paper-with-me

홈 › Papers

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation

2024-06-07 · Lianyu Pang, Jian Yin, Baoquan Zhao, Feize Wu, Fu Lee Wang, Qing Li, Xudong Mao

Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image personalization: Textual Inversion and DreamBooth. When integrating the learned concept into new prompts, Textual Inversion tends to overfit the concept, while DreamBooth often overlooks it. We attribute these issues to the incorrect learning of the embedding alignment for the concept. We introduce AttnDreamBooth, a novel approach that addresses these issues by separately learning the embedding alignment, the attention map, and the subject identity in different training stages. We also introduce a cross-attention map regularization term to enhance the learning of the attention map. Our method demonstrates significant improvements in identity preservation and text alignment compared to the baseline methods.

📄 PDF Abstract BibTeX arXiv:2406.05000

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeImage GenerationText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

PALP: Prompt Aligned Personalization of Text-to-Image Models

2024-01-11 · Moab Arar, Andrey Voynov, Amir Hertz, Omri Avrahami 외

Content creators often aim to create personalized images using personal subjects that go beyond the capabilities of conventional text-to-image models. Additionally, they may want the resulting image to encompass a specif…

Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona Distillation

2023-04-18 · Haolan Zhan, Xuming Lin, Shaobo Cui, Zhongzhou Zhao 외

Existing neural methods have shown great potentials towards generating informative text from structured tabular data as well as maintaining high content fidelity. However, few of them shed light on generating personalize…

Table-to-Text GenerationText Generation

Personalized Reward Modeling for Text-to-Image Generation

2025-11-21 · Jeongeun Lee, Ryang Heo, Dongha Lee arxiv

Recent text-to-image (T2I) models generate semantically coherent images from textual prompts, yet evaluating how well they align with individual user preferences remains an open challenge. Conventional evaluation methods…

Text-to-Image Generation

Few-shot Personalization of LLMs with Mis-aligned Responses

2024-06-26 · Jaehyung Kim, Yiming Yang

As the diversity of users increases, the capability of providing personalized responses by large language models (LLMs) has become increasingly important. Existing approaches have only limited successes in LLM personaliz…

Diversity

Personalized Showcases: Generating Multi-Modal Explanations for Recommendations

2022-06-30 · An Yan, Zhankui He, Jiacheng Li, Tianyang Zhang 외

Existing explanation models generate only text for recommendations but still struggle to produce diverse contents. In this paper, to further enrich explanations, we propose a new task named personalized showcases, in whi…

Contrastive Learning