OpenAI has recently unveiled a music video generated by Sora — and it feels reminiscent of a feverish dream.

The most recent Sora release from OpenAI is a music video that aims to depict the mental imagery that the musician had while writing the song.

Only a few people have used Sora, an artificial intelligence video generator, to produce content thus far. Sora can make multi-shot films lasting up to a minute, all from a text prompt. This year, OpenAI is gradually releasing its security updates.

August Kamp is a musician, researcher, and creative activist who is among the artists who were granted early access to Sora. According to her, Sora marks a "turning point" for artists because it implies that the only thing limiting pictures is the imagination of the human mind.

OpenAI has recently unveiled a music video generated by Sora — and it feels reminiscent of a feverish dream.
Sora AI

"August—we can share these with people," I said, pulling out some photos that I've had stashed away [in my memory] for the past two years. That, in my opinion, makes this gadget unique, the woman remarked.

What is the new Sora video like?

No detailed information about the prompts used to construct the video or the number of clips needed to make the entire two minutes and 19 seconds is available.

Other video systems can produce up to 12 seconds when using extensions, and up to three seconds for a single clip. However, they have trouble maintaining consistency after the first five seconds.

That all changes with Sora, who is able to produce significantly longer video that frequently contain numerous coherent shots. It appears that there are multiple 2-3 shot clips in this instance. 

The brand-new video, titled "Worldweight," transports you through a soggy mind like a fever dream. The dreamy soundtrack evokes the feeling of being in front of a bus shelter on a moonlit, deserted street as it pours rain outside.

Regarding the music, Kamp remarked, "It seems like my whole heart and soul. Nearly two years ago, these notes fell through my fingertips and into the keys of my synthesizer. I still remember how it felt," the woman remarked. "I remember how I felt so lucky to be able to pour these feelings into a song — something that could hold onto them so I didn't have to anymore," the speaker continued as it rained outside.

When will the general public be able to access Sora?

Mira Murati, CTO of OpenAI, made a clue about Sora's release this year. In addition, CEO Sam Altman stated that the company will release several new models this year, however he made no mention of Sora.

As other models begin to catch up, features are being added to enhance the usability of models from firms such as Runway, Pika Labs, and Viggle. Even Midjourney is developing a video artificial intelligence model that may be made available this year.

Given everything, I believe there's a good chance Sora will be released to the public in stages before the year is over. Opening it to well-known creatives might be the first step; after all, OpenAI appears to be actively pursuing Hollywood — but safety is the most important consideration.

OpenAI has said it won’t release any model that could cause undue impact on the upcoming global elections at the end of this year, so if the company can’t tackle the misinformation risks caused by such a powerful video model before November — the release may be delayed.

Which is a shame as it sounds like Sora could bring new ways of making visual content. Kamp wrote: “Being able to build and iterate on cinematic visuals this intuitively has opened up categorically new lanes of artistry to me...I truly cannot wait to see what other forms of storytelling will come into reach with the future of these tools."

Post a Comment

Previous Post Next Post