Photorealistic Video Generation with Diffusion Models

Agrim, Lijun Yu, Kihyuk Sohn, Xiuye Gu, Meera Hahn, Dr Fei-Fei Li, Irfan Essa, Lu Jiang, José Lezama

Photorealistic Video Generation with Diffusion Models: 24 upvotes on Hugging Face Daily Papers, #3 of 14 papers on 2023-12-12. Day-by-day upvote history.

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 times 896 resolution at 8 frames per second.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.