Beyond Fixed: Aligning Guidance with Diffusion Dynamics via Exponential Scaling

Jiayang Gao, Tianyi Zheng, Jiayang Zou, Fengxiang Yang, Shice Liu, Luyao Fan, Zheyu Zhang, Hao Zhang, Jinwei Chen, Peng-Tao Jiang, Bo Li, Jia Wang

Keywords: Diffusion model

Abstract:

Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirical and overlooks the inherent dynamics of the diffusion process.
In this paper, we provide a rigorous theoretical analysis of the Classifier-Free Guidance. Specifically, we establish strict upper bounds on the score discrepancy between conditional and unconditional distributions at different timesteps based on the diffusion process.
This finding explains the limitations of fixed-weight strategies and establishes a principled foundation for time-dependent guidance. Motivated by this insight, we introduce **Exponential Classifier-Free Guidance (E-CFG)**, a novel, training-free method that aligns the guidance strength with the diffusion dynamics via an exponential decay schedule. Extensive experiments show that E-CFG not only enhances controllability but also demonstrates significant performance gains across various benchmarks, including conditional image and text-to-image generation.

Primary Area: generative models

Submission Number: 1953