metadata
datasets:
- ILSVRC/imagenet-1k
license: apache-2.0
pipeline_tag: unconditional-image-generation
tags:
- flow-matching
- pixel-diffusion
- pixel-generation
Asymmetric Flow Models
Pixel-space flow models trained on ImageNet using the AsymFlow method proposed in the paper:
Asymmetric Flow Models
arXiv 2026
Hansheng Chen,
Jan Ackermann,
Minseo Kim,
Gordon Wetzstein,
Leonidas Guibas
Stanford University
Project Page | arXiv | Code | AsymFLUX.2 klein Demo🤗
Abstract
Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise. Asymmetric Flow Modeling (AsymFlow) is a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. On ImageNet 256$\times$256, AsymFlow achieves a leading 1.57 FID, outperforming prior DiT/JiT-like pixel diffusion models by a large margin.
Citation
@article{chen2026asymmetric,
title={Asymmetric Flow Models},
author={Hansheng Chen and Jan Ackermann and Minseo Kim and Gordon Wetzstein and Leonidas Guibas},
journal={arXiv preprint arXiv:2605.12964},
url={https://arxiv.org/abs/2605.12964},
year={2026},
}