Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System

• URL: http://arxiv.org/abs/2609.04151v2
• Date: Thu, 10 Sep 2026 14:54:13 GMT
• Title: Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System
• Abstract summary: Generative image models can produce high-quality images, follow complex instructions, and support precise edits.<n>But they still struggle to preserve who or what is being depicted.<n>We show that identity preservation remains a distinct limitation of current generative foundation models.
• Score: 20.281088110768955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative image models can now produce high-quality images, follow complex instructions, and support precise edits, but they still struggle to preserve who or what is being depicted. When generating or editing images of a specific subject, identity may drift as the pose, expression, appearance, viewpoint, or surrounding scene changes. Existing subject-driven methods make fundamentally different choices about where identity is represented: through the input context (GPT-Image-2, NB2), as trainable subject-specific model parameters (LoRA), or as a persistent identity layer (PHOTA IDENTITY) reusable across generations and edits. We systematically benchmark these paradigms across subject-driven generation, editing, restoration, and multi-subject settings, with tasks designed to increasingly stress identity preservation. Our results show that identity preservation remains a distinct limitation of current generative foundation models: strong image quality and instruction following do not necessarily imply strong identity fidelity, and identity degradation becomes more pronounced under iterative edits, small subject scales, severe image degradation, and multi-subject composition. Persistent identity substantially reduces this degradation across generation, editing, and restoration, consistently improving identity preservation when applied to different foundation models while maintaining comparable instruction adherence and perceptual image quality. These results suggest that identity does not simply emerge from increasingly capable generative models, but can instead be represented as persistent subject knowledge that is composed independently with the underlying generative model.

Related papers

• Latent-Identity Tuning in Text-to-Image Personalization Models [65.31471460269033]
  We present a method for fine-grained identity tuning in text-to-image personalization models.<n>Unlike standard image editing, identity tuning modifies the latent representation of a specific identity.<n>We show that meaningful directions can be identified within this space and within subspaces defined by selected tokens.
  arXiv  Detail & Related papers  (2026-07-13T17:59:49Z)
• Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement [54.199726425201895]
  Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks.<n>Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP.<n>We propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration.
  arXiv  Detail & Related papers  (2026-02-21T08:24:42Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• ID-Booth: Identity-consistent Face Generation with Diffusion Models [27.46650231581887]
  We present a novel generative diffusion-based framework called ID-Booth.<n>The framework enables identity-consistent image generation while retaining the synthesis capabilities of pretrained diffusion models.<n>Our method facilitates better intra-identity consistency and inter-identity separability than competing methods, while achieving higher image diversity.
  arXiv  Detail & Related papers  (2025-04-10T02:20:18Z)
• EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance [20.430259028981094]
  Zero-shot personalized image generation models aim to produce images that align with both a given text prompt and subject image.<n>Existing methods often struggle to capture fine-grained subject details and frequently prioritize one form of guidance over the other.<n>We introduce a new approach, EZIGen, that employs two main components: leveraging a fixed pre-trained Diffusion UNet itself as subject encoder.
  arXiv  Detail & Related papers  (2024-09-12T14:44:45Z)
• LIPE: Learning Personalized Identity Prior for Non-rigid Image Editing [20.861672583434718]
  LIPE is a two-stage framework designed to customize the generative model utilizing a limited set of images of the same subject. We present LIPE, a two-stage framework designed to customize the generative model utilizing a limited set of images of the same subject, and subsequently employ the model with learned prior for non-rigid image editing.
  arXiv  Detail & Related papers  (2024-06-25T02:56:16Z)
• ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning [57.91881829308395]
  Identity-preserving text-to-image generation (ID-T2I) has received significant attention due to its wide range of application scenarios like AI portrait and advertising. We present textbfID-Aligner, a general feedback learning framework to enhance ID-T2I performance.
  arXiv  Detail & Related papers  (2024-04-23T18:41:56Z)
• PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization [92.90392834835751]
  PortraitBooth is designed for high efficiency, robust identity preservation, and expression-editable text-to-image generation. PortraitBooth eliminates computational overhead and mitigates identity distortion. It incorporates emotion-aware cross-attention control for diverse facial expressions in generated images.
  arXiv  Detail & Related papers  (2023-12-11T13:03:29Z)
• DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation [50.39533637201273]
  We propose DisenBooth, an identity-preserving disentangled tuning framework for subject-driven text-to-image generation. By combining the identity-preserved embedding and identity-irrelevant embedding, DisenBooth demonstrates more generation flexibility and controllability.
  arXiv  Detail & Related papers  (2023-05-05T09:08:25Z)
• T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up [16.165889084870116]
  We present an end-to-end approach to generate high-resolution person images conditioned on texts only. We develop an effective generative model to produce person images with two novel mechanisms.
  arXiv  Detail & Related papers  (2022-08-18T07:41:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.