English

Photorealistic Video Generation with Diffusion Models

Computer Vision and Pattern Recognition 2023-12-12 v1 Artificial Intelligence Machine Learning

Abstract

We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of 512×896512 \times 896 resolution at 88 frames per second.

Keywords

Cite

@article{arxiv.2312.06662,
  title  = {Photorealistic Video Generation with Diffusion Models},
  author = {Agrim Gupta and Lijun Yu and Kihyuk Sohn and Xiuye Gu and Meera Hahn and Li Fei-Fei and Irfan Essa and Lu Jiang and José Lezama},
  journal= {arXiv preprint arXiv:2312.06662},
  year   = {2023}
}

Comments

Project website https://walt-video-diffusion.github.io/

R2 v1 2026-06-28T13:47:31.230Z