📚English | 📚中文阅读   |   机器之心

[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

Huanlin Gao^1,2*,  Ping Chen^1,2*,  Fuyuan Shi^1,2,  Chao Tan^1,2,  Zhaoxiang Liu^1,2
Fang Zhao^1,2†,  Kai Wang^1,2,  Shiguo Lian^1,2†

¹Data Science & Artificial Intelligence Research Institute, China Unicom,  ²Unicom Data Intelligence, China Unicom

(* Equal contribution. † Corresponding author.)

Introduction

LeMiCa is a training-free acceleration framework for diffusion-based video generation (and extendable to image generation). Instead of using local heuristic thresholds, LeMiCa formulates cache scheduling as a global path optimization problem with error-weighted edges and introduces a Lexicographic Minimax strategy to bound the worst-case global error. This global planning improves both inference speed and consistency across frames. For more details and visual results, please visit our project page.

🔥 Latest News

• [2026/04/16] ✨ Support ERNIE-Image text-to-image acceleration with LeMiCa.
• [2026/01/29] 🔥 Our latest work "MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference" is accepted by ICLR 2026! Codes are available at MeanCache! MeanCache achieves 4.12×, 4.56×, and 3.59× acceleration on FLUX.1, Qwen-Image, and HunyuanVideo, while consistently outperforming state-of-the-art caching baselines in generation quality. For more details, please refer to our latest research paper.
• [2026/01/20] 🔥 Added support for FLUX.1-dev and FLUX.2-Klein in LeMiCa4FLUX
• [2025/12/15] ✨ ComfyUI-LeMiCa has been seamlessly integrated into ComfyUI and is fully compatible with ComfyUI’s native nodes.
• [2025/12/08] ✨ Support HunyuanVideo-1.5 for both T2V and I2V.
• [2025/12/02] ✨ Support Z-Image and FLUX.2.
• [2025/11/14] ⭐ We have open-sourced Awesome-Acceleration-GenAI, collecting the latest generation acceleration techniques. Feel free to check it out !
• [2025/11/13] ✨ Support Wan2.1 for both T2V and I2V.
• [2025/11/07] ✨ Support Qwen-Image and Inference Code Released !
• [2025/10/29] 🚀 Code will be released soon !
• [2025/09/18] ✨ Selected as a NeurIPS 2025 Spotlight paper.
• [2025/09/18] ✨ Initial public release of LeMiCa.

Demo

ComfyUI-LeMiCa

ERNIE-Image

Method	ERNIE-Image	LeMiCa-slow	LeMiCa-medium	LeMiCa-fast
Latency	32.168 s	16.471 s	11.432 s	7.043 s
T2I

FLUX.2 [Klein-9B]

Method	Flux.2(klein-9B)	LeMiCa-slow	LeMiCa-medium	LeMiCa-fast	LeMiCa-ultra
Latency	20.04 s	10.77 s	8.45 s	6.54 s	4.59 s
T2I

Qwen-Image-2512

Method	Qwen-Image-2512	LeMiCa-slow	LeMiCa-medium	LeMiCa-fast
Latency	32.8 s	18.83 s	14.35 s	10.41 s
T2I

HunyuanVideo1.5

T2V 720P (Up to a 2.86× speedup）

HunyuanVideo1.5_T2V_720P.mp4

I2V 720P (Up to a 3.88× speedup）

HunyuanVideo1.5_I2V_720P.mp4

FLUX.2

Method	Flux.2(cpu-offload)	Flux.2	LeMiCa-slow	LeMiCa-medium	LeMiCa-fast
Latency	101.2 s	32.70 s	13.41 s	10.20 s	6.99 s
T2I

Z-Image

Method	Z-Image	LeMiCa-slow	LeMiCa-medium	LeMiCa-fast
Latency	2.55 s	2.19 s	1.94 s	1.78 s
T2I

Wan2.1

Wan2.1_I2V_14B_832_480.mp4

Open-Sora

Click to expand Open-Sora example

opensora_grid_5x5_with_header_bold.mp4

Qwen-Image

Click to expand Qwen-Image example

Supported Models

LeMiCa currently supports and has been tested on the following diffusion-based models:

Text-to-Video

• Open-Sora
• Latte
• CogVideoX 1.5
• Wan2.1
• HunyuanVideo-1.5

Text-to-Image

• ERNIE-Image
• Qwen-Image
• Z-Image
• FLUX.2

ToDo List

• 🗹 Public Project Page
• 🗹 Paper Released
• 🗹 Text-to-Image Forward Inference
• 🗹 Text-to-Video Forward Inference
• ☐ DAG Construction Code
• ☐ Support Acceleration Framework

Community Contributions & Friendly Links

• Qwen-Image and CogVideo featured LeMiCa on their project homepages.

• Cache-DiT A unified and flexible inference engine for DiTs, integrating and applying LeMiCa’s core insights. Welcome to try and explore. Details

• ComfyUI-LeMiCa now includes Z-Image nodes. Thanks @scruffynerf.

Acknowledgement

This repository is built based on or inspired by the following open-source projects: Diffusers, TeaCache, VideoSys. We sincerely thank these communities for their open contributions and inspiration.

License

The majority of this project is released under the Apache 2.0 license as found in the LICENSE file.

📖 Citation

If you find LeMiCa useful in your research or applications, please consider giving us a star ⭐ and citing it by the following BibTeX entry:

@inproceedings{gao2025lemica,
  title     = {LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation},
  author    = {Huanlin Gao and Ping Chen and Fuyuan Shi and Chao Tan and Zhaoxiang Liu and Fang Zhao and Kai Wang and Shiguo Lian},
  journal   = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2025},
  url       = {https://arxiv.org/abs/2511.00090}
}

⭐ Star History