Analysis of Classifier-Free Guidance Weight Schedulers
Abstract
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-toimage 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 single line of code. In addition, more complex parametrized schedulers can be optimized for further improvement, but do not generalize across different models and tasks.
Domains
Artificial Intelligence [cs.AI]
Fichier principal
TMLR_Guidance_Analysis_HAL.pdf (45.05 Mo)
Télécharger le fichier
thumbnail.png (2.46 Mo)
Télécharger le fichier
| Origin | Files produced by the author(s) |
|---|