OpenAI recently revealed the existence of its “Sora” AI video generator, which offers hyper-realistic video from a simple text prompt. However, the reception has been mixed.
OpenAI, commonly known as the creators of ChatGPT and DALL:E, has revealed its next project “Sora”, an ultra-realistic AI video generator, bypassing the AI audio toolbox segment. The model can create videos up to one minute long with a simple text prompt.
As shown off on OpenAI’s website, Sora appears to be a powerful generative AI tool, which can create realistic scenes, including people. However, additional examples have also shown that the model is also capable of generating “animated”-looking videos, too.
Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024
OpenAI claims that Sora is capable of generating “complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world.”
The model is not yet accessible to the public, and is instead only open to a select group of “Red team” testers, who will be able to explore and push the guardrails for the AI model, so it does not create content that goes against OpenAI’s guidelines, including “sexual content, hateful imagery, celebrity likeness, or the IP of others”.
The company also claims to have granted access to filmmakers and visual artists to gauge how it would be most useful for creative professionals. OpenAI has not disclosed the training data for the AI model itself, so we do not know where or how the AI model was trained, and if it was trained on content that it does not own.
Subscribe to our newsletter for the latest updates on Esports, Gaming and more.
Experts & directors weigh in on Sora AI
The internet has quickly responded to the new AI model, including YouTuber Marques Brownlee, who stated that “they’re going to have to very careful with this, they’re going to have a bunch of safety stuff to keep in mind, I think they’ll probably have to be more safe than DALL:E. Like, you shouldn’t be able to generate people’s likenesses. ” Brownlee only recently experienced AI chatbots using his name without permission.
He continued: “It is absolutely going to take a dent out of video licensing”, noting that companies selling stock footage could be impacted, as Sora could essentially replace it entirely.
Adam Deats, co-director of Castlevania on Netflix commented on Twitter / X: “I don’t really know what Animation and Film is going to look like in a few years, but this is legitimately horrifying. I don’t know how we’re going to survive this.”
AI is already making a huge difference in the way that millions use tech, with companies like Microsoft embedding AI tools into their OS for everyday use, and with Apple tipped to do the same. If nothing else, AI is being incredibly disruptive to the current tech landscape.