arXiv:2608.20336 · v3

WithEveryone: Unified Planning and Identity Grounding for Group Image Generation

首次提交 2026-08-21 01:59

版本更新 2026-11-11 17:11

雷达观测 2026-11-13 11:11

摘要

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 of 5-10 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. WithEveryone leads in identity similarity (0.538 versus GPT-Image-2.5's 0.472), with lower Copy-Paste (0.149 versus 0.197), 94.5% identity coverage, and 9.6% identity collisions. These results show that explicit identity-layout grounding enables identity-preserving generation to scale to larger groups without relying on direct reference-face copying.

作者备注：Project Page: doby-xu.github.io/WithEveryone/ ;Code will be released: github.com/Doby-Xu/WithEveryone/ ; References updated