[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
June 11, 2026 · View on GitHub
📚English | 📚中文阅读 | 机器之心 | 百度文心
[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
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）
https://github.com/user-attachments/assets/ebed2e0f-87f4-408e-98e3-93bd29bbc99f
I2V 720P (Up to a 3.88× speedup）
https://github.com/user-attachments/assets/d1a83d45-579f-4174-9477-ba0b9aebb322
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
https://github.com/user-attachments/assets/3d99b959-7253-47ec-af0a-da13a66e6d49
Open-Sora
Click to expand Open-Sora example
https://github.com/user-attachments/assets/ba205856-2d77-494a-aaa9-09189ba2915c
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
Text-to-Image
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}
}