Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance

TL;DR

This paper analyzes the limitations of Classifier-Free Guidance in diffusion models, identifies missing components for consistency, and proposes a Gibbs-like sampling method to improve sample quality and diversity in image and audio generation.

Contribution

It introduces a theoretical correction to CFG involving a Rényi divergence term and proposes a Gibbs-like sampling procedure to enhance diffusion model performance.

Findings

Significant improvements in sample quality and diversity over standard CFG.

Theoretical identification of the missing divergence component in CFG.

Effective application to image and text-to-audio generation tasks.

Abstract

Classifier-Free Guidance (CFG) is a widely used technique for improving conditional diffusion models by linearly combining the outputs of conditional and unconditional denoisers. While CFG enhances visual quality and improves alignment with prompts, it often reduces sample diversity, leading to a challenging trade-off between quality and diversity. To address this issue, we make two key contributions. First, CFG generally does not correspond to a well-defined denoising diffusion model (DDM). In particular, contrary to common intuition, CFG does not yield samples from the target distribution associated with the limiting CFG score as the noise level approaches zero -- where the data distribution is tilted by a power $w \gt 1$ of the conditional distribution. We identify the missing component: a R\'enyi divergence term that acts as a repulsive force and is required to correct CFG and render it consistent with a proper DDM. Our analysis shows that this correction term vanishes in the low-noise limit. Second, motivated by this insight, we propose a Gibbs-like sampling procedure to draw samples from the desired tilted distribution. This method starts with an initial sample from the conditional diffusion model without CFG and iteratively refines it, preserving diversity while progressively enhancing sample quality. We evaluate our approach on both image and text-to-audio generation tasks, demonstrating substantial improvements over CFG across all considered metrics. The code is available at https://github.com/yazidjanati/cfgig