Rethinking the design space of Vanilla Pixel Diffusion Transformers
Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoencoder. JiT shows that a vanilla diffusion transformer can generate directly in pixel space by replacing the commonly used velocity prediction ($\boldsymbol{u}$-prediction) with clean image prediction…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
