Efficient Video Diffusion Models: Advancements and Challenges

TL;DR

This survey reviews efficient video diffusion models, categorizing methods to reduce inference costs and discussing open challenges for practical deployment.

Contribution

First comprehensive survey organizing existing methods into four paradigms and analyzing their trends for efficient video diffusion.

Findings

Four main paradigms: step distillation, efficient attention, model compression, cache/trajectory optimization.

Analysis of how design choices reduce function evaluations and per-step overhead.

Discussion of open challenges like quality preservation and hardware-software co-design.

Abstract

Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis compounds computation across spatial-temporal token growth and iterative denoising, making attention and memory traffic major bottlenecks in real-world settings. This survey provides a systematic and deployment-oriented review of efficient video diffusion models. We propose a unified categorization that organizes existing methods into four classes of main paradigms, including step distillation, efficient attention, model compression, and cache/trajectory optimization. Building on this categorization, we respectively analyze algorithmic trends of these four paradigms and examine how different design choices target two core objectives: reducing the number of function evaluations and minimizing per-step overhead. Finally, we discuss open challenges and future directions, including quality preservation under composite acceleration, hardware-software co-design, robust real-time long-horizon generation, and open infrastructure for standardized evaluation. To the best of our knowledge, our work is the first comprehensive survey on efficient video diffusion models, offering researchers and engineers a structured overview of the field and its emerging research directions.