Adaptation to distorted faces is commonly interpreted as a shift in the face-space norm for the adapted attribute. This article shows that the size of the aftereffect varies as a function of the distortion level of the adapter. The pattern differed for different facial attributes, increasing with distortion level for symmetric deviations of eye height and decreasing for asymmetric deviations. These results are interpreted in terms of different coding ranges for the 2 facial attributes, arising from differences in eye-height variability in natural face images (large for symmetric, small for asymmetric). Neural models developed in low-level vision also are applied to facial attributes, contrasting a 2-pool (norm-based) and a multichannel (exemplar-based) model. The adapter position effects generally support a norm-based model, as did a finding that perception of stimuli further from the norm than the adapter was shifted in the direction of the norm, rather than repulsed away from the adapter.