From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate diffusion models by caching the features in the previous timesteps and then reusing them in the following timesteps. However, at timesteps with significant intervals, the feature similarity in diffusion models decreases substantially, leading to a pronounced increase in errors introduced by feature caching, significantly harming the generation quality. To solve this problem, we propose TaylorSeer, which firstly shows that features of diffusion models at future timesteps can be predicted based on their values at previous timesteps. Based on the fact that features change slowly and continuously across timesteps, TaylorSeer employs a differential method to approximate the higher-order derivatives of features and predict features in future timesteps with Taylor series expansion. Extensive experiments demonstrate its significant effectiveness in both image and video synthesis, especially in high acceleration ratios. For instance, it achieves an almost lossless acceleration of 4.99$\times$ on FLUX and 5.00$\times$ on HunyuanVideo without additional training. On DiT, it achieves $3.41$ lower FID compared with previous SOTA at $4.53$$\times$ acceleration. %Our code is provided in the supplementary materials and will be made publicly available on GitHub. Our codes have been released in Github:https://github.com/Shenyi-Z/TaylorSeer
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Test-time Sparsity for Extreme Fast Action Diffusion
Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current technologies showing promise in accelerating diffusion transformers…
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerati…
Video GenerationForecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
Diffusion Transformers (DiTs) have demonstrated remarkable performance in visual generation tasks. However, their low inference speed limits their deployment in low-resource applications. Recent training-free approaches …
Accelerating Diffusion Transformers with Token-wise Feature Caching
Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate …
Video GenerationAccelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching
Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E$^2$-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to …