A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models

Understand

Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio.

• A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of score estimation networks during the inference.
• In this work, we propose a novel framework capable of adaptively allocating compute required for the score estimation, thereby reducing the overall sampling time of diffusion models.
• We observe that the amount of computation required for the score estimation may vary along the time step for which the score is estimated.