Sora is currently in the testing phase with selected artists and security testers, and there is anticipation for a public release by the end of February 2024. However, OpenAI has not confirmed a specific release date...
Developed by OpenAI, Sora is an advanced AI model designed to generate realistic and creative videos based on textual descriptions. It stands out for its ability to create videos with intricate details, dynamic camera movements, and expressive characters.
As of now, Sora's access is limited to a select group of video creators, artists, and security testers. It remains unavailable for general public use.
Sora can produce videos lasting up to 60 seconds, incorporating detailed scenes, sophisticated camera transitions, and multiple characters showing a range of emotions. Employing a diffusion transformer architecture, Sora aims to replicate and interpret motion within the physical world. Despite its advanced features, the model faces challenges in simulating complex physics accurately and in understanding specific cause-and-effect scenarios.
The details regarding the public release, including pricing and licensing of Sora, have yet to be announced by OpenAI.
Sora encapsulates the essence of "60-second video creation," "multi-angle shots," and "dynamic world modeling."