PixelFlow: Pixel-Space Generative Models with Flow

Shoufa Chen, Chongjian Ge, Shilong Zhang, Peize Sun, Ping Luo
4/10/2025
cs.CV

Official code: ShoufaChen/PixelFlow (319 stars, MIT, last commit 2025-05-11). 1 more implementation below.

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$\times$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.

View on arXivView PDF

Code Implementations(2)

ShoufaChen/PixelFlowOfficial100%
MIT

Pixel-Space Generative Models

31918PythonApr 11, 20251 years agoMIT
nothingbutbut/PixelFlowCommunity72%
MIT

Pixel-Space Generative Models

00PythonDec 13, 20251 years agoMIT

Similar Papers

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

85% match1 repo2.0k2024

NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow Transformers

85% match2025

IDEA-Bench: How Far are Generative Models from Professional Designing?

85% match1 repo412026

BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities

84% match1 repo1432026

BLIP3o-NEXT: Next Frontier of Native Image Generation

84% match2025

EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models

84% match1 repo522026

Cite this paper

@article{chen2025pixelflow,
  title  = {PixelFlow: Pixel-Space Generative Models with Flow},
  author = {Shoufa Chen and Chongjian Ge and Shilong Zhang and Peize Sun and Ping Luo},
  year   = {2025},
  eprint = {2504.07963},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.07963v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.07963.svg)](https://codeofpaper.com/paper/2504.07963)

Discussion