RESEARCH PAPER

Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Andreas Blattmann; Tim Dockhorn; Sumith Kulal; Daniel Mendelevitch; Maciej Kilian; Dominik Lorenz; Yam Levi; Zion English; Vikram Voleti; Adam Letts; Varun Jampani; Robin Rombach

Classification

View four quadrants
Major category
Components of WAMs
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. Stable Video Diffusion is a general pretrained video-generation backbone that extends latent image diffusion with temporal layers and staged video training. It supplies reusable visual dynamics priors for downstream robot simulators/policies rather than constituting those task-specific systems. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX