Metraipolis › archive › dc_43bf5a26185e
Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models — arXiv:2611.06840
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06840
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:22:46.245Z
- SHA-256 of the archived text
4f2a1a4a05a909646d12ce25d39ca625beb7dde0bdfc95d3e8b2805046268202- Stable URL of this page
https://metraipolis.com/documento/dc_43bf5a26185e
How to cite
Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models — arXiv:2611.06840 — arXiv (en), https://arxiv.org/abs/2611.06840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43bf5a26185e (Metraipolis archive dc_43bf5a26185e, sha256 4f2a1a4a05a909646d12ce25d39ca625beb7dde0bdfc95d3e8b2805046268202)
BibTeX
@misc{dc43bf5a26185e,
title = {Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models — arXiv:2611.06840},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06840},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43bf5a26185e; sha256 4f2a1a4a05a909646d12ce25d39ca625beb7dde0bdfc95d3e8b2805046268202},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Ask SD3.5-Medium for twelve of an object and then, from the same starting noise, for twenty-five. The picture keeps its layout, but the count changes about as much as it would under a new random seed, and in no consistent direction. We study what number words do once a request passes about ten objects, in five open text-to-image models. Holding the object and the starting noise fixed, we change one thing at a time, and people who never see the request count 3,088 of the images. Every model follows the number for small crowds, but only up to a point, its reach: SD3.5-M and FLUX.1-dev stop following it soon after ten, while FLUX.2 [klein] and Qwen-Image follow it loosely up to twenty-five. Beyond SD3.5-M's reach, the coarse part of the starting noise fixes the composition of the picture but not how many objects it holds: redrawing only the noise finer than an eighth of the image keeps the layout as well as a new number does, and already moves the count two-thirds as far. The number word still reaches the denoiser and acts in its first steps, but nothing we tried gives it a clear direction. Shown instead as a noised grid in the starting latent, the count is drawn: people find it in 59% of images, against 4% when it is only told. Past ten, an exact-match score barely separates a model that follows the number loosely from one that ignores it, and a relative-error score can even prefer a constant guess of sixteen. A same-noise test with a few requests per object tells them apart. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.06840 — 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 2026-11-05T18:15:49.044Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).