Score: 0

S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

Published: August 18, 2025 | arXiv ID: 2508.12880v1

By: Chubin Chen , Jiashu Zhu , Xiaokun Feng and more

Potential Business Impact:

Makes AI images and videos look better.

Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Gaussian mixture modeling with a closed-form solution, we observe a discrepancy between the suboptimal results produced by CFG and the ground truth. The model's excessive reliance on these suboptimal predictions often leads to semantic incoherence and low-quality outputs. To address this issue, we first empirically demonstrate that the model's suboptimal predictions can be effectively refined using sub-networks of the model itself. Building on this insight, we propose S^2-Guidance, a novel method that leverages stochastic block-dropping during the forward process to construct stochastic sub-networks, effectively guiding the model away from potential low-quality predictions and toward high-quality outputs. Extensive qualitative and quantitative experiments on text-to-image and text-to-video generation tasks demonstrate that S^2-Guidance delivers superior performance, consistently surpassing CFG and other advanced guidance strategies. Our code will be released.

Page Count
24 pages

Category
Computer Science:
CV and Pattern Recognition