Cross-Person Identity Change Under Source-Coupled Multi-Human Generation: A Controlled UniPortrait Study

Edrees Al-Edreesi; Ghaleb Al-Gaphari; Muneer Alsurori; Mohammed Edrees; Fouad Al-Hamdani

cs.CVOct 15, 2026

Cross-Person Identity Change Under Source-Coupled Multi-Human Generation: A Controlled UniPortrait Study

Authors: Edrees Al-Edreesi, Ghaleb Al-Gaphari, Muneer Alsurori, Mohammed Edrees, Fouad Al-Hamdani

Organizations: Sana’a University, Sana’a, Yemen. · Ibb University, Ibb, Yemen.

Abstract

Multi-human personalization must account for identity changes in people outside the nominal target of a generative operation. We characterize this behavior in UniPortrait, without introducing a new preservation algorithm. Two sequential studies use 119 accepted two-person baseline scenes and three fixed output seeds, measuring continuous reference-based facial similarity with InsightFace \buffalo. In Study1, source-coupled single-ID target-only generation (A1) produces negative mean transitions for both the protected person ( $-0.567904$ ) and target ( $-0.236904$ ), indicating broad perturbation rather than established successful repair with collateral loss. In Study2, native dual-ID generation (A2) yields more positive paired contrasts: protected $+0.512918$ (95% case-cluster CI $[0.471434,0.550259]$ ) and target $+0.158853$ ( $[0.118903,0.197523]$ ), across 287 jointly measurable pairs from 111 cases. Shared baseline similarity cancels algebraically in these paired contrasts, leaving a matched POST comparison. Validation designed after the primary result freeze finds directional agreement with an independent identity evaluator and blinded human judgments; within-\buffalo\ nuisance models provide supportive sensitivity evidence. The findings characterize intact native regimes, whose references, routing, adapters, and token counts co-vary. They do not establish component causality, categorical identity preservation, successful localized editing, or generalization beyond the evaluated implementation and measurable cohort.

Figures & tables

Panel of Figure 1 — Figure 1: Design schematic of the evaluated implementation. A1/A2 supply PRE-derived attention context from source slot 0 to a seeded Gaussian output in slot 1. The reference configuration changes as an intact native regime. A0 has no PRE coupling. DIoU and human correspondence occur after generation and do not condition it. Boxes denote operations rather than identity-preservation guarantees.

Study 1: 597 measurable action outputs; 257 jointly measurable case–seed pairs.
Metric	A1	A0	A2
Planned outputs per action	357	357	357
Identity-measurable outputs	304	293	319
Unavailable outputs	53	64	38
Correspondence	DIoU	Human consensus	DIoU
Study 2: 287 paired rows from 111 cases; 74 complete three-seed cases.

Table 1: Study design and availability. All actions use 119 accepted PRE cases and seeds 1101, 2202, 3303. A1 is reused in Study 2. Joint Study 2 counts partition the 357 planned pairs; a case can contribute several seeds.

Study / role	Estimand	Estimate	95% bootstrap CI	Bootstrap SE
1 / Protected $j$	A1 transition	$-0.567904$	$[-0.597297,-0.536832]$	$0.015604$
	A0 transition	$-0.010801$	$[-0.030899,+0.011336]$	$0.010925$
	A1 $-$ A0	$-0.557103$	$[-0.582850,-0.530484]$	$0.013219$
1 / Target $k$	A1 transition	$-0.236904$	$[-0.265309,-0.209629]$	$0.014251$
	A0 transition	$-0.021632$	$[-0.038848,-0.003419]$	$0.009013$
	A1 $-$ A0	$-0.215272$	$[-0.245432,-0.184669]$	$0.015603$

Table 2: Primary and secondary fitted Buffalo_L estimates. Study 1 uses 597 measurable action observations in the 119-case design (A1 304, A0 293); Study 2 uses 287 jointly measurable pairs from 111 cases. All rows use equal seed weights and 5,000 case-cluster bootstrap resamples. Full variance and sensitivity records are in Supplement Tables S2, S3, S6–S8.

