Efficient Video Generation and Streaming Systems
StreamDiffusion: A Pipeline-Level Solution for Real-time Interactive Generation
Akio Kodaira*, Chenfeng Xu*, Toshiki Hazama*, Takanori Yoshimoto, Kohei Ohno, Shogo Mitsuhori, Soichi Sugano, Hanying Cho, Zhijian Liu, Masayoshi Tomizuka, Kurt Keutzer. 🔥 10K stars [github][paper][ICCV 2025]. Check the TouchDesigner tutorial for designing your cool demo 😎 [Tutorial][Youtube]
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Haocheng Xi*, Shuo Yang*, Yilong Zhao, Chenfeng Xu (Advise this project, corresponding author), Muyang Li, Xiuyu Li, Yujun Lin, Han Cai, Jintao Zhang, Dacheng Li, Jianfei Chen, Ion Stoica, Kurt Keutzer, Song Han. [ICML 2025] (SparseVideoGenV2 is faster now! See [NeurIPS 2025 Spotlight])
​
I am also very proud to share that to accelerate Video Sparsity computation, we develop Flash-kmeans ! This tool is very powerful!!
Looking Backward: Streaming Video-to-Video Translation with Feature Banks
Feng Liang, Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu. [Project page] [ICLR 2025]
StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
Tianrui Feng, Zhi Li, Shuo Yang, Haocheng Xi, Muyang Li, Xiuyu Li, Lvmin Zhang, Keting Yang, Kelly Peng, Song Han, Maneesh Agrawala, Kurt Keutzer, Akio Kodaira, Chenfeng Xu. [MLSys2026, Website] ​
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Haocheng Xi*, Shuo Yang*, Yilong Zhao, Muyang Li, Han Cai, Xingyang Li, Yujun Lin, Zhuoyang Zhang, Jintao Zhang, Xiuyu Li, Zhiying Xu, Jun Wu, Chenfeng Xu (Advise this project, co-corresponding author), Ion Stoica, Song Han, Kurt Keutzer.
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Yiheng Li, Heyang Jiang, Akio Kodaira, Masayoshi Tomizuka, Kurt Keutzer, Chenfeng Xu [NeurIPS 2024] [paper] ​
​Now we have an improved Immiscible Diffusion! See recent version [Improved Immiscible Diffusion]
