Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

arXiv:2404.13686v1 Announce Type: new
Abstract: Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation; and ii) ODE Trajectory Reformulation. However, these approaches suffer from severe performance degradation or domain shifts. To address these limitations, we propose Hyper-SD, a novel framework that synergistically amalgamates the advantages of ODE Trajectory Preservation and Reformulation, while …

abstract algorithms arxiv computational consistency model cs.cv current diffusion diffusion models distillation however image inference preservation process series synthesis trajectory type