Abstract
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fusion matrix of multiple Low-Rank Adaptations (LoRAs) to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, where the model struggles to preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through concept injection constraints, enhancing visibility via an expanded cross-attention mechanism. To combat concept confusion, concept isolation constraints are introduced, refining the self-attention computation. Furthermore, we propose two inference techniques to accelerate inference speed without performance degradation and enhance the accuracy of the generated region, respectively. Extensive experiments demonstrate that LoRA-Composer significantly outperforms standard baselines, especially in scenarios without image-based conditions such as canny edge or pose estimation.
Funding Information
  • National Natural Science Foundation of China (62402417)
  • National Natural Science Foundation of China (62273302)
  • National Natural Science Foundation of China (62036009)
  • National Natural Science Foundation of China (61936006)
  • Key Research and Development Program of Ningbo (2024Z115)
  • Yongjiang Talent Introduction Program (2023A-197-G)
  • China Computer Federation (CCF)-Tencent Open Fund (JR2023TEG012)