paper-with-me

홈 › Papers

Foundation Cures Personalization: Recovering Facial Personalized Models' Prompt Consistency

2024-11-22 · Yiyang Cai, Zhengkai Jiang, Yulong Liu, Chunyang Jiang, Wei Xue, Wenhan Luo, Yike Guo

Facial personalization represents a crucial downstream task in the domain of text-to-image generation. To preserve identity fidelity while ensuring alignment with user-defined prompts, current mainstream frameworks for facial personalization predominantly employ identity embedding mechanisms to associate identity information with textual embeddings. However, our experiments show that identity embeddings compromise the effectiveness of other tokens within the prompt, thereby hindering high prompt consistency, particularly when prompts involve multiple facial attributes. Moreover, previous works overlook the fact that their corresponding foundation models hold great potential to generate faces aligning to prompts well and can be easily leveraged to cure these ill-aligned attributes in personalized models. Building upon these insights, we propose FreeCure, a training-free framework that harnesses the intrinsic knowledge from the foundation models themselves to improve the prompt consistency of personalization models. First, by extracting cross-attention and semantic maps from the denoising process of foundation models, we identify easily localized attributes (e.g., hair, accessories, etc). Second, we enhance multiple attributes in the outputs of personalization models through a novel noise-blending strategy coupled with an inversion-based process. Our approach offers several advantages: it eliminates the need for training; it effectively facilitates the enhancement for a wide array of facial attributes in a non-intrusive manner; and it can be seamlessly integrated into existing popular personalization models. FreeCure has demonstrated significant improvements in prompt consistency across a diverse set of state-of-the-art facial personalization models while maintaining the integrity of original identity fidelity.

📄 PDF Abstract BibTeX arXiv:2411.15277

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability

2025-03-09 · Xirui Hu, Jiahao Wang, Hao Chen, Weizhan Zhang 외

Recent advancements in text-to-image generation have spurred interest in personalized human image generation, which aims to create novel images featuring specific human identities as reference images indicate. Although e…

Contrastive LearningFacial EditingImage GenerationText to Image Generation+1

Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach

2025-09-16 · Yiyuan Yang, Guodong Long, Qinghua Lu, Liming Zhu 외 arxiv

Federated foundation models represent a new paradigm to jointly fine-tune pre-trained foundation models across clients. It is still a challenge to fine-tune foundation models for a small group of new users or specialized…

Personalization of Large Language Models: A Survey

2024-10-29 · Zhehao Zhang, Ryan A. Rossi, Branislav Kveton, Yijia Shao 외

Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focu…

Recommendation SystemsSurveyText Generation

ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning

2023-10-08 · Wang Lu, Hao Yu, Jindong Wang, Damien Teney 외

When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources. In addition to typical limitations such as data, computation, and communication costs, …

Federated LearningPersonalized Federated Learning

My3DGen: A Scalable Personalized 3D Generative Model

2023-07-11 · Luchao Qi, Jiaye Wu, Annie N. Wang, Shengze Wang 외

In recent years, generative 3D face models (e.g., EG3D) have been developed to tackle the problem of synthesizing photo-realistic faces. However, these models are often unable to capture facial features unique to each in…

modelNovel View Synthesis