Over the weekend, a video appeared on X that claimed to include footage from Sora v2, a new version of the yet-to-be-released AI video model from OpenAI.
OpenAI first unveiled Sora earlier this year to much fanfare. At a time when the best AI video models generated 3-5 seconds of footage that just resembled real movement, Sora offered near-photorealistic footage of up to a minute long.
Ruud van der Linden, CEO of LontVideo, shared a slightly shaky video showing a projected film. At first glance, it looks like footage from a Viking movie, but in reality, it is output from the next-generation version of Sora.
This footage, apparently generated by creating images in Midjourney and then using them as an initial prompt in Sora v2, was shown during a keynote at C21Media Keynote by OpenAI's Chad Nelson in London.
What we don't know yet is whether this new Sora model will be released at some point during the 12 Days of OpenAI event, or if this is a "future version," reserved for filmmakers and industry insiders (much like v1 currently is).
Sora v2 release is impending:* 1-minute video outputs* text-to-video* text+image-to-video* text+video-to-videoOpenAI's Chad Nelson showed this at the C21Media Keynote in London. And he said we will see it very very soon, as @sama has foreshadowed. pic.twitter.com/xZiDaydoDVDecember 7, 2024
According to van der Lindon, Sora v2 will come with one-minute video output, text-to-video, image, and video-to-video modes — and "we will see it very soon".
Chinese models such as Kling and Hailuo MiniMax are already achieving levels of output similar to those we saw in the first version of Sora at the start of this year. Runway, Luma Labs Dream Machine, and Pika are also at a similar level.
Even open-source models such as Mochi-1 and Tencent's Hunyuan aren't far behind Sora in terms of motion and visual realism. We saw during the recent Sora leak that footage has some of the same issues faced by the current leading models.
While I can't tell whether what we saw during the leak is what we might get this week or if it will be closer to the footage seen in Sora v2, it is clear we will get some form of AI video release from OpenAI during its 12 Days.
My prediction is we'll get something like Sora v1, with shorter initial videos and lower resolution in the $20 per month plan, and Sora v2 will be announced but not released. And, when it is released, it will be in the $200 per month ChatGPT Pro.