Figure 2: Protected-person evidence across the sequential studies. (a) Distributions of

\Delta\mathrm{ID}_{j}

for A1 (

n=304

) and A0 (

n=293

). (b) 287 jointly measurable paired contrasts, their fitted estimate and 95% case-cluster bootstrap interval, and seed strata (

n=94,97,96

). The panels have different endpoints and scales: within-action change in (a), paired between-action difference in (b).

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Axis	Evidential role	Protected: estimate [95% CI]	Target: estimate [95% CI]
Primary Study 2	Buffalo_L paired anchor	$+0.512918$ $[0.471434,0.550259]$	$+0.158853$ $[0.118903,0.197523]$
V1: ID-Sim	Independent metric concordance	$+0.231351$ $[0.207440,0.254732]$	$+0.072272$ $[0.048170,0.097237]$
V2: Human ( $N=5$ raters)	Independent human concordance	$+0.986667$ $[0.965000,1.000000]$	$+0.401948$ $[0.304816,0.498673]$
V3: Core	Supportive within-Buffalo_L sensitivity	$+0.511637$ $[0.471271,0.548896]$	$+0.158524$ $[0.122081,0.192932]$
V3: Pose	Supportive within-Buffalo_L sensitivity	$+0.511421$ $[0.471351,0.550273]$	$+0.158543$ $[0.123847,0.192405]$

Appendix

Table S10: Validation summary. The protocol classifications are CONCORDANT for V1/V2/V3 and OVERALL_CONCORDANT overall. Independent metric/human measurements and supportive within-Buffalo_L nuisance sensitivity have distinct evidential roles. Intervals are 95% case-cluster bootstrap intervals; scales are not interchangeable.

Model	Role	Estimate	95% case-cluster CI
Core	Protected $j$	$+0.511636943$	$[0.47127149,0.54889617]$
Core	Target $k$	$+0.158524410$	$[0.12208135,0.19293198]$
Pose-augmented	Protected $j$	$+0.511421391$	$[0.47135144,0.55027348]$
Pose-augmented	Target $k$	$+0.158542884$	$[0.12384655,0.19240531]$

Appendix

Table S11: V3 nuisance-adjusted estimates and 95% case-cluster bootstrap intervals.

Identity-Preserving Image Generation

Identity-preserving image generation creates or edits images while retaining a person's recognizable features across changes in pose, style, or scene.

See all 48 papers

Oct 23, 2025

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer

Gordon Guocheng Qian, Ruihang Zhang, Tsai-Shien Chen +11

Snap Inc., USA · University of Toronto, Canada · University of California, Merced, USA +1

Subject-Driven Image Generation Image Generation Compositional Image Generation Identity-Preserving Image Generation Conditional Diffusion Models Multi-Subject Image Generation

Ask PDF

Mar 16, 2026

AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas

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.

Longhui Yuan

Identity-Preserving Image Generation Controllable Image Generation Diffusion-Based Image Generation

Ask PDF

Jun 29, 2026

IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation

Customized Portrait Generation (CPG) technologies have been widely used to generate high-fidelity person images given an input image indicating the identity and a text prompt indicating the required edits. Yet these methods pose significant privacy risks by spreading fake visual information. Against such risks, each public generator should be able to suppress its generation ability for a particular person when requested. Therefore, in this work we investigate the identity unlearning problem for CPG. Since there are no previous methods in this field, we propose a simple baseline that updates the image encoder by minimizing identity similarity between generated and input images for target identities to be unlearned, while maximizing it for identities to be retained. However, we find such a global perturbation in the feature space harms the fidelity of generated images for other identities to be retained. To solve this problem, we propose a novel method IREU, which first locates identity-related features in an offline manner and then only performs feature perturbations on them. The experimental results show that our proposed method IREU achieves better identity unlearning performance for target identities to be unlearned, and also keeps high fidelity for other identities to be retained. In addition, our unlearned image encoder is generalizable across different generators with the same encoder without fine-tuning, which is friendly for deployment in practice.

Chaoyi Shi, Shanshan Zhang, Jian Yang

PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology · PCA Lab, School of Intelligence Science and Technology, Nanjing University

Subject-Driven Image Generation Machine Unlearning

Ask PDF

Abstract

Identity-Preserving Image Generation

Explore similar work

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas

IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation