ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Haofeng Huang, Rui Wan, Widyadewi Soedarmadji, Enshu Liu, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
2025Year
57Top-tier citations
Abstract
Quantization Method specialized for DiT Figure 1: We introduce ViDiT-Q, a quantization method specialized for diffusion transformers used in image and video generation. ViDiT-Q achieves lossless W8A8 quantization and minimal visual quality degradation at W4A8, gaining 2.5x model size reduction and a 1.5x latency speedup. 1
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3b2ace52-ef10-41bd-a490-a33dde42f487Cited by top-tier papers57
- DiTFastAttn: Attention Compression for Diffusion Transformer ModelsZhihang Yuan, Hanling Zhang, Lu Pu, Xuefei Ning et al.NeurIPS 2024 · 134 citations
- Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion ModelsLvmin Zhang, Shengqu Cai, Muyang Li, Gordon Wetzstein et al.NeurIPS 2025 · 132 citations
- Radial Attention: 𝒪(n log n) Sparse Attention with Energy Decay for Long Video GenerationXingyang Li, Muyang Li, Tianle Cai, Haocheng Xi et al.NeurIPS 2025 · 66 citations
- QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action ModelsJingxuan Zhang, Yunta Hsieh, Zhongwei Wan, Haokun Lin et al.CVPR 2026 · 24 citations
- Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive ActivationsChaofan Gan, Yuanpeng Tu, Xi Chen, Tieyuan Chen et al.NeurIPS 2025 · 22 citations
Builds on29
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessTri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra et al.NeurIPS 2022 · 5,493 citations
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations
Related papers
- VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion TransformersJuncan Deng, Shuaiting Li, Zeyu Wang, Hong Gu et al.AAAI 2025 · 12 citations
- DVD-Quant: Data-free Video Diffusion Transformers QuantizationZhiteng Li, Hanxuan Li, Junyi Wu, Kai Liu et al.ICLR 2026 · 13 citations
- Q-DiT: Accurate Post-Training Quantization for Diffusion TransformersLei Chen, Yuan Meng, Chen Tang, Xinzhu Ma et al.CVPR 2025
- VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion TransformersQinkai Xu, Yijin Liu, Yang Chen, Lin F. Yang et al.NeurIPS 2025 · 3 citations
- Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion TransformersWeilun Feng, Chuanguang Yang, Haotong Qin, Xiangqi Li et al.ICML 2025
