Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
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.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
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
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 GenerationGuidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
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 GenerationManifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance
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
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…