Video Creation by Demonstration

We explore a novel video creation experience, namely Video Creation by Demonstration. Given a demonstration video and a context image from a different scene, we generate a physically plausible video that continues naturally from the context image and carries out the action concepts from the demonstration. To enable this capability, we present \(\delta\)-Diffusion, a self-supervised training approach that learns from unary unlabeled videos by conditional future frame prediction. Unlike most existing video generation controls that are based on explicit signals, we adopts the form of implicit latent control for maximal flexibility and expressiveness required by general videos. By leveraging a video foundation model with an appearance bottleneck design on top, we extract action latents from demonstration videos for conditioning the generation process with minimal appearance leakage. Empirically, \(\delta\)-Diffusion outperforms related baselines in terms of both human preference and large-scale machine evaluations, and demonstrates potentials towards interactive world simulation.

Given one context image, \(\delta\)-Diffusion generates videos with a variety of actions by conditioning on different demonstration videos. The context images are shown and paused initially in the generated videos.

Auto-regressive generation controlled via a sequence of three different demonstration videos of varying lengths. The demonstration videos are placed side-by-side and played sequentially when they are conditioned on for visualization purpose.

Please refer to this page for more qualitative samples, ablation study on the bottleneck design, qualitative comparisons against prior works, and failure cases.