Papers
arxiv:2407.02687

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Published on Jul 2
· Submitted by msadat97 on Jul 4
#3 Paper of the day
Authors:
,

Abstract

Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the training procedure by periodically inserting a null condition. There is also no clear extension of CFG to unconditional models. In this paper, we revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG), which provides the benefits of CFG without the need for any special training procedures. Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model. Additionally, by leveraging the time-step information encoded in all diffusion networks, we propose an extension of CFG, called time-step guidance (TSG), which can be applied to any diffusion model, including unconditional ones. Our guidance techniques are easy to implement and have the same sampling cost as CFG. Through extensive experiments, we demonstrate that ICG matches the performance of standard CFG across various conditional diffusion models. Moreover, we show that TSG improves generation quality in a manner similar to CFG, without relying on any conditional information.

Community

Paper author Paper submitter
edited Jul 4

TL/DR: We show that applying CFG does not require any specific training procedure (e.g. inserting a null condition during training), and CFG can be extended to a more general method that is applicable to any diffusion model, including unconditional ones.

Discussion thread on X: https://twitter.com/Msadat97/status/1808780460912263418

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2407.02687 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2407.02687 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2407.02687 in a Space README.md to link it from this page.

Collections including this paper 11