Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

arXiv:2404.02241v1 Announce Type: new
Abstract: Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate weight checkpoints are not fully utilized and only the last converged checkpoint is used. In this work, we find that high-quality model weights often lie in a basin which cannot be reached by SGD but can be obtained by proper checkpoint averaging. Based on these observations, we propose …

arxiv combination cs.cv diffusion diffusion models linear type