LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

• URL: http://arxiv.org/abs/2510.05367v1
• Date: Mon, 06 Oct 2025 20:54:44 GMT
• Title: LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
• Authors: Yang Xiao, Gen Li, Kaiyuan Deng, Yushu Wu, Zheng Zhan, Yanzhi Wang, Xiaolong Ma, Bo Hui,
• Abstract summary: Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models.<n>In this paper, we decompose the inference process into the encoding, denoising, and decoding stages.<n>We propose stage-specific strategies for reducing memory consumption.
• Score: 40.968338980157846
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we decompose the inference process into the encoding, denoising, and decoding stages, and observe that cache-based acceleration methods often lead to substantial memory surges in the latter two stages. To address this problem, we analyze the characteristics of inference across different stages and propose stage-specific strategies for reducing memory consumption: 1) Asynchronous Cache Swapping. 2) Feature chunk. 3) Slicing latents to decode. At the same time, we ensure that the time overhead introduced by these three strategies remains lower than the acceleration gains themselves. Compared with the baseline, our approach achieves faster inference speed and lower memory usage, while maintaining quality degradation within an acceptable range. The Code is available at https://github.com/NKUShaw/LightCache .

Related papers

• SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching [75.02865981328509]
  Caching reduces computation by reusing previously computed model outputs across timesteps.<n>We propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis.<n>SenCache achieves better visual quality than existing caching methods under similar computational budgets.
  arXiv  Detail & Related papers  (2026-02-27T17:36:09Z)
• Flow caching for autoregressive video generation [72.10021661412364]
  We present FlowCache, the first caching framework specifically designed for autoregressive video generation.<n>Our method achieves remarkable speedups of 2.38 times on MAGI-1 and 6.7 times on SkyReels-V2, with negligible quality degradation.
  arXiv  Detail & Related papers  (2026-02-11T13:11:04Z)
• MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference [11.934900617930774]
  MeanCache is a training-free caching framework for efficient Flow Matching inference.<n>We demonstrate that MeanCache achieves 4.12X and 4.56X and 3.59X acceleration, respectively, while consistently outperforming state-of-the-art caching baselines in generation quality.
  arXiv  Detail & Related papers  (2026-01-27T08:35:50Z)
• ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion [30.897215456167753]
  Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process.<n>We propose ERTACache, a principled caching framework that jointly rectifies both error types.<n>ERTACache achieves up to 2x inference speedup while consistently preserving or even improving visual quality.
  arXiv  Detail & Related papers  (2025-08-27T10:37:24Z)
• DiCache: Let Diffusion Model Determine Its Own Cache [62.954717254728166]
  DiCache is a training-free adaptive caching strategy for accelerating diffusion models at runtime.<n>Online Probe Profiling Scheme leverages a shallow-layer online probe to obtain an on-the-fly indicator for the caching error in real time.<n> Dynamic Cache Trajectory Alignment approximates the deep-layer feature output from multi-step historical caches.
  arXiv  Detail & Related papers  (2025-08-24T13:30:00Z)
• Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching [57.7533917467934]
  EasyCache is a training-free acceleration framework for video diffusion models.<n>We conduct comprehensive studies on various large-scale video generation models, including OpenSora, Wan2.1, and HunyuanVideo.<n>Our method achieves leading acceleration performance, reducing inference time by up to 2.1-3.3$times$ compared to the original baselines.
  arXiv  Detail & Related papers  (2025-07-03T17:59:54Z)
• dKV-Cache: The Cache for Diffusion Language Models [53.85291644298835]
  Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models.<n>We propose a KV-cache-like mechanism, delayed KV-Cache, for the denoising process of DLMs.<n>Our approach is motivated by the observation that different tokens have distinct representation dynamics throughout the diffusion process.
  arXiv  Detail & Related papers  (2025-05-21T17:32:10Z)
• FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality [58.80996741843102]
  FasterCache is a training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation.<n>We show that FasterCache can significantly accelerate video generation while keeping video quality comparable to the baseline.
  arXiv  Detail & Related papers  (2024-10-25T07:24:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.