---
title: "Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06840v1"
permalink: "https://feed.astralor.com/items/itm_570dc6051d48ddd91a1cf011"
published: "2026-11-04T17:57:53.000Z"
score: 60
channel: "ai"
tags: ["Same Layout","Different Count","What Number Words","Past Ten","Text-to-Image Models Ask","SD3","Medium"]
---

# Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models

## 速览

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 consiste…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_570dc6051d48ddd91a1cf011