English

PixelFlow: Pixel-Space Generative Models with Flow

Computer Vision and Pattern Recognition 2025-04-11 v1

Abstract

We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256×\times256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models. Code and models are available at https://github.com/ShoufaChen/PixelFlow.

Keywords

Cite

@article{arxiv.2504.07963,
  title  = {PixelFlow: Pixel-Space Generative Models with Flow},
  author = {Shoufa Chen and Chongjian Ge and Shilong Zhang and Peize Sun and Ping Luo},
  journal= {arXiv preprint arXiv:2504.07963},
  year   = {2025}
}

Comments

Technical report. Code: https://github.com/ShoufaChen/PixelFlow

R2 v1 2026-06-28T22:54:00.080Z