Saved in:
Bibliographic Details
Main Author: Yuan, Longhui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14770
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918390023585792
author Yuan, Longhui
author_facet Yuan, Longhui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14770
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas
Yuan, Longhui
Computer Vision and Pattern Recognition
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.
title AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.14770