Metraipolis › archive › dc_4cab407c8a68

ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model — arXiv:2610.03512

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.03512
License (as archived)
CC0-1.0
Archived
2026-10-06T09:08:44.242Z
SHA-256 of the archived text
d1e03f44e125ce3d020f1d99259ff92f363dbb88aa1759285869ad7a9db51fc5
Stable URL of this page
https://metraipolis.com/documento/dc_4cab407c8a68

How to cite

ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model — arXiv:2610.03512 — arXiv (en), https://arxiv.org/abs/2610.03512 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4cab407c8a68 (Metraipolis archive dc_4cab407c8a68, sha256 d1e03f44e125ce3d020f1d99259ff92f363dbb88aa1759285869ad7a9db51fc5)
BibTeX
@misc{dc4cab407c8a68,
  title = {ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model — arXiv:2610.03512},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.03512},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4cab407c8a68; sha256 d1e03f44e125ce3d020f1d99259ff92f363dbb88aa1759285869ad7a9db51fc5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03512. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humans draw progressively: a few strokes, a look at the result, a stroke erased, a prompt revised. Image generators do not work this way. They typically take a finished sketch and produce the image in a single pass, so every edit starts the picture again, and the models that do keep state across turns are driven by text, cannot take a stroke, and are too slow to draw with. We present ProgressNet, a training-free framework that lets a frozen text-to-image model follow a drawing session as it unfolds: strokes are added and erased, the prompt is revised, and the image keeps up at about a second per turn. It needs no new parameters because the frozen model already has what a progressive generator needs, a pathway through which the previous turn can be remembered, layers that can carry appearance forward without freezing structure, and an internal signal of how far to trust an unfinished sketch; three inference-time mechanisms (Previous-Concept Memory, Layer-Selective K/V Injection and Banded Adaptive Control) use each in turn. As a sketch fills in, every existing method degrades, the FID of the FLUX+ControlNet baseline doubling between 10% and 100% completion on FS-COCO, while ProgressNet's barely moves; it maintains strong fidelity and progressive coherence across three sketch domains and is preferred by users over five competitors, most widely on erasure.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.03512 — 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 2026-10-06T08:21:44.259Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).