Keywords: Fast sampling, diffusion probabilistic models, image generation, audio synthesis
TL;DR: We propose FastDPM, a unified framework for fast sampling in diffusion probabilistic models.
Abstract: In this work, we propose FastDPM, a unified framework for fast sampling in diffusion probabilistic models. FastDPM generalizes previous methods and gives rise to new algorithms with improved sample quality. We systematically investigate the fast sampling methods under this framework across different domains, on different datasets, and with different amount of conditional information provided for generation. We find the performance of a particular method depends on data domains (e.g., image or audio), the trade-off between sampling speed and sample quality, and the amount of conditional information. We further provide insights and recipes on the choice of methods for practitioners.
Questions/feedback Request For Reviewers: Related work and experimental results are in the appendix.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/on-fast-sampling-of-diffusion-probabilistic/code)
3 Replies
Loading