Metraipolis › archive › dc_4d2bac70da7a
Local Content-Style Control for Diffusion-based Image Stylization — arXiv:2610.08704
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08704
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:08:00.765Z
- SHA-256 of the archived text
ff091b341d36220ce2fb073f9298e2815ff99e3f0f3d4d92cdaa3de0f5ef05fa- Stable URL of this page
https://metraipolis.com/documento/dc_4d2bac70da7a
How to cite
Local Content-Style Control for Diffusion-based Image Stylization — arXiv:2610.08704 — arXiv (en), https://arxiv.org/abs/2610.08704 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d2bac70da7a (Metraipolis archive dc_4d2bac70da7a, sha256 ff091b341d36220ce2fb073f9298e2815ff99e3f0f3d4d92cdaa3de0f5ef05fa)
BibTeX
@misc{dc4d2bac70da7a,
title = {Local Content-Style Control for Diffusion-based Image Stylization — arXiv:2610.08704},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08704},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d2bac70da7a; sha256 ff091b341d36220ce2fb073f9298e2815ff99e3f0f3d4d92cdaa3de0f5ef05fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08704. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Image stylization with latent-diffusion models entangles two independently refined axes: what a region depicts and how it is depicted. Such pipelines expose only global controls, yet professional retouching demands deliberate, region-specific control. We lift two conditioning weights already present in a ControlNet + IP-Adapter stylization pipeline from global scalars to per-location spatial maps, yielding local, per-axis control of content and style in a single generative pass. Because the two weights act on disjoint pathways, adjusting them independently spans a 2x2 retouching vocabulary, from free regeneration to identity preservation. We validate that edits stay confined to the retouched region and that each weight predominantly steers its own axis. Our approach requires no retraining and drops unchanged into any such pipeline. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.08704 — 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 2026-10-07T12:37:33.050Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).