paper-with-me

Papers

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

2026-03-25 · Tianyi Liu, Ye Lu, Linfeng Zhang, Chen Cai, Jianjun Gao, Yi Wang, Kim-Hui Yap, Lap-Pui Chau arxiv

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally expensive due to the iterative denoising process, posing challenges for practical deployment. Existing video diffusion acceleration methods primarily exploit denoising timestep-level feature reuse, which mitigates the redundancy in denoising process, but overlooks the architectural redundancy within the DiT that many attention operations over spatio-temporal tokens are redundantly executed, offering little to no incremental contribution to the model output. This work introduces HetCache, a training-free diffusion acceleration framework designed to exploit the inherent heterogeneity in diffusion-based masked video-to-video (MV2V) generation and editing. Instead of uniformly reuse or randomly sampling tokens, HetCache assesses the contextual relevance and interaction strength among various types of tokens in designated computing steps. Guided by spatial priors, it divides the spatial-temporal tokens in DiT model into context and generative tokens, and selectively caches the context tokens that exhibit the strongest correlation and most representative semantics with generative ones. This strategy reduces redundant attention operations while maintaining editing consistency and fidelity. Experiments show that HetCache achieves a noticeable acceleration, including a 2.67$\times$ latency speedup and FLOPs reduction over commonly used foundation models, with negligible degradation in editing quality.

📄 PDF Abstract BibTeX arXiv:2603.24260

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

2026-02-27 · Yasaman Haghighi, Alexandre Alahi arxiv

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 Generation

Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse

2026-04-06 · Hao Liu, Ye Huang, Chenghuan Huang, Zhenyi Zheng 외 arxiv

Video Diffusion Transformer (DiT) models are a dominant approach for high-quality video generation but suffer from high inference cost due to iterative denoising. Existing caching approaches primarily exploit similarity …

Video Generation

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

2026-08-18 · Jinshan Liu, Haoran Qin, Xiaobing Tu, Jiacheng Liu 외 arxiv

Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature caching has emerged a…

Video Generation

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers

2026-03-05 · Guandong Li arxiv

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing …

Video Generation

Accelerating Diffusion Transformers with Token-wise Feature Caching

2024-10-05 · Chang Zou, Xuyang Liu, Ting Liu, Siteng Huang 외

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 Generation