Metraipolis › archive › dc_2f60c80eddc0
PASTA: Prompt-Aware Annealed Diffusion Sampling — arXiv:2610.32390
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32390
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:51:55.550Z
- SHA-256 of the archived text
fdebf8294e90d5636b4d24d63bd5ab06b68b879c285ebc1c156422abf8efe621- Stable URL of this page
https://metraipolis.com/documento/dc_2f60c80eddc0
How to cite
PASTA: Prompt-Aware Annealed Diffusion Sampling — arXiv:2610.32390 — arXiv (en), https://arxiv.org/abs/2610.32390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f60c80eddc0 (Metraipolis archive dc_2f60c80eddc0, sha256 fdebf8294e90d5636b4d24d63bd5ab06b68b879c285ebc1c156422abf8efe621)
BibTeX
@misc{dc2f60c80eddc0,
title = {PASTA: Prompt-Aware Annealed Diffusion Sampling — arXiv:2610.32390},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32390},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f60c80eddc0; sha256 fdebf8294e90d5636b4d24d63bd5ab06b68b879c285ebc1c156422abf8efe621},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Diffusion models produce high-quality images, real-world visual design requires intentionally preserving clean regions for headlines, logos, or UI elements. Existing layout-aware text-to-image methods struggle to strictly preserve reserved regions, often introducing unwanted content that complicates downstream editing. Existing approaches either manipulate attention to displace content or suppress conditioning via noise-level interventions. However, these methods sacrifice visual coherence, producing flat regions or noticeable style inconsistencies between reserved and non-reserved areas. To address this limitation, we propose a Prompt-Aware Shared-Latent Training-Free Annealed Diffusion Sampling (PASTA), a training-free framework that enforces reserved-region constraints by selectively applying semantic guidance to object-allowed regions during sampling. PASTA operates on a shared latent trajectory, where full-prompt and context-prompt guidance are fused through mask-guided sampling. An annealed schedule suppresses semantic leakage during early denoising stages while gradually restoring visual consistency in later stages. Extensive experiments demonstrate that PASTA improves reserved-region fidelity while preserving overall image realism and perceptual consistency. 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); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.32390 — 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 2026-10-26T19:45:33.411Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).