OpenAI just dropped an AI bombshell with its up-to-date Sora video generation model.
The text-to-video diffusion model allows you to create minute-long videos that are so realistic that they look real. Reactions to X can be divided into two camps: “Will Sora make video production obsolete?” and “How can I try this?”
The tweet may have been deleted
The answer to the reasonable first question will undoubtedly be a long and arduous fight for artistic rights, requiring regulation at the highest level.
The tweet may have been deleted
The answer to the second question is: you can’t yet.
Although Sora was publicly announced today, OpenAI says it is still in the red-teaming phase. This means that Sora is adversarially tested to ensure that it does not produce harmful or inappropriate content. OpenAI is also providing access to a select group of “visual artists, designers, and filmmakers for feedback on how to improve the model to make it most useful to original professionals.” This is ostensibly intended to give original professionals the ability to employ the technology rather than replace them, but we won’t really know until Sora becomes publicly available and used by companies.
If you want to see Sora demos in action, OpenAI has several on file announcement. CEO Sam Altman also shares videos with tips that X users have requested.
The tweet may have been deleted
The tweet may have been deleted
OpenAI has not provided any timeline for a general release. So unless you’re a member of the red team or one of the original testers, you’ll have to keep placid and settle for the existing demos.
