metadata
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-image
Scale-wise Distillation 3.5 Large
Scale-wise Distillation (SwD) is a novel framework for accelerating diffusion models (DMs)
by progressively increasing spatial resolution during the generation process.
SwD achieves significant speedups (2.5× to 10×) compared to full-resolution models
while maintaining or even improving image quality.
Usage
To generate images using SwD, go to GitHub or Hugging Face's demo .
This is a Hugging Face Diffusers implementation of the paper Scale-wise Distillation of Diffusion Models.
The project page can be found at https://yandex-research.github.io/swd
Citation
@article{starodubcev2025swd,
title={Scale-wise Distillation of Diffusion Models},
author={Nikita Starodubcev and Denis Kuznedelev and Artem Babenko and Dmitry Baranchuk},
journal={arXiv preprint arXiv:2503.16397},
year={2025}
}