No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching

• URL: http://arxiv.org/abs/2512.12604v1
• Date: Sun, 14 Dec 2025 09:02:18 GMT
• Title: No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching
• Abstract summary: We present X-Slim (e-Xtreme-Slimming Caching), a training-free, cache-based accelerator.<n>It is the first unified framework to exploit cacheable redundancy across timesteps, structure (blocks), and space (tokens)<n>It reduces latency by up to 4.97x and 3.52x with minimal perceptual loss.
• Score: 17.396336005757025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an inherent trade-off remains: aggressive timestep reuse offers large speedups but can easily cross the critical line, hurting fidelity, while block- or token-level reuse is safer but yields limited computational savings. We present X-Slim (eXtreme-Slimming Caching), a training-free, cache-based accelerator that, to our knowledge, is the first unified framework to exploit cacheable redundancy across timesteps, structure (blocks), and space (tokens). Rather than simply mixing levels, X-Slim introduces a dual-threshold controller that turns caching into a push-then-polish process: it first pushes reuse at the timestep level up to an early-warning line, then switches to lightweight block- and token-level refresh to polish the remaining redundancy, and triggers full inference once the critical line is crossed to reset accumulated error. At each level, context-aware indicators decide when and where to cache. Across diverse tasks, X-Slim advances the speed-quality frontier. On FLUX.1-dev and HunyuanVideo, it reduces latency by up to 4.97x and 3.52x with minimal perceptual loss. On DiT-XL/2, it reaches 3.13x acceleration and improves FID by 2.42 over prior methods.

Related papers

• LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models [9.146969118551167]
  DLLMs enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation.<n>Current methods suffer from severe operator-level redundancy.<n>We propose LaCache, a training-free acceleration framework.
  arXiv  Detail & Related papers  (2026-07-16T10:49:15Z)
• Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion [61.57938553036056]
  ARL2 is a hybrid attention module that replaces quadratic cross-frame attention with a fixed-size recurrent state.<n>We decompose self-attention into two branches: an intra-frame softmax branch for spatial detail and local dependencies, and an inter-frame recurrent linear branch that maintains a fixed-size state for streaming context.<n>With 75% of layers replaced by hybrid linear attention, the model achieves up to 2.26 wall-clock speedup and 54% memory reduction, while maintaining comparable quality with improving temporal consistency.
  arXiv  Detail & Related papers  (2026-05-15T19:33:45Z)
• Motion-Aware Caching for Efficient Autoregressive Video Generation [73.27762884730272]
  MotionCache exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics.<n>Experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups.
  arXiv  Detail & Related papers  (2026-05-03T05:49:27Z)
• X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference [37.22440439525785]
  We present X-Cache, a training-free acceleration method that caches across consecutive generation chunks rather than across denoising steps.<n>X-Cache achieves 71% block skip rate with 2.6x wall-clock speedup while maintaining minimum degradation.
  arXiv  Detail & Related papers  (2026-04-22T07:36:59Z)
• WorldCache: Content-Aware Caching for Accelerated Video World Models [50.7543797435026]
  We present textbfWorldCache, a Perception-Constrained Dynamic CaCache framework.<n>WorldCache improves both when and how to reuse features.<n>On Cosmos-2.5-2B evaluated on PAI-Bench, WorldCache achieves textbf$2.3times$ inference speedup while preserving textbf99.4% of baseline quality.
  arXiv  Detail & Related papers  (2026-03-23T17:59:54Z)
• PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation [35.47114707080758]
  High computational costs and slow inference hinder the practical application of video generation models.<n>We propose textbfPreciseCache, a plug-and-play framework that precisely detects and skips truly redundant computations.
  arXiv  Detail & Related papers  (2026-03-01T08:08:49Z)
• 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)
• 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)
• PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache [61.57938553036056]
  We introduce PackCache, a training-free KV-cache management method that compacts the KV cache through three coordinated mechanisms.<n>In terms of efficiency, PackCache accelerates end-to-end generation by 1.7-2.2x on 48-frame long sequences.
  arXiv  Detail & Related papers  (2026-01-07T19:51:06Z)
• ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration [14.306565517230775]
  Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment.<n>Existing methods suffer from two key limitations: (1) uniform caching intervals fail to align with the non-uniform temporal dynamics of DiT, and (2) naive feature reuse with excessively large caching intervals can lead to severe error accumulation.<n>We propose ProCache, a training-free dynamic feature caching framework that addresses these issues via two core components.
  arXiv  Detail & Related papers  (2025-12-19T07:27:19Z)
• H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models [7.8812023976358425]
  H2-cache is a novel hierarchical caching mechanism designed for modern generative diffusion model architectures.<n>Our method is founded on the key insight that the denoising process can be functionally separated into a structure-defining stage and a detail-refining stage.<n>Experiments on the Flux architecture demonstrate that H2-cache achieves significant acceleration (up to 5.08x) while maintaining image quality nearly identical to the baseline.
  arXiv  Detail & Related papers  (2025-10-31T04:47:14Z)
• LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation [40.968338980157846]
  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.
  arXiv  Detail & Related papers  (2025-10-06T20:54:44Z)
• 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)
• Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation [50.04968365065964]
  Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference.<n>We introduce Lightning-fast Caching-based Parallel denoising prediction (LightningCP)<n>We also propose Decoupled Foreground Attention (DFA) to further accelerate attention computations.
  arXiv  Detail & Related papers  (2025-08-25T02:58:39Z)
• MagCache: Fast Video Generation with Magnitude-Aware Cache [91.2771453279713]
  We introduce a novel and robust discovery: a unified magnitude law observed across different models and prompts.<n>We introduce a Magnitude-aware Cache (MagCache) that adaptively skips unimportant timesteps using an error modeling mechanism and adaptive caching strategy.<n> Experimental results show that MagCache achieves 2.10x-2.68x speedups on Open-Sora, CogVideoX, Wan 2.1, and HunyuanVideo, while preserving superior visual fidelity.
  arXiv  Detail & Related papers  (2025-06-10T17:59:02Z)
• FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [43.83288560196838]
  Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks.<n>FastCache is a hidden-state-level caching and compression framework that accelerates DiT inference.<n> Empirical evaluations across multiple DiT variants demonstrate substantial reductions in latency and memory usage.
  arXiv  Detail & Related papers  (2025-05-26T05:58:49Z)
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching [56.286064975443026]
  We make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through a caching mechanism, can be readily removed even without updating the model parameters. We introduce a novel scheme, named Learningto-Cache (L2C), that learns to conduct caching in a dynamic manner for diffusion transformers. Experimental results show that L2C largely outperforms samplers such as DDIM and DPM-r, alongside prior cache-based methods at the same inference speed.
  arXiv  Detail & Related papers  (2024-06-03T18:49:57Z)
• DeepCache: Accelerating Diffusion Models for Free [65.02607075556742]
  DeepCache is a training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models. Under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS.
  arXiv  Detail & Related papers  (2023-12-01T17:01:06Z)

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.