Rethinking Score Distillation as a Bridge Between Image Distributions David McAllister 1 Songwei Ge2 Jia-Bin Huang 2 David W. Jacobs 2

Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in general-purpose applications. In this paper, we make progress toward understanding the behavior of SDS and its variants by viewing them as solving an optimal-cost transport path from a source distribution to a target distribution.