Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement

• URL: http://arxiv.org/abs/2602.18752v1
• Date: Sat, 21 Feb 2026 08:24:42 GMT
• Title: Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement
• Authors: Yuran Dong, Hang Dai, Mang Ye,
• Abstract summary: 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.
• Score: 54.199726425201895
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks. However, a persistent and long-standing limitation is the decline in facial identity (ID) consistency during realistic portrait editing. Due to the human eye's high sensitivity to facial features, such inconsistency significantly hinders the practical deployment of these models. Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP due to Cross-source Distribution Bias and Cross-source Feature Contamination. To address these issues, we propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration. By systematically analyzing diffusion trajectories, sampler behaviors, and attention properties, we introduce three key components: 1) Adaptive mixing strategy that aligns cross-source latent representations throughout the diffusion process. 2) Hybrid solver that disentangles source-specific identity attributes and details. 3) Attentional gating mechanism that selectively entangles visual elements. Extensive experiments show that EditedID achieves state-of-the-art performance in preserving original facial ID and edited element IP consistency. As a training-free and plug-and-play solution, it establishes a new benchmark for practical and reliable single/multi-person facial identity restoration in open-world settings, paving the way for the deployment of multimodal editing large models in real-person editing scenarios. The code is available at https://github.com/NDYBSNDY/EditedID.

Related papers

• 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)
• Zero-shot Face Editing via ID-Attribute Decoupled Inversion [5.695436409400152]
  We propose a zero-shot face editing method based on ID-Attribute Decoupled Inversion.<n>We decompose the face representation into ID and attribute features, using them as joint conditions to guide both the inversion and the reverse diffusion processes.<n>Our method supports a wide range of complex multi-attribute face editing tasks using only text prompts, without requiring region-specific input, and operates at a speed comparable to DDIM inversion.
  arXiv  Detail & Related papers  (2025-10-13T06:34:40Z)
• From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts [69.44297222099175]
  We introduce a Mixture of Facial Experts (MoFE) that captures distinct but mutually reinforcing aspects of facial attributes.<n>To mitigate dataset limitations, we have tailored a data processing pipeline centered on two key aspects: Face Constraints and Identity Consistency.<n>We have curated and refined a Large Face Angles (LFA) dataset from existing open-source human video datasets.
  arXiv  Detail & Related papers  (2025-08-13T04:10:16Z)
• Personalized Face Super-Resolution with Identity Decoupling and Fitting [50.473357681579664]
  In extreme degradation scenarios, critical attributes and ID information are often severely lost in the input image.<n>Existing methods tend to generate hallucinated faces under such conditions, producing restored images lacking authentic ID constraints.<n>We propose a novel FSR method with Identity Decoupling and Fitting (IDFSR) to enhance ID restoration under large scaling factors.
  arXiv  Detail & Related papers  (2025-08-13T02:33:11Z)
• DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability [12.692129257068085]
  We present DynamicID, a tuning-free framework that inherently facilitates both single-ID and multi-ID personalized generation.<n>Our key innovations include: 1) Semantic-Activated Attention (SAA), which employs query-level activation gating to minimize disruption to the base model when injecting ID features and achieve multi-ID personalization without requiring multi-ID samples during training; 2) Identity-Motion Reconfigurator (IMR), which applies feature-space manipulation to effectively disentangle facial motion and identity features, supporting flexible facial editing; and 3) a task-decoupled training paradigm that reduces data dependency, together with VariFace-10k,
  arXiv  Detail & Related papers  (2025-03-09T08:16:19Z)
• Towards Consistent and Controllable Image Synthesis for Face Editing [18.646961062736207]
  RigFace is a novel approach to control the lighting, facial expression and head pose of a portrait photo.<n>Our model achieves comparable or even superior performance in both identity preservation and photorealism compared to existing face editing models.
  arXiv  Detail & Related papers  (2025-02-04T16:36:07Z)
• ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving [64.90148669690228]
  ConsistentID is an innovative method crafted for diverseidentity-preserving portrait generation under fine-grained multimodal facial prompts.<n>We present a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets.
  arXiv  Detail & Related papers  (2024-04-25T17:23:43Z)
• 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)

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.