paper-with-me

Papers

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency

2025-06-26 · Kaiyu Song, Hanjiang Lai

Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of the conditional term. However, the high guidance scale often results in oversaturation and unrealistic artifacts. In this paper, we introduce a new perspective based on low-frequency signals, identifying the accumulation of redundant information in these signals as the key factor behind oversaturation and unrealistic artifacts. Building on this insight, we propose low-frequency improved classifier-free guidance (LF-CFG) to mitigate these issues. Specifically, we introduce an adaptive threshold-based measurement to pinpoint the locations of redundant information. We determine a reasonable threshold by analyzing the change rate of low-frequency information between prior and current steps. We then apply a down-weight strategy to reduce the impact of redundant information in the low-frequency signals. Experimental results demonstrate that LF-CFG effectively alleviates oversaturation and unrealistic artifacts across various diffusion models, including Stable Diffusion-XL, Stable Diffusion 2.1, 3.0, 3.5, and SiT-XL.

📄 PDF Abstract BibTeX arXiv:2506.21452

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

2024-10-03 · Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber

Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidance scale is generally required to enhance…

Prompt-aware classifier free guidance for diffusion models

2025-09-25 · Xuanhao Zhang, Chang Li arxiv

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 general…

Audio Generation

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

2026-02-26 · Dian Xie, Shitong Shao, Lichen Bai, Zikai Zhou 외 arxiv

Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance methods have emerged with improved generation quality and human prefere…

Text-to-Image Generation

Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance

2026-03-12 · Zexi Jia, Pengcheng Luo, Zhengyao Fang, Jinchao Zhang 외 arxiv

Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this…

Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

2026-07-08 · Shiheng Zhang arxiv

Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with m…