FasterVD: On Acceleration of Video Diffusion Models

FasterVD: On Acceleration of Video Diffusion Models

Pinrui Yu, Dan Luo, Timothy Rupprecht, Lei Lu, Zhenglun Kong, Pu Zhao, Yanyu Li, Octavia Camps, Xue Lin, Yanzhi Wang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Demo Track. Pages 8838-8842. https://doi.org/10.24963/ijcai.2024/1044

Equipped with Denoising Diffusion Probabilistic Models, video content generation has gained significant research interest recently. However, diffusion pipelines call for intensive computation and model storage, which poses challenges for their wide and efficient deployment. In this work, we address this issue by integrating LCM-LoRA to reduce the denoising steps and escalating the video generation process by frame skipping and interpolation. Our framework achieves an approximately 10× inference acceleration for high-quality realistic video generation on commonly available GPUs.
Keywords:
Machine Learning: ML: Optimization
Machine Learning: ML: Applications