paper-with-me

Papers

DiCache: Let Diffusion Model Determine Its Own Cache

2025-08-24 · Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Dahua Lin, Jiaqi Wang arxiv

Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: "When to cache" and "How to use cache", typically relying on predefined empirical laws or dataset-level priors to determine caching timings and adopting handcrafted rules for multi-step cache utilization. However, given the highly dynamic nature of the diffusion process, they often exhibit limited generalizability and fail to cope with diverse samples. In this paper, a strong sample-specific correlation is revealed between the variation patterns of the shallow-layer feature differences in the diffusion model and those of deep-layer features. Moreover, we have observed that the features from different model layers form similar trajectories. Based on these observations, we present DiCache, a novel training-free adaptive caching strategy for accelerating diffusion models at runtime, answering both when and how to cache within a unified framework. Specifically, DiCache is composed of two principal components: (1) Online Probe Profiling Scheme leverages a shallow-layer online probe to obtain an on-the-fly indicator for the caching error in real time, enabling the model to dynamically customize the caching schedule for each sample. (2) Dynamic Cache Trajectory Alignment adaptively approximates the deep-layer feature output from multi-step historical caches based on the shallow-layer feature trajectory, facilitating higher visual quality. Extensive experiments validate DiCache's capability in achieving higher efficiency and improved fidelity over state-of-the-art approaches on various leading diffusion models including WAN 2.1, HunyuanVideo and Flux.

📄 PDF Abstract BibTeX arXiv:2508.17356

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ACID: Adaptive Caching for vIDeo generation

2026-07-14 · Om Agrawal, Saurabh Agarwal, Aditya Akella arxiv

Video diffusion models produce high-quality generations but remain slow at inference due to their sequential denoising procedure. Caching-based acceleration methods address this by reusing intermediate model outputs: lea…

Video Generation

ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

2026-06-04 · Mishan Aliev, Eva Neudachina, Ilya Bykov, Aleksandr Oganov 외 arxiv

Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations acr…

SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving

2026-03-09 · Ayush Barik, Sofia Stoica, Nikhil Sarda, Arnav Kethana 외 arxiv

Text-to-audio diffusion models produce high-fidelity audio but require tens of function evaluations (NFEs), incurring multi-second latency and limited throughput. We present SoundWeaver, the first training-free, model-ag…

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models

2025-08-22 · Huanpeng Chu, Wei Wu, Guanyu Fen, Yutao Zhang arxiv

Diffusion models have emerged as a powerful paradigm for generative tasks such as image synthesis and video generation, with Transformer architectures further enhancing performance. However, the high computational cost o…

Video Generation

Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration

2025-11-27 · Mengyu Yang, Yanming Yang, Chenyi Xu, Chenxi Song 외 arxiv

Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denoising process. While re…

Video Generation