Openai explore large-scale training of generative models on video data. Specifically, Openai train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. Openai leverage a transformer architecture that operates on spacetime patches of video and image latent codes. The largest model, Sora, is capable of generating a minute of high fidelity video. Their results suggest that scaling video generation models is a promising path towards building general purpose simulators of the physical world.