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 256×256 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.
@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}
}