Metraipolis › archive › dc_2275ec7bfd77

Rethinking the design space of Vanilla Pixel Diffusion Transformers — arXiv:2610.23854

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23854
License (as archived)
CC0-1.0
Archived
2026-10-19T08:43:24.586Z
SHA-256 of the archived text
74f1c7ea1ac637d68c2000fbbf33d3acb396a73c2af490864d877e1b5ca3ba11
Stable URL of this page
https://metraipolis.com/documento/dc_2275ec7bfd77

How to cite

Rethinking the design space of Vanilla Pixel Diffusion Transformers — arXiv:2610.23854 — arXiv (en), https://arxiv.org/abs/2610.23854 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2275ec7bfd77 (Metraipolis archive dc_2275ec7bfd77, sha256 74f1c7ea1ac637d68c2000fbbf33d3acb396a73c2af490864d877e1b5ca3ba11)
BibTeX
@misc{dc2275ec7bfd77,
  title = {Rethinking the design space of Vanilla Pixel Diffusion Transformers — arXiv:2610.23854},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23854},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2275ec7bfd77; sha256 74f1c7ea1ac637d68c2000fbbf33d3acb396a73c2af490864d877e1b5ca3ba11},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23854. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 ($\boldsymbol{x_0}$-prediction). In this work, we revisit this choice and introduce MFlow, an adaptive parameterization that learns to interpolate between $\boldsymbol{x_0}$- and $\boldsymbol{u}$-prediction across principal directions of the data, learned end-to-end with diffusion training. We find that the preferred parameterization varies systematically with the data representation and model capacity -- notably, increasing model capacity shifts preference toward velocity prediction. We evaluate MFlow across ImageNet, UCF-101 video, and large-scale text-to-image generation, demonstrating competitive or improved generative performance across diverse settings. In addition, we find that vanilla pixel diffusion transformers, irrespective of parameterization, retain a persistent high-frequency deficit relative to real images. To address this, we introduce ConvRefiner, a lightweight convolutional module trained post-hoc with an adversarial loss while keeping the diffusion backbone frozen. With only a small amount of additional training, ConvRefiner restores the high-frequency statistics of generated images while preserving FID. Project webpage: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.23854 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T08:39:10.167Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).