让十个人同框不串脸：AI 图像生成的新解法
现在的 AI 画一个人像已经很像了，但让它把十个指定的人放进同一张照片，几乎必然有人被画错、被复制粘贴。这篇论文的解法是把「谁站在哪」先画成一张布局图，再让模型照着布局图去填每个人的脸，而不是靠模糊的「这个人像谁」的向量去猜。结果：十人合影里，97.3% 的指定身份都被正确画出来，重复率只有 2.8%，而且「复制粘贴」的穿帮痕迹从 0.169 降到 0.055。它不是你明天就能用的工具，但它是「AI 合影」从单人到群像跨过的一道坎——以后你想要的「全家福」「团队照」可能真的能凭空生成。
📄 原文摘要(英文)
Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people. Beyond retaining each identity, the model must bind every reference to a distinct person and location, while training-time identity losses must establish correspondence among several noisy predicted faces. We introduce WithEveryone, a unified framework for generating group images up to ten reference identities. WithEveryone injects each selected identity as an addressed token, predicts a structured identity--layout plan, and renders the plan as a visual condition. Its key objective, Layout-Grounded ID Loss, uses annotated face regions to supervise the intended identities directly, avoiding unstable embedding-based face matching; ID Representation Forcing additionally trains a prediction for each identity before image synthesis. On an identity-disjoint benchmark, WithEveryone achieves the highest target-context identity similarity, improving face similarity from 0.462 for GPT-Image-2 to 0.499, while reducing copy-paste artifacts from 0.169 to 0.055. It further covers 97.3\% of the requested identities with a duplicate rate of only 2.8\%. These results show that explicit identity--layout grounding enables identity-preserving generation to scale to larger groups without relying on direct reference-face copying.