Stable Velocity: A Variance Perspective on Flow Matching

arXiv Project Page GitHub

Model Description

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.

Checkpoints

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

Download Checkpoints

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 ./

Citation

@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}, 
}

License

This project is licensed under the MIT License.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train linYD0718/stable-velocity

Paper for linYD0718/stable-velocity