According to a blog post published by OpenAI on Thursday, the text-to-video model, known as Sora, can create “compelling characters that express vibrant emotions” and has “a deep understanding of language.”
OpenAI SORA: AI Video Generator
The minute-long films produced by the text-to-video diffusion model are so lifelike that they appear authentic. “Is Sora going to make video production obsolete?” and “How can I try it?” are the two main reactions on X.
It will surely take a lengthy, hard fight for creative rights and top-level regulation to address the legitimate first question.
Despite being made public today, OpenAI claims that Sora is still in the red-teaming stage. In other words, Sora is undergoing adversarial testing to ensure that it doesn’t generate offensive or dangerous stuff. A limited set of “visual artists, designers, and filmmakers” will also get access to the model thanks to OpenAI’s decision to “gain feedback on how to advance the model to be most helpful for creative professionals.” Presumably, this is to make sure creative workers can take advantage of the technology instead of having it replace them, but we won’t truly know until Sora is made accessible to the general public and is used by companies.
OpenAI offers numerous Sora demonstrations in the announcement if you’d want to watch them in action. Additionally, CEO Sam Altman has begun posting videos of user-requested questions on X.
No release schedule for a broader distribution has been disclosed by OpenAI. Thus, you’ll have to wait it out and settle for the current demonstrations unless you’re a creative tester or a member of the red team.
Ted Underwood, an information science professor at the University of Illinois at Urbana-Champaign, stated, “I didn’t expect this level of sustained, coherent video generation for another two to three years.” Though he issued a warning, pointing out that OpenAI most likely selected films that best illustrate the model, he said that “there seems to have been a bit of a jump in capacity” from previous text-to-video tools.
Even though he is incarcerated, former Pakistani prime leader Imran Khan has using artificial intelligence to produce a digital replica of himself making talks. An AI audio generator was used to simulate the voice of former president Donald Trump in an advertisement for Florida Governor Ron DeSantis’s now-defunct candidacy as the Republican contender for president.