This technical report focuses on (1) our methodology for turning visible knowledge of every kind right into a unified illustration that allows large-scale coaching of generative fashions, and (2) qualitative analysis of Sora’s capabilities and limitations. Mannequin and implementation particulars should not included on this report.
A lot prior work has studied generative modeling of video knowledge utilizing quite a lot of strategies, together with recurrent networks,[^1][^2][^3] generative adversarial networks,[^4][^5][^6][^7] autoregressive transformers,[^8][^9] and diffusion fashions.[^10][^11][^12] These works typically deal with a slim class of visible knowledge, on shorter movies, or on movies of a set dimension. Sora is a generalist mannequin of visible knowledge—it will probably generate movies and pictures spanning numerous durations, facet ratios and resolutions, as much as a full minute of excessive definition video.