Sampling-Aware Quantization for Diffusion Models

arXiv:2505.02242v2 Announce Type: replace 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.

Related

• Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
• Adversarial Concept Distillation for One-Step Diffusion Personalization
• Reward-Aware Trajectory Shaping for Few-step Visual Generation
• Step-level Denoising-time Diffusion Alignment with Multiple Objectives
• Elucidating the SNR-t Bias of Diffusion Probabilistic Models
• Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

Source: arXiv cs.CV | 2026-04-23