'Future is wild': Netizens react to OpenAI's newly launched Sora that creates HD videos from written text

OpenAI, the parent company of ChatGPT launched its new AI tool, Sora, which converts user texts into videos. The new app can generate videos up to a minute in length, based on prompts given to its system. The application was launched on Thursday.

In its blog post, OpenAI said Sora is an attempt to teach AI to “understand and simulate the physical in motion”.

While text-to-video is not a new concept in the field of deep learning, and there are already big players in the market like MidJourney and CapCut, OpenAI’s new launch might overtake this storm soon. Videos shared on its blog post show that Sora is different from other players, as it produces high-quality (HD) videos within minutes that look very close to real ones.

Also Read |Taste of your favourite tea may be dependent on specific microbes

One video on the blog post based on “Prompt: A movie trailer featuring the adventures of the 30-year-old spaceman wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, vivid colours”, looks straight out of some Hollywood sci-fi movie, almost making it impossible to detect whether it's real or completely AI-generated.

As of now, Sora can only be accessed by a few researchers and video creators, the company said Thursday. The experts would “red team” the product – test it for susceptibility to skirt OpenAI’s terms of service, which prohibit “extreme violence, sexual content, hateful imagery, celebrity likeness, or the IP of others”, per the company’s blog post.

Also Read |A man found a bone while walking his dog. What he discovered next was unbelievable

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

Sam Altman, the CEO of OpenAI, also shared a video rendered by Sora based on the prompt of an X user. The prompt was,

“Two golden retrievers podcasting on top of a mountain,” and this was the result.

https://t.co/uCuhUPv51N pic.twitter.com/nej4TIwgaP — Sam Altman (@sama) February 15, 2024

OpenAI did not disclose how much footage was used to train Sora or where the training videos may have originated, other than telling the New York Times that the corpus contained videos that were both publicly available and licensed from copyright owners.

Netizens react to OpenAI’s Sora

The launch of Sora caused a frenzy among netizens about how clear HD-quality videos it can create with a precision that almost looks real, with people asking on X, “Is this real?” and “So what even is real.”

One X user wrote, “'Is this real'question will pop up more than we imagine from now on.” Another wrote on Sam Altman’s feed, “Sam please don’t make me homeless”.

Another said, “The future is wild”, and someone asked, “Why? Why why why does the world need this.”

Apart from generating videos from text prompts, Sora can animate a still image, the company said in a blog post.

(With inputs from agencies)