Summary of Fast and Memory-efficient Video Diffusion Using Streamlined Inference, by Zheng Zhan et al.
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
by Zheng Zhan, Yushu Wu, Yifan Gong, Zichong Meng, Zhenglun Kong, Changdi Yang, Geng Yuan, Pu Zhao, Wei Niu, Yanzhi Wang
First submitted to arxiv on: 2 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The rapid progress in artificial intelligence-generated content (AIGC) has significantly advanced video generation. However, current models exhibit demanding computational requirements and high peak memory usage, especially for generating longer and higher-resolution videos. To address this issue, we present a novel training-free framework named Streamlined Inference, which leverages temporal and spatial properties of video diffusion models. Our approach integrates Feature Slicer, Operator Grouping, and Step Rehash to reduce memory usage without sacrificing quality or speed. Extensive experiments demonstrate that our approach significantly reduces peak memory and computational overhead, making it feasible to generate high-quality videos on a single consumer GPU (e.g., reducing peak memory of AnimateDiff from 42GB to 11GB). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Video generation has become more realistic with AI-generated content. But current models need powerful computers to work efficiently. Our new approach makes video generation faster and uses less memory, so it’s possible on regular computers or even smartphones. |
Keywords
» Artificial intelligence » Inference
