The text-to-video model can generate videos up to a minute long while maintaining visual quality, and adhering to the user’s prompt.
OpenAI said the model has a deep understanding of language, “enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions”.
OpenAI said it is granting access to several visual artists, designers and filmmakers to gain feedback on how to advance the model, so it becomes helpful to creative professionals.
Reaction to the product from the tech space has been largely positive, however those outside of the space have voiced concerns.
Concerns
Yet again, though, concerns surrounding the advancement of AI have been raised.
Steven Bartlett, host of The Diary Of A CEO revealed his thoughts about Sora on LinkedIn, labelling it as a “complete paradigm shift”.
“My companies are already saving weeks of time and thousands of pounds by using AI tools, instead of hiring, and these tools are in their infancy,” he wrote.
“To understand an unclear future, sometimes we have to look to the past, and the past tells us that the people, teams, and companies that fully understand the magnitude of this shift and take it seriously will likely be those that sail away on the lifeboats.”
OpenAI said it is taking several important safety steps ahead of making Sora available in OpenAI’s products.
“We are working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who will be adversarially testing the model,” the company writes on its website.
We’re also building tools to help detect misleading content such as a detection classifier that can tell when a video was generated by Sora. We plan to include C2PA metadata in the future if we deploy the model in an OpenAI product.
