Dynamic Classifier-Free Diffusion Guidance via Online Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Papalampidi, Pinelopi, Wiles, Olivia, Ktena, Ira, Shtedritski, Aleksandar, Bugliarello, Emanuele, Kajic, Ivana, Albuquerque, Isabela, Nematzadeh, Aida
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915506049515520
author Papalampidi, Pinelopi
Wiles, Olivia
Ktena, Ira
Shtedritski, Aleksandar
Bugliarello, Emanuele
Kajic, Ivana
Albuquerque, Isabela
Nematzadeh, Aida
author_facet Papalampidi, Pinelopi
Wiles, Olivia
Ktena, Ira
Shtedritski, Aleksandar
Bugliarello, Emanuele
Kajic, Ivana
Albuquerque, Isabela
Nematzadeh, Aida
contents Classifier-free guidance (CFG) is a cornerstone of text-to-image diffusion models, yet its effectiveness is limited by the use of static guidance scales. This "one-size-fits-all" approach fails to adapt to the diverse requirements of different prompts; moreover, prior solutions like gradient-based correction or fixed heuristic schedules introduce additional complexities and fail to generalize. In this work, we challeng this static paradigm by introducing a framework for dynamic CFG scheduling. Our method leverages online feedback from a suite of general-purpose and specialized small-scale latent-space evaluations, such as CLIP for alignment, a discriminator for fidelity and a human preference reward model, to assess generation quality at each step of the reverse diffusion process. Based on this feedback, we perform a greedy search to select the optimal CFG scale for each timestep, creating a unique guidance schedule tailored to every prompt and sample. We demonstrate the effectiveness of our approach on both small-scale models and the state-of-the-art Imagen 3, showing significant improvements in text alignment, visual quality, text rendering and numerical reasoning. Notably, when compared against the default Imagen 3 baseline, our method achieves up to 53.8% human preference win-rate for overall preference, a figure that increases up to to 55.5% on prompts targeting specific capabilities like text rendering. Our work establishes that the optimal guidance schedule is inherently dynamic and prompt-dependent, and provides an efficient and generalizable framework to achieve it.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16131
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Classifier-Free Diffusion Guidance via Online Feedback
Papalampidi, Pinelopi
Wiles, Olivia
Ktena, Ira
Shtedritski, Aleksandar
Bugliarello, Emanuele
Kajic, Ivana
Albuquerque, Isabela
Nematzadeh, Aida
Machine Learning
Computer Vision and Pattern Recognition
Classifier-free guidance (CFG) is a cornerstone of text-to-image diffusion models, yet its effectiveness is limited by the use of static guidance scales. This "one-size-fits-all" approach fails to adapt to the diverse requirements of different prompts; moreover, prior solutions like gradient-based correction or fixed heuristic schedules introduce additional complexities and fail to generalize. In this work, we challeng this static paradigm by introducing a framework for dynamic CFG scheduling. Our method leverages online feedback from a suite of general-purpose and specialized small-scale latent-space evaluations, such as CLIP for alignment, a discriminator for fidelity and a human preference reward model, to assess generation quality at each step of the reverse diffusion process. Based on this feedback, we perform a greedy search to select the optimal CFG scale for each timestep, creating a unique guidance schedule tailored to every prompt and sample. We demonstrate the effectiveness of our approach on both small-scale models and the state-of-the-art Imagen 3, showing significant improvements in text alignment, visual quality, text rendering and numerical reasoning. Notably, when compared against the default Imagen 3 baseline, our method achieves up to 53.8% human preference win-rate for overall preference, a figure that increases up to to 55.5% on prompts targeting specific capabilities like text rendering. Our work establishes that the optimal guidance schedule is inherently dynamic and prompt-dependent, and provides an efficient and generalizable framework to achieve it.
title Dynamic Classifier-Free Diffusion Guidance via Online Feedback
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.16131