> For the complete documentation index, see [llms.txt](https://metaverse-imagen.gitbook.io/ai-tools-research/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metaverse-imagen.gitbook.io/ai-tools-research/ai-tools-main-categories/video-and-animation/video-synthesis-generation/sora-openai/sora-technical-explanation.md).

# SORA Technical Explanation

## Video generation models as world simulators

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

{% embed url="<https://openai.com/research/video-generation-models-as-world-simulators>" %}