Xin Zhou1*,
Dingkang Liang1*,
Kaijin Chen1, Tianrui Feng1,
Xiwu Chen2, Hongkai Lin1,
Yikang Ding2, Feiyang Tan2,
Hengshuang Zhao3,
Xiang Bai1†
1 Huazhong University of Science and Technology, 2 MEGVII Technology, 3 The University of Hong Kong
(*) Equal contribution. (†) Corresponding author.
Video synchronization issues may occur due to network load, for improved visualization, see the project page
Prompt: "Grassland at dusk, wild horses galloping, golden light flickering across manes." (HunyuanVideo)
Baseline | Ours (2.28x) | TeaCache (1.68x) | PAB (1.19x) |
---|---|---|---|
![]() |
![]() |
![]() |
![]() |
Prompt: "A top-down view of a barista creating latte art, skillfully pouring milk to form the letters 'TPAMI' on coffee." (Wan2.1-14B)
Baseline | Ours (2.63x) | TeaCache (1.46x) | PAB (2.10x) |
---|---|---|---|
![]() |
![]() |
![]() |
![]() |
Compatibility with SVG
SVG with EasyCache on HunyuanVideo can achieve more than 3x speedup.
SVG.with.EasyCache.mp4
- If you like our project, please give us a star ⭐ on GitHub for the latest update.
- [2025/07/06] 🔥 EasyCache for Wan2.1 I2V is released.
- [2025/07/05] 🔥 EasyCache for Wan2.1 T2V is released.
- [2025/07/04] 🎉 Release the paper of EasyCache.
- [2025/07/03] 🔥 EasyCache for Sparse-VideoGen on HunyuanVideo is released.
- [2025/07/02] 🔥 EasyCache for HunyuanVideo is released.
Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process. Addressing this bottleneck is essential for democratizing advanced video synthesis technologies and enabling their integration into real-world applications. This work proposes EasyCache, a training-free acceleration framework for video diffusion models. EasyCache introduces a lightweight, runtime-adaptive caching mechanism that dynamically reuses previously computed transformation vectors, avoiding redundant computations during inference. Unlike prior approaches, EasyCache requires no offline profiling, pre-computation, or extensive parameter tuning. We conduct comprehensive studies on various large-scale video generation models, including OpenSora, Wan2.1, and HunyuanVideo. Our method achieves leading acceleration performance, reducing inference time by up to 2.1-3.3× compared to the original baselines while maintaining high visual fidelity with a significant up to 36% PSNR improvement compared to the previous SOTA method. This improvement makes our EasyCache a efficient and highly accessible solution for high-quality video generation in both research and practical applications.
We validated the performance of EasyCache on leading video generation models and compared it with other state-of-the-art training-free acceleration methods.
Tested on Vbench prompts with NVIDIA A800.
Performance on HunyuanVideo:
Method | Latency (s)↓ | Speedup ↑ | PSNR ↑ | SSIM ↑ | LPIPS ↓ |
---|---|---|---|---|---|
HunyuanVideo (Baseline) | 1124.30 | 1.00x | - | - | - |
PAB | 958.23 | 1.17x | 18.58 | 0.7023 | 0.3827 |
TeaCache | 674.04 | 1.67x | 23.85 | 0.8185 | 0.1730 |
SVG | 802.70 | 1.40x | 26.57 | 0.8596 | 0.1368 |
EasyCache (Ours) | 507.97 | 2.21x | 32.66 | 0.9313 | 0.0533 |
Performance on Wan2.1-1.3B:
Method | Latency (s)↓ | Speedup ↑ | PSNR ↑ | SSIM ↑ | LPIPS ↓ |
---|---|---|---|---|---|
Wan2.1 (Baseline) | 175.35 | 1.00x | - | - | - |
PAB | 102.03 | 1.72x | 18.84 | 0.6484 | 0.3010 |
TeaCache | 87.77 | 2.00x | 22.57 | 0.8057 | 0.1277 |
EasyCache (Ours) | 69.11 | 2.54x | 25.24 | 0.8337 | 0.0952 |
EasyCache is orthogonal to other acceleration techniques, such as the efficient attention mechanism SVG, and can be combined with them for even greater performance gains.
Combined Performance on HunyuanVideo (720p): Tested on NVIDIA H20 GPUs.
Method | Latency (s)↓ | Speedup ↑ | PSNR (dB) ↑ |
---|---|---|---|
Baseline | 6594s | 1.00x | - |
SVG | 3474s | 1.90x | 27.56 |
SVG (w/ TeaCache) | 2071s | 3.18x | 22.65 |
SVG (w/ Ours) | 1981s | 3.33x | 27.26 |
Detailed instructions for each supported model are provided in their respective directories. We are continuously working to extend support to more models.
- Prerequisites: Set up the environment and download weights from the official HunyuanVideo repository.
- Copy Files: Place the EasyCache script files into your local HunyuanVideo project directory.
- Run: Execute the provided Python script to run inference with acceleration. For complete instructions, please refer to the README.
- Prerequisites: Set up the environment and download weights from the official Wan2.1 repository.
- Copy Files: Place the EasyCache script files into your local Wan2.1 project directory.
- Run: Execute the provided Python script to run inference with acceleration. For complete instructions, please refer to the README.
- Support HunyuanVideo
- Support Sparse-VideoGen on HunyuanVideo
- Support Wan2.1 T2V
- Support Wan2.1 I2V
- Support FLUX
We would like to thank the contributors to the Wan2.1, HunyuanVideo, OpenSora, and SVG repositories, for their open research and exploration.
If you find this repository useful in your research, please consider giving a star ⭐ and a citation.
@article{zhou2025easycache,
title={Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching},
author={Zhou, Xin and Liang, Dingkang and Chen, Kaijin and and Feng, Tianrui and Chen, Xiwu and Lin, Hongkai and Ding, Yikang and Tan, Feiyang and Zhao, Hengshuang and Bai, Xiang},
journal={arXiv preprint arXiv:2507.02860},
year={2025}
}