EP-CFG: Energy-Preserving Classifier-Free Guidance
This addresses image quality degradation in diffusion models for AI image generation, but is an incremental improvement to existing CFG methods.
The paper tackles the problem of over-contrast and over-saturation artifacts in classifier-free guidance (CFG) for diffusion models at higher guidance strengths, and shows that EP-CFG preserves natural image quality and details across guidance strengths while retaining semantic alignment benefits with minimal computational overhead.
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.