AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation

Shengkun Tang*, Yaqing Wang, Caiwen Ding, Yi Liang, Yao Li, Dongkuan Xu ;

"Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application, especially in real-time scenarios, is hampered by their inherently slow generation speed. The slow generation stems from the necessity of multi-step network inference. While some certain predictions benefit from the full computation of the model in each sampling iteration, not every iteration requires the same amount of computation, potentially leading to inefficient computation. Unlike typical adaptive computation challenges that deal with single-step generation problems, diffusion processes with a multi-step generation need to dynamically adjust their computational resource allocation based on the ongoing assessment of each step’s importance to the final image output, presenting a unique set of challenges. In this work, we propose , an adaptive framework that dynamically allocates computation resources in each sampling step to improve the generation efficiency of diffusion models. To assess the effects of changes in computational effort on image quality, we present a timestep-aware uncertainty estimation module (UEM). Integrated at each intermediate layer, the UEM evaluates the predictive uncertainty. This uncertainty measurement serves as an indicator for determining whether to terminate the inference process. Additionally, we introduce an uncertainty-aware layer-wise loss aimed at bridging the performance gap between full models and their adaptive counterparts. Comprehensive experiments including class-conditional, unconditional, and text-guided image generation across multiple datasets demonstrate superior performance and efficiency of relative to current early exiting techniques in diffusion models. Notably, we observe enhanced performance on FID, with an acceleration ratio reduction of around 45%. Another exciting observation is that adaptive computation can synergize with other efficiency-enhancing methods such as reducing sampling steps to accelerate inference."