Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
Institute of Smart Cities (ISC)（智能城市研究所）；Department of Statistics, Computer Science and Mathematics（统计学、计算机科学与数学系）；Public University of Navarre (UPNA)（纳瓦拉公共大学）
Ruben Pascual, Mikel Sesma-Sara, Aranzazu Jurio, Daniel Paternain, Mikel Galar
The audiovisual industry is undergoing a profound transformation as it is integrating AI developments not only to automate routine tasks but also to inspire new forms of art. This paper addresses the problem of producing a virtually unlimited number of novel characters that preserve the artistic style and shared visual traits of a small set of human-designed reference characters, thus broadening creative possibilities in animation, gaming, and related domains. Our solution builds upon DreamBooth, a well-established fine-tuning technique for text-to-image diffusion models, and adapts it to tackle two core challenges: capturing intricate character details beyond textual prompts and the few-shot nature of the training data. To achieve this, we propose a multi-token strategy, using clustering to assign separate tokens to individual characters and their collective style, combined with LoRA-based parameter-efficient fine-tuning. By removing the class-specific regularization set and introducing random tokens and embeddings during generation, our approach allows for unlimited character creation while preserving the learned style. We evaluate our method on five small specialized datasets, comparing it to relevant baselines using both quantitative metrics and a human evaluation study. Our results demonstrate that our approach produces high-quality, diverse characters while preserving the distinctive aesthetic features of the reference characters, with human evaluation further reinforcing its effectiveness and highlighting the potential of our method.
A New Chinese Landscape Paintings Generation Model based on Stable Diffusion using DreamBooth
California State University, Long Beach（加州州立大学长滩分校）；Columbia University（哥伦比亚大学）；Northeastern University（东北大学）；No.1 Central Primary School Shanghai Huangpu（上海市黄浦区第一中心小学）；Shanghai Palmim Information Technology Ltd（上海帕米姆信息技术有限公司）
DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
Indian Institute of Information Technology Guwahati（印度古瓦哈蒂印度信息技术学院）；Hugging Face；National Yang Ming Chiao Tung University（国立阳明交通大学）；IBM Research（IBM研究院）
Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRA
Department of Computer Science, SCMNS School, Morgan State University, Baltimore, Maryland 21251, USA；Electrical \& Computer Engineering Dept., School of Engineering, Morgan State University, Baltimore, Maryland 21251, USA
Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
University of Manchester（曼彻斯特大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；InstantX Team（InstantX团队）；University of Edinburgh（爱丁堡大学）；Aalto University（阿alto大学）
GEM-Style Constraints for PEFT with Dual Gradient Projection in LoRA
Department of Computer Science University of North Carolina Greensboro（计算机科学系北卡罗来纳州立大学）；Department of Computer Science North Carolina State University（计算机科学系北卡罗来纳州立大学）
SplitFlux: Learning to Decouple Content and Style from a Single Image
School of Computing and Artificial Intelligence（计算与人工智能学院）；University College London, University of London（伦敦大学大学学院）；College of Computer Science and Technology（计算机科学与技术学院）
StyleAdapter: A Unified Stylized Image Generation Model
The University of Hong Kong（香港大学）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；The University of Macau（澳门大学）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Balanced Image Stylization with Style Matching Score
Show Lab, National University of Singapore（新加坡国立大学Show实验室）；Agency for Science, Technology and Research (A*STAR)（科技研究局）；Nanyang Technological University（南洋理工大学）；Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）
TriLoRA: Integrating SVD for Advanced Style Personalization in Text-to-Image Generation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Southeast University（东南大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shaanxi Normal University（陕西师范大学）
MuseumMaker: Continual Style Customization without Catastrophic Forgetting
State Key Laboratory of Robotics, the Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造研究院机器人国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；School of Automation Science and Engineering, South China University of Technology（华南理工大学自动化科学与工程学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Salesforce AI Research（Salesforce AI研究部门）
TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；Northeastern University（东北大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）
Filtering Memorization from Parameter-Space in Diffusion Models
RIKEN AIP（理化学研究所Advanced Institute for Peripheral Research）；Science of Tokyo（东京科学大学）；University of California, Berkeley（加州大学伯克利分校）；Zhejiang University（浙江大学）
Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection
School of Computer Science and Software Engineering, Southwest Petroleum University（西南石油大学计算机科学与软件工程学院）；School of Electronic Information and Artificial Intelligence, Leshan Normal University（乐山师范学院电子信息与人工智能学院）
