LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

TL;DR

LeMiCa introduces a novel cache scheduling method using lexicographic minimax path optimization to accelerate diffusion-based video generation while maintaining high content consistency and quality.

Contribution

It formulates cache scheduling as a directed graph with error-weighted edges and explicitly bounds worst-case errors, improving global content consistency in accelerated video synthesis.

Findings

2.9x inference speedup on Latte model

LPIPS score of 0.05 on Open-Sora

Minimal perceptual quality degradation

Abstract

We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of global errors, leading to noticeable content degradation between accelerated and original videos. To address this issue, we formulate cache scheduling as a directed graph with error-weighted edges and introduce a Lexicographic Minimax Path Optimization strategy that explicitly bounds the worst-case path error. This approach substantially improves the consistency of global content and style across generated frames. Extensive experiments on multiple text-to-video benchmarks demonstrate that LeMiCa delivers dual improvements in both inference speed and generation quality. Notably, our method achieves a 2.9x speedup on the Latte model and reaches an LPIPS score of 0.05 on Open-Sora, outperforming prior caching techniques. Importantly, these gains come with minimal perceptual quality degradation, making LeMiCa a robust and generalizable paradigm for accelerating diffusion-based video generation. We believe this approach can serve as a strong foundation for future research on efficient and reliable video synthesis. Our code is available at :https://github.com/UnicomAI/LeMiCa