AnyPhoto: 多人身份保持图像生成与基于ID自适应调制的定位画布
AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas
AI总结：
AnyPhoto通过定位画布和身份自适应调制实现多人身份保持生成，提升可控性和多样性。
摘要：
多人物身份保持生成需要将多个参考面孔绑定到指定位置下文本提示。强身份/布局条件常导致复制粘贴快捷方式并削弱提示驱动的可控性。我们提出了AnyPhoto，一种扩散-变压器微调框架，包含（i）对齐RoPE的定位画布和定位对齐的token修剪用于空间定位，（ii）AdaLN风格的身份自适应调制从面部识别嵌入中获取持久身份注入，以及（iii）身份隔离注意力以防止跨身份干扰。训练结合条件流匹配与嵌入空间面部相似性损失，再加上参考面部替换和定位画布退化，以抑制快捷方式。在MultiID-Bench上，AnyPhoto在提高身份相似性的同时减少复制粘贴倾向，随着身份数量的增加，增益增加。AnyPhoto还支持通过提示驱动的风格化，显示巨大的应用价值。
英文摘要：
Multi-person identity-preserving generation requires binding multiple reference faces to specified locations under a text prompt. Strong identity/layout conditions often trigger copy-paste shortcuts and weaken prompt-driven controllability. We present AnyPhoto, a diffusion-transformer finetuning framework with (i) a RoPE-aligned location canvas plus location-aligned token pruning for spatial grounding, (ii) AdaLN-style identity-adaptive modulation from face-recognition embeddings for persistent identity injection, and (iii) identity-isolated attention to prevent cross-identity interference. Training combines conditional flow matching with an embedding-space face similarity loss, together with reference-face replacement and location-canvas degradations to discourage shortcuts. On MultiID-Bench, AnyPhoto improves identity similarity while reducing copy-paste tendency, with gains increasing as the number of identities grows. AnyPhoto also supports prompt-driven stylization with accurate placement, showing great potential application value.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
