Poster
in
Workshop: NeurIPS 2023 Workshop on Diffusion Models
LoRA can Replace Time and Class Embeddings in Diffusion Probabilistic Models
Joo Young Choi · Jaesung Park · Inkyu Park · Jaewoong Cho · Albert No · Ernest Ryu
Abstract:
We propose LoRA modules as a replacement for the time and class embeddings of the U-Net architecture for diffusion probabilistic models. Our experiments on CIFAR-10 show that a score network trained with LoRA achieves competitive FID scores while being more efficient in memory compared to a score network trained with time and class embeddings.
Chat is not available.