與任何人：邁向可控且身份一致之圖像生成

WithAnyone: Towards Controllable and ID Consistent Image Generation

October 16, 2025

作者: Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang Yu, Xingjun Ma, Yu-Gang Jiang

cs.AI

摘要

身份一致性生成已成為文本到圖像研究的重要焦點，近期模型在生成與參考身份對齊的圖像方面取得了顯著成功。然而，由於缺乏包含同一人多次圖像的大規模配對數據集，大多數方法被迫採用基於重建的訓練方式。這種依賴性往往導致我們稱之為“複製-貼上”的失敗模式，即模型直接複製參考面部，而非在姿勢、表情或光照的自然變化中保持身份一致性。這種過度相似性削弱了可控性，並限制了生成的表現力。為解決這些限制，我們（1）構建了一個專為多人物場景設計的大規模配對數據集MultiID-2M，為每個身份提供多樣化的參考；（2）引入了一個基準，量化“複製-貼上”偽影以及身份保真度與變異之間的權衡；（3）提出了一種新穎的訓練範式，利用對比身份損失來平衡保真度與多樣性。這些貢獻最終形成了WithAnyone，這是一個基於擴散的模型，有效減少了“複製-貼上”現象，同時保持了高度的身份相似性。廣泛的定性和定量實驗表明，WithAnyone顯著減少了“複製-貼上”偽影，提高了對姿勢和表情的可控性，並保持了強烈的感知質量。用戶研究進一步驗證了我們的方法在實現高身份保真度的同時，能夠進行富有表現力的可控生成。

English

Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets containing multiple images of the same individual forces most approaches to adopt reconstruction-based training. This reliance often leads to a failure mode we term copy-paste, where the model directly replicates the reference face rather than preserving identity across natural variations in pose, expression, or lighting. Such over-similarity undermines controllability and limits the expressive power of generation. To address these limitations, we (1) construct a large-scale paired dataset MultiID-2M, tailored for multi-person scenarios, providing diverse references for each identity; (2) introduce a benchmark that quantifies both copy-paste artifacts and the trade-off between identity fidelity and variation; and (3) propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity. These contributions culminate in WithAnyone, a diffusion-based model that effectively mitigates copy-paste while preserving high identity similarity. Extensive qualitative and quantitative experiments demonstrate that WithAnyone significantly reduces copy-paste artifacts, improves controllability over pose and expression, and maintains strong perceptual quality. User studies further validate that our method achieves high identity fidelity while enabling expressive controllable generation.