OpenAI just dropped an AI bombshell with its new video generating model Sora.

The text-to-video diffusion model is capable of minute-long videos that are so realistic, it looks like the real thing. Reactions on X can be divided into two camps: "Is Sora going to make video production obsolete?" and "How can I try it?"

Answering the valid first question will undoubtedly be a long arduous battle for artistic rights, involving regulation at the highest level.

The answer to the second question is, you can't yet.

While Sora was publicly announced today, OpenAI says it's still in red-teaming phase. That means Sora is being adversarially tested to make sure it doesn't produce harmful or inappropriate content. OpenAI is also granting access to a select group of "visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals." This is ostensibly to ensure creative professionals can benefit from the technology, rather than be replaced by it, but we won't really know until Sora becomes publicly available and leveraged by businesses.

OpenAI hasn't shared any timeline on a widespread release. So unless you're a red-teamer or one of the creative testers, you'll have to sit tight and make do with the existing demos.