Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
Diffusion models have become a leading method for generative modeling of both image and scientific data. As these models are costly to train and evaluate, reducing the inference cost for diffusion models remains a major goal. Inspired by the recent empirical success in accelerating diffusion models via the parallel sampling technique~\cite{shih2024parallel}, we propose to divide the sampling process into $\mathcal{O}(1)$ blocks with parallelizable Picard iterations within each block. Rigorous theoretical analysis reveals that our algorithm achieves $\widetilde{\mathcal{O}}(\mathrm{poly} \log d)$ overall time complexity, marking the first implementation with provable sub-linear complexity w.r.t. the data dimension $d$. Our analysis is based on a generalized version of Girsanov's theorem and is compatible with both the SDE and probability flow ODE implementations. Our results shed light on the potential of fast and efficient sampling of high-dimensional data on fast-evolving modern large-memory GPU clusters.
Code (0)
등록된 구현이 없습니다.
Tasks
GPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Accelerating Parallel Sampling of Diffusion Models
Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling proc…
Image GenerationAccelerating Discrete Diffusion Models with Parallel-In-Time Sampling
Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, w…
DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach
Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-exiting has recently been proposed, where …
DenoisingImage GenerationLightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation
Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference, limiting practical applications. Existing acceleration methods for general diffusion models fail to exploit…
Talking Head GenerationAccelerating Speculative Diffusions via Block Verification
Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribution. Adapting this to continuous diffus…