Classifier-free guidance (CFG) is widely used in diffusion models but often introduces over-contrast and over-saturation artifacts at higher guidance strengths. We present EP-CFG (Energy-Preserving Classifier-Free Guidance), which addresses these issues by preserving the energy distribution of the conditional prediction during the guidance process. Our method simply rescales the energy of the guided output to match that of the conditional prediction at each denoising step, with an optional robust variant for improved artifact suppression. Through experiments, we show that EP-CFG maintains natural image quality and preserves details across guidance strengths while retaining CFG's semantic alignment benefits, all with minimal computational overhead.

翻译：无分类器引导（CFG）在扩散模型中广泛应用，但在较高引导强度下常会引入过度对比和过度饱和的伪影。我们提出了EP-CFG（能量保持的无分类器引导），该方法通过在引导过程中保持条件预测的能量分布来解决这些问题。我们的方法只需在每一步去噪过程中，将引导输出的能量重新缩放以匹配条件预测的能量，并提供一个可选的高鲁棒性变体以增强伪影抑制能力。实验表明，EP-CFG能够在保持CFG语义对齐优势的同时，维持自然的图像质量并在不同引导强度下保留细节，且仅需极小的计算开销。