12 papers
AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation
Haoran Qin, Zhengan Yan, Shikang Zheng +9
Diffusion Transformers (DiTs) achieve high-quality generation but are costly due to iterative sampling. Dynamic-resolution sampling reduces early-stage cost by denoising at low res…
LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
Jinshan Liu, Haoran Qin, Xiaobing Tu +9
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 d…
Dynamic Video Generation: Shaping Video Generation Across Time and Space
Shikang Zheng, Jingkai Huang, Jiacheng Liu +5
Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens…
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
Zhengan Yan, Shikang Zheng, Haoran Qin +9
Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dyna…
From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution
Shikang Zheng, Guantao Chen, Lixuan He +4
Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a…
Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers
Guantao Chen, Shikang Zheng, Yuqi Lin +1
Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To a…
A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation
Jiacheng Liu, Xinyu Wang, Yuqi Lin +10
Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iteratio…
FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
Jiacheng Liu, Peiliang Cai, Qinming Zhou +9
The application of diffusion transformers is suffering from their significant inference costs. Recently, feature caching has been proposed to solve this problem by reusing features…
Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
Shikang Zheng, Guantao Chen, Qinming Zhou +6
Diffusion Transformers offer state-of-the-art fidelity in image and video synthesis, but their iterative sampling process remains a major bottleneck due to the high cost of transfo…
LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
Haozhe Jia, Wenshuo Chen, Yuqi Lin +8
While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic mi…
Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
Shikang Zheng, Liang Feng, Xinyu Wang +8
Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation. To reduce their substantial computational costs, feature cachin…
HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Acceleration
Liang Feng, Shikang Zheng, Jiacheng Liu +8
Diffusion models have achieved remarkable success in content generation but often incur prohibitive computational costs due to iterative sampling. Recent feature caching methods ac…