Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA

arXiv:2304.06027v2 Announce Type: replace-cross
Abstract: Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential (i.e., continual) manner? In our work, we show that recent state-of-the-art customization of text-to-image models suffer from catastrophic forgetting when new concepts arrive sequentially. Specifically, when adding a new concept, the ability to generate high quality images of past, similar concepts …

arxiv continual cs.ai cs.cv cs.lg customization diffusion image image diffusion lora text text-to-image type