“Introducing Sora, our text-to-video model.”
OpenAI, the creator of ChatGPT, have introduced their next leap into artificial intelligence by launching Sora, a brand-new text-to-video model.
Sora has “a deep understanding of language” and can create “compelling characters that express vibrant emotions,” OpenAI said in a blog post on Thursday.
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W
Prompt: “Beautiful, snowy… pic.twitter.com/ruTEWn87vf
— OpenAI (@OpenAI) February 15, 2024
Sora is not the first of its kind. Google, Meta and the startup Runaway ML are among many other companies who have demonstrated similar technology. However, the high quality of videos displayed by OpenAI, after CEO Sam Altman asked social media users to send in ideas for some written prompts, stunned viewers and surpassed all expectations.
Prompt: “Animated scene features a close-up of a short fluffy monster kneeling beside a melting red candle. the art style is 3d and realistic, with a focus on lighting and texture. the mood of the painting is one of wonder and curiosity, as the monster gazes at the flame with… pic.twitter.com/aLMgJPI0y6
— OpenAI (@OpenAI) February 15, 2024
However, OpenAI has also warned users of Sora’s potential weaknesses: “It may struggle with accurately simulating the physics of a complex scene, and may not understand specific instances of cause and effect. For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark. The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory.”
Sora is not publicly available yet and OpenAI has revealed very limited information about how it was built. Furthermore, it hasn’t disclosed what image and video sources were used to train Sora, despite the fact that the company has been sued by authors and the New York Times over its use of copyrighted works of writing in order to train ChatGPT.
OpenAI has revealed in their blog post that they are engaging with policymakers and artists before releasing the tool to the public. “We are working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who will be adversarially testing the model. 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.”
While many users are elated and congratulatory about this launch, Sora’s introduction has also raised growing concerns about the ethical and societal implications of such a tool, and has intensified worries about the potentially detrimental long-term effects of expanding AI, including plagiarism, exploitation and a loss of jobs.
Find out more on Sora here.
Leave feedback about this