Distribution Matching Distillation without Fake Score Network
Paper โข 2605.19256 โข Published
Pretrained weights and evaluation assets for Distribution Matching Distillation without Fake Score Network.
Code and instructions are available in the GitHub repository.
outputs/: Pretrained checkpoints.buffers/vaes/: VAE checkpoints and latent statistics.buffers/refs/: Reference files for FID evaluation.| Checkpoint | Network | Steps | FID50K |
|---|---|---|---|
2026.10.22KST20.04.12-fsfdmd-distill |
FSF-DMD-DiT-B/1 (VA-VAE) | 3K | 3.8942 |
2026.10.24KST16.38.59-fsfdmd-imf-official |
iMF-DiT-B/2 (SD-VAE) | 1K | 3.2964 |
Place the downloaded outputs and buffers directories at the top level of
the code repository, then run the provided training or evaluation scripts.
TARGET=2026.10.22KST20.04.12-fsfdmd-distill bash scripts/eval.sh
@misc{kim2026distributionmatchingdistillationfake,
title={Distribution Matching Distillation without Fake Score Network},
author={Youngjoong Kim and Deokyeong Lee and Jaesik Park},
year={2026},
eprint={2605.19256},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2605.19256},
}