---
title: pi-Flow-ImageNet
canonical_url: "https://www.modelscope.cn/models/Lakonik/pi-Flow-ImageNet"
md_url: "https://www.modelscope.cn/models/Lakonik/pi-Flow-ImageNet.md"
repository: Lakonik/pi-Flow-ImageNet
last_updated: 2026-05-14
license: apache-2.0
parameters: 4.3B
tensor_type:
  - F16
  - BF16
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 96
stars: 0
---

# pi-Flow-ImageNet

> pi-Flow-ImageNet - Lakonik 在 ModelScope 开源的模型。pi-Flow: Policy-Based Flow Models

Lakonik/pi-Flow-ImageNet 是 ModelScope 魔搭社区上的 4.3B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: Lakonik/pi-Flow-ImageNet
- **License**: apache-2.0
- **Parameters**: 4.3B
- **Downloads**: 96
- **Stars**: 0
- **Last updated**: 2026-05-14

Source: https://www.modelscope.cn/models/Lakonik/pi-Flow-ImageNet

---

# pi-Flow: Policy-Based Flow Models

Distilled 1-step and 2-step ImageNet DiTs proposed in the paper:

**pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation**
<br>
[Hansheng Chen](https://lakonik.github.io/)<sup>1</sup>, 
[Kai Zhang](https://kai-46.github.io/website/)<sup>2</sup>,
[Hao Tan](https://research.adobe.com/person/hao-tan/)<sup>2</sup>,
[Leonidas Guibas](https://geometry.stanford.edu/?member=guibas)<sup>1</sup>,
[Gordon Wetzstein](http://web.stanford.edu/~gordonwz/)<sup>1</sup>, 
[Sai Bi](https://sai-bi.github.io/)<sup>2</sup><br>
<sup>1</sup>Stanford University, <sup>2</sup>Adobe Research
<br>
[[arXiv](https://arxiv.org/abs/2510.14974)] [[Code](https://github.com/Lakonik/piFlow)] [[pi-Qwen Demo🤗](https://huggingface.co/spaces/Lakonik/pi-Qwen)] [[pi-FLUX Demo🤗](https://huggingface.co/spaces/Lakonik/pi-FLUX.1)] 

![teaser](https://cdn-uploads.huggingface.co/production/uploads/638067fcb334960c987fbeda/H0J1LYUcSS5YqOwZqQ0Jb.jpeg)

## Citation
```
@misc{piflow,
      title={pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation}, 
      author={Hansheng Chen and Kai Zhang and Hao Tan and Leonidas Guibas and Gordon Wetzstein and Sai Bi},
      year={2025},
      eprint={2510.14974},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2510.14974}, 
}
```