Sampling-Aware Quantization for Diffusion Models
Qian Zeng, Jie Song, Yuanyu Wan, Huiqiong Wang, Mingli Song
Abstract
Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and resource-limited environments. Previous research has endeavored to address these limitations in a decoupled manner, utilizing either advanced samplers or efficient model quantization techniques. In this study, we uncover that quantization-induced noise disrupts directional estimation at each sampling step, further distorting the precise directional estimations of higher-order samplers when solving the sampling equations through discretized numerical methods, thereby altering the optimal sampling trajectory. To attain dual acceleration with high fidelity, we propose a sampling-aware quantization strategy, wherein a Mixed-Order Trajectory Alignment technique is devised to impose a more stringent constraint on the error bounds at each sampling step, facilitating a more linear probability flow. Extensive experiments on sparse-step fast sampling across multiple datasets demonstrate that our approach preserves the rapid convergence characteristics of high-speed samplers while maintaining superior generation quality. Code is publicly available at: https://github.com/TaylorJocelyn/ Sampling-aware-Quantization.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- RePaint: Inpainting using Denoising Diffusion Probabilistic Models cites Denoising Diffusion Probabilistic Models
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps cites Denoising Diffusion Probabilistic Models
- Directly Denoising Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Directly Denoising Diffusion Models cites DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
- Directly Denoising Diffusion Models cites Denoising Diffusion Probabilistic Models
Builds on24
- 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
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 StepsCheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen et al.NeurIPS 2022 · 2,653 citations
- RePaint: Inpainting using Denoising Diffusion Probabilistic ModelsAndreas Lugmayr, Martin Danelljan, Andrés Romero, Fisher Yu et al.CVPR 2022 · 1,425 citations
Related papers
- SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal SparsityZichen Fan, Steve Dai, Rangharajan Venkatesan, Dennis Sylvester et al.DAC 2025 · 3 citations
- Align Your Steps: Optimizing Sampling Schedules in Diffusion ModelsAmirmojtaba Sabour, Sanja Fidler, Karsten KreisICML 2024 · 74 citations
- Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value ApproachYuchen Jiao, Na Li, Changxiao Cai, Gen LiICML 2026 · 1 citation
- D2-DPM: Dual Denoising for Quantized Diffusion Probabilistic ModelsQian Zeng, Jie Song, Han Zheng, Hao Jiang et al.AAAI 2025 · 1 citation
- TCFG: Truncated Classifier-Free Guidance for Efficient and Scalable Text-to-Image AccelerationXiaomeng Fu, Jia LiICCV 2025 · 1 citation
