paper-with-me

홈 › Papers

LoRACLR: Contrastive Adaptation for Customization of Diffusion Models

2024-12-12 · CVPR 2025 1 · Enis Simsar, Thomas Hofmann, Federico Tombari, Pinar Yanardag

Recent advances in text-to-image customization have enabled high-fidelity, context-rich generation of personalized images, allowing specific concepts to appear in a variety of scenarios. However, current methods struggle with combining multiple personalized models, often leading to attribute entanglement or requiring separate training to preserve concept distinctiveness. We present LoRACLR, a novel approach for multi-concept image generation that merges multiple LoRA models, each fine-tuned for a distinct concept, into a single, unified model without additional individual fine-tuning. LoRACLR uses a contrastive objective to align and merge the weight spaces of these models, ensuring compatibility while minimizing interference. By enforcing distinct yet cohesive representations for each concept, LoRACLR enables efficient, scalable model composition for high-quality, multi-concept image synthesis. Our results highlight the effectiveness of LoRACLR in accurately merging multiple concepts, advancing the capabilities of personalized image generation.

📄 PDF Abstract BibTeX arXiv:2412.09622

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeImage GenerationPersonalized Image Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

2024-04-24 · Zinan Guo, Yanze Wu, Zhuowei Chen, Lang Chen 외

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces bo…

Image GenerationText to Image GenerationText-to-Image Generation

CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models

2025-02-11 · Sen Peng, Mingyue Wang, Jianfei He, Jijia Yang 외

Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the pri…

Image Generation

Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models

2024-02-22 · Yixuan Ren, Yang Zhou, Jimei Yang, Jing Shi 외

Image customization has been extensively studied in text-to-image (T2I) diffusion models, leading to impressive outcomes and applications. With the emergence of text-to-video (T2V) diffusion models, its temporal counterp…

Video Generation

Orthogonal Adaptation for Modular Customization of Diffusion Models

2023-12-05 · CVPR 2024 1 · Ryan Po, Guandao Yang, Kfir Aberman, Gordon Wetzstein

Customization techniques for text-to-image models have paved the way for a wide range of previously unattainable applications, enabling the generation of specific concepts across diverse contexts and styles. While existi…

One-shot Embroidery Customization via Contrastive LoRA Modulation

2025-09-23 · Jun Ma, Qian He, Gaofeng He, Huang Chen 외 arxiv

Diffusion models have significantly advanced image manipulation techniques, and their ability to generate photorealistic images is beginning to transform retail workflows, particularly in presale visualization. Beyond ar…

Knowledge DistillationContrastive LearningImage ManipulationStyle Transfer