Stable Velocity: A Variance Perspective on Flow Matching
Paper
•
2602.05435
•
Published
•
3
This repository contains SiT-XL/2 checkpoints trained with Stable Velocity Matching (StableVM) and Variance-Aware Representation Alignment (VA-REPA) on ImageNet 256×256, as described in the paper.
Class-conditional generation on ImageNet 256×256 with classifier-free guidance (CFG).
| Checkpoint | Steps | FID ↓ |
|---|---|---|
2000000.pt |
2.0 M | 1.34 |
2400000.pt |
2.4 M | 1.33 |
3000000.pt |
3.0 M | 1.30 |
from huggingface_hub import hf_hub_download
# Download a specific checkpoint
ckpt_path = hf_hub_download(
repo_id="linYD0718/stable-velocity",
filename="checkpoints/3000000.pt",
)
Or via CLI:
huggingface-cli download linYD0718/stable-velocity checkpoints/3000000.pt --local-dir ./
@misc{yang2026stablevelocityvarianceperspective,
title={Stable Velocity: A Variance Perspective on Flow Matching},
author={Donglin Yang and Yongxing Zhang and Xin Yu and Liang Hou and Xin Tao and Pengfei Wan and Xiaojuan Qi and Renjie Liao},
year={2026},
eprint={2602.05435},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2602.05435},
}
This project is licensed under the MIT License.