Continual Diffusion：使用 C-LoRA 实现文本到图像的持续个性化（英文版）

英文标题：Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA中文摘要：本研究提出了一种新的方法 C-LoRA，用于解决文本到图像连续定制中的遗忘问题，并取得了良好的效果，为各种应用开启了新的可能性。英文摘要：Recent works demonstrate a remarkable ability to customize text-to-imagediffusion models while only providing a few example images. What happens if youtry to customize such models using multiple, fine-grained concepts in asequential (i.e., continual) manner? In our work, we show that recentstate-of-the-art customization of text-to-imag