Exploring the Design Factors of Pixel-Space Diffusion

In this paper, we introduce EiT by exploring the key design factors of pixel-space diffusion from three perspectives: model architecture, representation, and frequency domain. Inspired by Denoising Autoencoders (DAE) which performs denoising through a bottleneck, we construct a U-shaped pixel diffusion transformer that performs explicit compression along the channel dimension. In terms of representation, we find that both pixel and latent diffusion transformers exhibit a three-stage representation dynamics across layers and timesteps: denoising/local feature expansion, basis lift-up, and posterior projection. Moreover, earlier denoising and a longer basis lift-up stage are associated with better generation, which EiT naturally achieves through its channel bottleneck and increased depth. From the frequency perspective, we establish the equivalence between pixel-space and frequency-space diffusion, and show that the latter enables flexible frequency-band loss reweighting, yielding performance gains at no extra cost. On ImageNet 256$\times$256 and 512$\times$512, EiT achieves significantly better generation quality than JiT (Just image Transformers). Our code will be made publicly available.