研究：文生图模型超过十个物体后基本不数数了
Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models
用 SD3.5 或 FLUX 画一堆物体总画不对数量？这篇把原因拆到了噪声层面，还给出了能画对数字的输入方法。
一项 arXiv 研究测试了五个开源文生图模型对数量词的响应，人工标注者统计了 3,088 张生成图。SD3.5-Medium 和 FLUX.1-dev 在超过十个物体后就不再跟随提示词中的数字，FLUX.2 [klein] 和 Qwen-Image 则能松散跟随到二十五个。在相同初始噪声下，从十二个改到二十五个，画面布局不变但数量变化与换随机种子相当。数字以噪声网格形式写入初始 latent 时，人工在 59% 的图中能数出目标数量，仅用文字提示时只有 4%。研究还指出超过十个物体后，exact-match 指标几乎无法区分松散跟随数字和完全忽略数字的模型。
Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models
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.
