PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation

Jiangshan Wang; Kang Zhao; Jiayi Guo; Jiayu Wang; Hang Guo; Chenyang Zhu; Xiu Li; Xiangyu Yue

cs.CVMar 1, 2026

PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation

Authors: Jiangshan Wang, Kang Zhao, Jiayi Guo, Jiayu Wang, Hang Guo, Chenyang Zhu, Xiu Li, Xiangyu Yue

Organizations: MMLab, CUHK · Tsinghua University · Tongyi Lab, Alibaba

Abstract

High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching, they often suffer from notable quality degradation. In this work, we reveal that this issue arises from their inability to distinguish truly redundant features, which leads to the unintended skipping of computations on important features. To address this, we propose PreciseCache, a plug-and-play framework that precisely detects and skips truly redundant computations, thereby accelerating inference without sacrificing quality. Specifically, PreciseCache contains two components: LFCache for step-wise caching and BlockCache for block-wise caching. For LFCache, we compute the Low-Frequency Difference (LFD) between the prediction features of the current step and those from the previous cached step. Empirically, we observe that LFD serves as an effective measure of step-wise redundancy, accurately detecting highly redundant steps whose computation can be skipped through reusing cached features. To further accelerate generation within each non-skipped step, we propose BlockCache, which precisely detects and skips redundant computations at the block level within the network. Extensive experiments on various backbones demonstrate the effectiveness of our PreciseCache, such as achieving an average of $2.6\times$ speedup on Wan2.1-14B without noticeable quality loss.

Figures & tables

Figure 1: Qualitative Results of PreciseCache on Wan2.1-14B ( Wang et al., 2025 ) . Compared with previous methods, our PreciseCache achieves higher acceleration (about 2.6 $\times$ speedup) of the base model without sacrificing the quality of generated videos.

Figure 2: The Illustration of the Denoising Process for Video Generation . At high-noise timesteps, the prediction of the model varies significantly. Reusing the cached features in this stage (the red line ) can significantly affect both the content and the quality of generated videos compared to the videos generated without caching (the orange line ). In contrast, the feature caching during low-noise timesteps only introduces negligible impacts (the green line ).

Figure 3: The Impact of Reusing the Cached Model Prediction at Each Timestep. Considering a 50-step denoising process from the Gaussian Noise $\bm{Z}_{50}$ to a clean latent $\bm{Z}_{0}$ , we respectively reuse the model output at timestep $t_{i+1}$ for each $i\in\{49,48,\cdots,0\}$ , and perform the subsequent denoising steps to generate the final video. We then compare each resulting video with the baseline (i.e., generated without caching and reusing) to evaluate the impact of reusing cached predictions. Different colors indicate different prompts.

Figure 4: The Difference between Model Predictions at Adjacent Timesteps. Although the difference is relatively large in the low-noise stage, it primarily arises from high-frequency components, which have limited influence on the perceptual quality of the generated results. Different colors indicate different prompts.

Figure 6: The Relationship between Latent Resolution and LFD. We observe that downsampling has little effect on the computation of LFD. The experiment is conducted on Wan2.1-14B ( Wang et al., 2025 ) .

Figure 7: The Importance of Each Transformer Block within the Video Diffusion Transformer. Different colors represent different denoising steps. The experiment is conducted on Wan2.1-14B ( Wang et al., 2025 ) .

Open-Sora 1.2 (480P, 192 frames)
Method	Efficiency			Visual Quality
Method	MACs (P) $\downarrow$	Speedup $\uparrow$	Latency (s) $\downarrow$	VBench $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$
Open-Sora 1.2 ( $T=30$ )	6.30	$1\times$	47.23	78.79%	-	-	-
PAB	5.33	$1.26\times$	38.40	78.15%	0.1041	0.8821	26.43
TeaCache	3.29	$1.95\times$	24.73	78.23%	0.0974	0.8897	26.84
FasterCache	4.13	$1.67\times$	29.15	78.46%	0.0835	0.8932	27.03

Table 1: Quantitative Comparison of efficiency and visual quality on 4 A800 GPUs.

Figure 8: Qualitative Comparison . Zoom in for the best views.

Table 10

Strategy	VBench $\uparrow$	LPIPS $\downarrow$
Reuse prediction ( $\bm{F}$ )	83.52%	0.0793
Reuse residuals ( $\bm{R}$ )	83.50%	0.0791
TaylorSeer	83.54%	0.0801

Table 4: Feature Reusing Strategy for Step-wise Caching. Without loss of generality, we conduct experiments on Wan2.1-14B ( Wang et al., 2025 ) , generating videos with 1080P resolution.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 9: More Qualitative Results of PreciseCache on Wan2.1-14B . Zoom in for the best views.

Efficient Video Generation

See all 26 papers

Motion-Aware Caching for Efficient Autoregressive Video Generation
May 3, 2026Jing Xu, Yuexiao Ma, Xuzhe Zheng +7Video Diffusion Models KV-Cache Management
1Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China · 2ByteDance · 3Max Planck Institute for Intelligent Systems, 4ELLIS Institute Tbingen, 5Tbingen AI Center
Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration
Oct 12, 2026Jiyue Jiang, Zhiyu Huo, Yuhan Chen +3Diffusion Model Caching Diffusion Model Acceleration
Department of Computer Science and Engineering, The Chinese University of Hong Kong · Theory Lab, 2012 Labs, Huawei Technology Co. Ltd
Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
Mar 6, 2026Dennis Menn, Yuedong Yang, Bokun Wang +6Video Generation Video Token Compression
University of Texas at Austin · Meta

May 3, 2026J/K move · Enter open · S save

Motion-Aware Caching for Efficient Autoregressive Video Generation

Jing Xu, Yuexiao Ma, Xuzhe Zheng, Xing Wang+6

1Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China · 2ByteDance · 3Max Planck Institute for Intelligent Systems, 4ELLIS Institute Tbingen, 5Tbingen AI Center

Video Diffusion Models KV-Cache Management Diffusion Model Caching Autoregressive Video Generation Diffusion Model Inference Acceleration Efficient Video Generation

Open paper AskPDF arXiv

Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of

\textbf{6.28}\times

and

\textbf{1.64}\times

respectively, while effectively preserving generation quality (VBench:

1\%\downarrow

and

0.01\%\downarrow

respectively). The code is available at https://github.com/ywlq/MotionCache.

Abstract

Efficient Video Generation

Explore similar work

Motion-Aware Caching for Efficient Autoregressive Video Generation

Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration

Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery