJunyi Wu, Zhiteng Li, Zheng Hui, Yulun Zhang et al.ICCV 2025 · 20 citations
