Metraipolis › archive › dc_100fce54667b

Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers — arXiv:2611.01696

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01696
License (as archived)
CC0-1.0
Archived
2026-11-03T11:41:37.154Z
SHA-256 of the archived text
f0c7bfa1eb54d0786c232a8be44943775e93f14198062b97a56f224b283190b6
Stable URL of this page
https://metraipolis.com/documento/dc_100fce54667b

How to cite

Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers — arXiv:2611.01696 — arXiv (en), https://arxiv.org/abs/2611.01696 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_100fce54667b (Metraipolis archive dc_100fce54667b, sha256 f0c7bfa1eb54d0786c232a8be44943775e93f14198062b97a56f224b283190b6)
BibTeX
@misc{dc100fce54667b,
  title = {Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers — arXiv:2611.01696},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01696},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_100fce54667b; sha256 f0c7bfa1eb54d0786c232a8be44943775e93f14198062b97a56f224b283190b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01696. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion Transformer (DiT)-based text-to-image models have recently achieved remarkable success in image synthesis. However, when directly applied beyond their training resolution, these models often suffer from severe semantic degradation, where meaningful semantic content disappears. Although existing training-free high-resolution generation methods can mitigate this issue, the inherent semantic degradation at high resolutions remains largely unresolved, leading to degraded fine-grained details. Furthermore, widely used structural guidance methods lack modeling of the structure and details in the intermediate trajectory, which degrades the quality of the generated results. In this paper, we propose a training-free framework for high-resolution image generation to address these challenges. First, we propose a text-visual scale-decoupled attention (TVSDA) module, which restores the model's ability to generate semantically meaningful content at high resolutions by preserving the global receptive field of text tokens while aligning the receptive field of image tokens with the training resolution. Second, we propose a structure-detail guidance (SDG) strategy that explicitly models structural information and fine details through scale-wise and temporal-wise guidance, overcoming the limitations of conventional low-resolution guidance. Extensive experiments demonstrate that our method significantly improves both structural coherence and detail fidelity over existing training-free DiT-based high-resolution generation approaches. The code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.01696 — 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 2026-11-03T11:06:37.504Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).