PixelGen: Improving Pixel Diffusion with Perceptual Supervision

TL;DR

PixelGen introduces perceptual supervision into pixel diffusion models, significantly improving image quality and training efficiency on ImageNet and text-to-image tasks.

Contribution

It proposes a novel end-to-end pixel diffusion framework with perceptual losses and noise-gating, enhancing sample quality without complex two-stage pipelines.

Findings

Achieves an FID of 5.11 on ImageNet-256 in 80 epochs.

Reaches a GenEval score of 0.79 in text-to-image generation.

Outperforms latent diffusion baselines on key metrics.

Abstract

Pixel diffusion generates images directly in pixel space, avoiding the VAE artifacts and representational bottlenecks of two-stage latent diffusion. Recent JiT further simplifies pixel diffusion with x-prediction, where the model predicts clean images rather than velocity. However, the standard pixel-wise diffusion loss treats all pixels equally, spending model capacity to perceptually insignificant signals and often leading to blurry samples. We propose PixelGen, an end-to-end pixel diffusion framework that augments x-prediction with perceptual supervision. Specifically, PixelGen introduces two complementary perceptual losses on top of x-prediction: an LPIPS loss for local textures and a P-DINO loss for global semantics. To preserve sample coverage, PixelGen further proposes a noise-gating strategy that applies these losses only at lower-noise timesteps. On ImageNet-256 without classifier-free guidance, PixelGen achieves an FID of 5.11 in 80 training epochs, surpassing the latent diffusion baselines. Moreover, PixelGen scales efficiently to text-to-image generation, reaching a GenEval score of 0.79 with only 6 days of training on 8xH800 GPUs. These results show that perceptual supervision substantially narrows the gap between pixel and latent diffusion while preserving a simple one-stage pipeline. Codes are available at https://github.com/Zehong-Ma/PixelGen.