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

arXiv: https://arxiv.org/abs/2602.18752 · HTML: https://mlsanity.com/paper/2602.18752/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 21 Feb 2026.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023)
- [In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer](https://mlsanity.com/paper/2504.20690/) (2025)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [DifFace: Blind Face Restoration with Diffused Error Contraction](https://mlsanity.com/paper/2212.06512/) (2022)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control](https://mlsanity.com/paper/2405.12970/) (2024)
- [DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization](https://mlsanity.com/paper/2402.09812/) (2024)
- [FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping](https://mlsanity.com/paper/2210.10473/) (2022)
- [A Formal Evaluation of PSNR as Quality Measurement Parameter for Image Segmentation Algorithms](https://mlsanity.com/paper/1605.07116/) (2016)
- [Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models](https://mlsanity.com/paper/2409.07269/) (2024)
- [Universal Image Restoration Pre-training via Degradation Classification](https://mlsanity.com/paper/2501.15510/) (2025)
- [Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration](https://mlsanity.com/paper/2410.00418/) (2024)
- [MEGANE: Morphable Eyeglass and Avatar Network](https://mlsanity.com/paper/2302.04868/) (2023)
- [Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer](https://mlsanity.com/paper/2405.04312/) (2024)
- [DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning](https://mlsanity.com/paper/2504.14509/) (2025)

## Abstract (arXiv)

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.