Disentangling Density from Semantics in Classifier-Free Guidance

Classifier-Free Guidance (CFG) is essential for conditional diffusion and flow-matching models. However, operating at high guidance scales, where prompt alignment is strongest, causes two distinct failure modes: $(i)$visual oversaturation (color burnout) and $(ii)$an unintended coupling between prompt alignment and sample density, which forces trajectories into high-density mode centers and suppresses fine structural details. Because the clean image estimate and noise prediction directions are not aligned during generation, previous methods that correct only one of these two directions leave the other distortion uncorrected. To resolve both issues simultaneously, we introduce _Density-Decoupled CFG_ (${\text{D}}^2$-CFG), a training-free framework that projects guidance updates orthogonally to both directions. By decoupling semantic steering from typicality control, ${\text{D}}^2$-CFG mitigates density drift into mode centers. This preserves the high-dimensional typical-set structure of the latent space, generating highly detailed images without the color oversaturation induced by standard high guidance. This allows increasing guidance without visual burnout and gives independent, calibrated control over sample density via a quantile parameter $q$. Across SDXL and SD3.5, ${\text{D}}^2$-CFG consistently achieves superior text alignment, natural contrast, and improved distribution fidelity when using high guidance.