Downloads · 30 days
0
YoungJoong/improvedSelfDistillation
improvedSelfDistillation is a machine learning model from YoungJoong. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Pretrained weights and evaluation assets for Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation.
Downloads · 30 days
0
Access
Public
Updated Jun 3, 2026
Repo size
44.2 GB
Likes
0
Public
Click a slice to open those files.
.pt21.8 GB · 99%
From the Hugging Face model README
Pretrained weights and evaluation assets for Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation.
Code and instructions are available in the GitHub repository.
outputs/: pretrained checkpointsbuffers/vaes/: VAE checkpoints and latent statisticsbuffers/refs/: reference files for FID evaluation| Checkpoint | Network | Steps | FID50K |
|---|---|---|---|
2026.02.15KST14.22.08-base4 | FlowMapTiT-B/4 (SD-VAE, TrigFlow) | 400K | 14.58 |
2026.01.18KST19.26.11-xlarge1 | ADiT-XL/1 (VA-VAE, Linear) | 600K | 2.30 |
Place the downloaded outputs and buffers directories at the top level of
the code repository, then run the provided training or evaluation scripts.
bash eval.sh
@misc{kim2026stabilizingconsistencytrainingflow,
title={Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation},
author={Youngjoong Kim and Duhoe Kim and Woosung Kim and Jaesik Park},
year={2026},
eprint={2601.22679},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2601.22679},
}