Constant Rate Scheduling: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models
This work addresses efficiency and performance improvements in diffusion models for image generation, representing an incremental advancement in noise schedule optimization.
The authors tackled the problem of optimizing noise schedules in diffusion models to ensure a constant rate of distributional change, achieving a state-of-the-art FID score of 2.03 on LSUN Horse 256×256 without sacrificing mode coverage.
We propose a general approach to optimize noise schedules for training and sampling in diffusion models. Our approach optimizes the noise schedules to ensure a constant rate of change in the probability distribution of diffused data throughout the diffusion process. Any distance metric for measuring the probability-distributional change is applicable to our approach, and we introduce three distance metrics. We evaluated the effectiveness of our approach on unconditional and class-conditional image-generation tasks using the LSUN (Horse, Bedroom, Church), ImageNet, FFHQ, and CIFAR10 datasets. Through extensive experiments, we confirmed that our approach broadly improves the performance of pixel-space and latent-space diffusion models regardless of the dataset, sampler, and number of function evaluations ranging from 5 to 250. Notably, by using our approach for optimizing both training and sampling schedules, we achieved a state-of-the-art FID score of 2.03 without sacrificing mode coverage on LSUN Horse 256 $\times$ 256.