Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion

Songwei Liu, Chao Zeng, Chenqian Yan, Xurui Peng, XING WANG, Fangmin Chen, Xing Mei

Keywords: Diffusion Models, Post-training Quantization

TL;DR: We propose a timestep-aware error compensation scheme that mitigates quantization error accumulation in low-precision diffusion models, achieving SOTA performance through theoretical error propagation analysis and adaptive correction

Abstract: Diffusion models have transformed image synthesis by establishing unprecedented quality and creativity benchmarks. Nevertheless, their large-scale deployment faces challenges due to computationally intensive iterative denoising processes. Although post-training quantization (PTQ) provides an effective pathway for accelerating sampling, the iterative nature of diffusion models causes stepwise quantization errors to accumulate progressively during generation, inevitably compromising output fidelity. To address this challenge, we develop a theoretical framework that mathematically formulates error propagation in Diffusion Models (DMs), deriving per-step quantization error propagation equations and establishing the first closed-form solution for cumulative error. Building on this theoretical foundation, we propose a timestep-aware cumulative error compensation scheme. Extensive experiments on multiple image datasets demonstrate that our compensation strategy effectively mitigates error propagation, significantly enhancing existing PTQ methods. Specifically, it achieves a 1.2 PSNR improvement over SVDQuant on SDXL W4A4, while incurring only an additional $<$ 0.5\% time overhead.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 2540