Cover Image

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sadat, Seyedmorteza, Hilliges, Otmar, Weber, Romann M.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
by: Sadat, Seyedmorteza, et al.
Published: (2024)

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
by: Sadat, Seyedmorteza, et al.
Published: (2023)

HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
by: Sadat, Seyedmorteza, et al.
Published: (2025)

HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
by: Vontobel, Tobias, et al.
Published: (2025)

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

Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales
by: Sadat, Seyedmorteza, et al.
Published: (2025)

SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion
by: Ho, Hsuan-I, et al.
Published: (2023)

ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
by: Zhang, Hui, et al.
Published: (2023)

Regressor-Guided Generative Image Editing Balances User Emotions to Reduce Time Spent Online
by: Gebhardt, Christoph, et al.
Published: (2025)

Reviving ConvNeXt for Efficient Convolutional Diffusion Models
by: Kwon, Taesung, et al.
Published: (2026)

Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
by: Kim, Myeongsoo, et al.
Published: (2026)

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
by: Song, Kaiyu, et al.
Published: (2025)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance
by: Triaridis, Kostas, et al.
Published: (2025)

Explicit Critic Guidance for Aligning Diffusion Models
by: Liang, Zhengyang, et al.
Published: (2026)

Steering Guidance for Personalized Text-to-Image Diffusion Models
by: Park, Sunghyun, et al.
Published: (2025)

GraspXL: Generating Grasping Motions for Diverse Objects at Scale
by: Zhang, Hui, et al.
Published: (2024)

Unified Control for Inference-Time Guidance of Denoising Diffusion Models
by: Goyal, Maurya, et al.
Published: (2025)

AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos
by: Lu, Feichi, et al.
Published: (2024)

Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
by: Menn, Dennis, et al.
Published: (2024)

Insights into Closed-form IPM-GAN Discriminator Guidance for Diffusion Modeling
by: Srikanth, Aadithya, et al.
Published: (2023)

Navigating with Annealing Guidance Scale in Diffusion Space
by: Yehezkel, Shai, et al.
Published: (2025)

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

Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
by: Bellchambers, Gregory
Published: (2025)

Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance
by: Mohseni-Sehdeh, Saeed, et al.
Published: (2025)

Variational Control for Guidance in Diffusion Models
by: Pandey, Kushagra, et al.
Published: (2025)

Momentum Guidance: Plug-and-Play Guidance for Flow Models
by: Liao, Runlong, et al.
Published: (2026)

Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance
by: Moufad, Badr, et al.
Published: (2025)

RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance
by: Mukherjee, Avideep, et al.
Published: (2024)

Diffusion Models without Classifier-free Guidance
by: Tang, Zhicong, et al.
Published: (2025)

Learning Diffusion Models with Flexible Representation Guidance
by: Wang, Chenyu, et al.
Published: (2025)

Understanding and Improving Training-free Loss-based Diffusion Guidance
by: Shen, Yifei, et al.
Published: (2024)

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

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

Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
by: Mei, Kangfu, et al.
Published: (2024)

REG: Rectified Gradient Guidance for Conditional Diffusion Models
by: Gao, Zhengqi, et al.
Published: (2025)

Don't Play Favorites: Minority Guidance for Diffusion Models
by: Um, Soobin, et al.
Published: (2023)

Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
by: Kansy, Manuel, et al.
Published: (2024)

Video Reconstruction using Diffusion-based Image-to-Video Generation with Trajectory Guidance
by: Bompai, Stelio, et al.
Published: (2026)

Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
by: Zheng, Candi, et al.
Published: (2023)