The Determinism of Randomness: Latent Space Degeneracy in Diffusion Model

ArXi:2511.07756v4 Announce Type: replace Diffusion models initialize generation from an isotropic Gaussian latent, yet changing only the random seed can substantially alter prompt faithfulness, composition, and visual quality. We explain this gap by distinguishing the Euclidean geometry of the prior from the semantic geometry induced by the sampler: the effective map from initial noise to semantic outcome has many semantic-invariant directions and a much smaller set of semantic-sensitive directions.