Prompt-aware classifier free guidance for diffusion models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xuanhao, Li, Chang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914074924679168
author Zhang, Xuanhao
Li, Chang
author_facet Zhang, Xuanhao
Li, Chang
contents Diffusion models have achieved remarkable progress in image and audio generation, largely due to Classifier-Free Guidance. However, the choice of guidance scale remains underexplored: a fixed scale often fails to generalize across prompts of varying complexity, leading to oversaturation or weak alignment. We address this gap by introducing a prompt-aware framework that predicts scale-dependent quality and selects the optimal guidance at inference. Specifically, we construct a large synthetic dataset by generating samples under multiple scales and scoring them with reliable evaluation metrics. A lightweight predictor, conditioned on semantic embeddings and linguistic complexity, estimates multi-metric quality curves and determines the best scale via a utility function with regularization. Experiments on MSCOCO~2014 and AudioCaps show consistent improvements over vanilla CFG, enhancing fidelity, alignment, and perceptual preference. This work demonstrates that prompt-aware scale selection provides an effective, training-free enhancement for pretrained diffusion backbones.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22728
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt-aware classifier free guidance for diffusion models
Zhang, Xuanhao
Li, Chang
Sound
Artificial Intelligence
Multimedia
Audio and Speech Processing
Diffusion models have achieved remarkable progress in image and audio generation, largely due to Classifier-Free Guidance. However, the choice of guidance scale remains underexplored: a fixed scale often fails to generalize across prompts of varying complexity, leading to oversaturation or weak alignment. We address this gap by introducing a prompt-aware framework that predicts scale-dependent quality and selects the optimal guidance at inference. Specifically, we construct a large synthetic dataset by generating samples under multiple scales and scoring them with reliable evaluation metrics. A lightweight predictor, conditioned on semantic embeddings and linguistic complexity, estimates multi-metric quality curves and determines the best scale via a utility function with regularization. Experiments on MSCOCO~2014 and AudioCaps show consistent improvements over vanilla CFG, enhancing fidelity, alignment, and perceptual preference. This work demonstrates that prompt-aware scale selection provides an effective, training-free enhancement for pretrained diffusion backbones.
title Prompt-aware classifier free guidance for diffusion models
topic Sound
Artificial Intelligence
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2509.22728