Analysis of Classifier-Free Guidance Weight Schedulers

arXiv:2404.13040v1 Announce Type: cross
Abstract: Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models. It operates by combining the conditional and unconditional predictions using a fixed weight. However, recent works vary the weights throughout the diffusion process, reporting superior results but without providing any rationale or analysis. By conducting comprehensive experiments, this paper provides insights into CFG weight schedulers. Our findings suggest that simple, monotonically increasing weight schedulers consistently lead to improved performances, requiring merely a …

abstract analysis arxiv classifier cs.cv cs.lg diffusion diffusion models free guidance however image image diffusion predictions process quality reporting results text text-to-image type