Cover Image

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Kaiyu, Lai, Hanjiang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving Training-free Conditional Diffusion Model via Fisher Information
by: Song, Kaiyu, et al.
Published: (2024)

Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion
by: Song, Kaiyu, et al.
Published: (2024)

Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
by: Tong, Baoshun, et al.
Published: (2024)

Test-time Alignment-Enhanced Adapter for Vision-Language Models
by: Tong, Baoshun, et al.
Published: (2024)

An Iteration-Free Fixed-Point Estimator for Diffusion Inversion
by: Chen, Yifei, et al.
Published: (2025)

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
by: Shen, Dazhong, et al.
Published: (2024)

Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance
by: Jiang, Zhou, et al.
Published: (2026)

Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
by: Song, Kaiyu, et al.
Published: (2024)

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
by: Sadat, Seyedmorteza, et al.
Published: (2024)

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
by: Sadat, Seyedmorteza, et al.
Published: (2024)

Two Simple Principles for Diffusion-Based Test-Time Adaptation
by: Song, Kaiyu, et al.
Published: (2023)

Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation
by: Song, Kaiyu, et al.
Published: (2025)

Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
by: Chen, Junyang, et al.
Published: (2023)

Towards Understanding the Mechanisms of Classifier-Free Guidance
by: Li, Xiang, et al.
Published: (2025)

Factored Classifier-Free Guidance
by: Xia, Tian, et al.
Published: (2025)

DICE: Distilling Classifier-Free Guidance into Text Embeddings
by: Zhou, Zhenyu, et al.
Published: (2025)

Dynamic Classifier-Free Diffusion Guidance via Online Feedback
by: Papalampidi, Pinelopi, et al.
Published: (2025)

Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations
by: Wang, Kaibo, et al.
Published: (2025)

Analysis of Classifier-Free Guidance Weight Schedulers
by: Wang, Xi, et al.
Published: (2024)

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance
by: Fu, Minghao, et al.
Published: (2025)

CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
by: Fan, Weichen, et al.
Published: (2025)

Improving Classifier-Free Guidance of Flow Matching via Manifold Projection
by: Cai, Jian-Feng, et al.
Published: (2026)

Efficient Distillation of Classifier-Free Guidance using Adapters
by: Jensen, Cristian Perez, et al.
Published: (2025)

Gradient-Free Classifier Guidance for Diffusion Model Sampling
by: Shenoy, Rahul, et al.
Published: (2024)

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
by: Wang, Hanyang, et al.
Published: (2026)

Classifier-free Guidance with Adaptive Scaling
by: Malarz, Dawid, et al.
Published: (2025)

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier
by: Zhou, Yujie, et al.
Published: (2026)

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
by: You, Yuyang, et al.
Published: (2026)

Model Guidance via Explanations Turns Image Classifiers into Segmentation Models
by: Yu, Xiaoyan, et al.
Published: (2024)

Classifier-Free Guidance is a Predictor-Corrector
by: Bradley, Arwen, et al.
Published: (2024)

Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective
by: Zhao, Xiaoming, et al.
Published: (2025)

TCFG: Tangential Damping Classifier-free Guidance
by: Kwon, Mingi, et al.
Published: (2025)

Diffusion Classifier Guidance for Non-robust Classifiers
by: Vaeth, Philipp, et al.
Published: (2025)

Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance
by: Wang, Haoxuan, et al.
Published: (2025)

EP-CFG: Energy-Preserving Classifier-Free Guidance
by: Zhang, Kai, et al.
Published: (2024)

Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
by: Deng, Yang, et al.
Published: (2026)

How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
by: Zhang, Huixuan, et al.
Published: (2025)

SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector
by: Li, Kaiyu, et al.
Published: (2024)

TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment
by: Baek, Kanghyun, et al.
Published: (2025)

Guidance Free Image Editing via Explicit Conditioning
by: Noroozi, Mehdi, et al.
Published: (2025)