paper-with-me

Papers

Accelerating Diffusion Transformers with Token-wise Feature Caching

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

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 diffusion transformers by caching the features in previous timesteps and reusing them in the following timesteps. However, previous caching methods ignore that different tokens exhibit different sensitivities to feature caching, and feature caching on some tokens may lead to 10$\times$ more destruction to the overall generation quality compared with other tokens. In this paper, we introduce token-wise feature caching, allowing us to adaptively select the most suitable tokens for caching, and further enable us to apply different caching ratios to neural layers in different types and depths. Extensive experiments on PixArt-$\alpha$, OpenSora, and DiT demonstrate our effectiveness in both image and video generation with no requirements for training. For instance, 2.36$\times$ and 1.93$\times$ acceleration are achieved on OpenSora and PixArt-$\alpha$ with almost no drop in generation quality.

📄 PDF Abstract BibTeX arXiv:2410.05317

Code (2)

Shenyi-Z/ToCa 공식 구현 pytorch
shenyi-z/duca pytorch

Tasks

Video Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching

2025-09-12 · Zhixin Zheng, Xinyu Wang, Chang Zou, Shaobo Wang 외 arxiv

Diffusion transformers have gained significant attention in recent years for their ability to generate high-quality images and videos, yet still suffer from a huge computational cost due to their iterative denoising proc…

Text-to-Video Generation

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

2026-04-04 · Haowei Zhu, Ji Liu, Ziqiong Liu, Dong Li 외 arxiv

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cac…

Image Generation

Accelerating Diffusion Transformers with Dual Feature Caching

2024-12-25 · Chang Zou, Evelyn Zhang, Runlin Guo, Haohang Xu 외

Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT acceleration, feature caching methods are des…

Video Generation

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching

2025-09-17 · Hanshuai Cui, Zhiqing Tang, Zhifei Xu, Zhi Yao 외 arxiv

Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiti…

Video Generation

SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models Inference

2026-08-04 · Shanghao Liu, Renze Chen, Size Zheng, Yuanqiang Liu 외 arxiv

Video diffusion transformers (vDiTs) generate high quality but pay quadratic self-attention cost, making inference prohibitive at video-token scales. The challenge is input-adaptive sparsity: selecting critical Q/K/V tok…

Video Generation