Sora AI is a new development in AI technology, able to create imaginative videos straight from a text description, described as a text-to-video model. It is created by OpenAI, the same company that created the extensive model that is ChatGPT. This model utilizes natural language processing (NLP) and computer vision techniques to understand and interpret textual descriptions and then generate corresponding visual content. In other words, Sora AI is able to generate videos based on descriptive prompts given by the user. These prompts are able to be developed from still images, and extending existing videos forwards and backwards in time. Sora is currently able to create videos up to a minute long. It is not available to the public as of yet, and only available to the team researchers, referred to as “red teamers” who are still developing the platform and testing for bugs or any danger that the platform could potentially cause.
The video below is an example of a Sora AI video that was generated and shown directly on their website. The prompt that created this video was “a close up view of a glass sphere that has a zen garden within it. There is a small dwarf in the sphere who is raking the zen garden and creating patterns in the sand.”