The new AI video model, called Kling, seems to offer many of the same features that made OpenAI's Sora stand out when it was first announced earlier this year

Built by Chinese video platform company Kuaishou, its features include longer video generation, improved movement, better prompt follow and multi-shot sequence Unlike Sora, it seems that Kling is already available to users through a waiting list for cancellation 

OpenAI announced Sora in May and we are starting to see an increase in creators using it, including five award-winning filmmakers set to premiere shorts made by Sora at the Tribeca Film Festival next week Nevertheless, it is still not widely available to the public

Among the clips shared from Kling, I've seen long clips of photorealistic videos of a boy riding a bike, a horse in the desert, a man eating noodles and a boy enjoying a burger

According to Kuaishou Kling, it can generate up to two minutes of video from a single prompt at 30p at 1080 frames per second It can also "accurately simulate real-world physics," which most AI models struggle with

It is the same diffusion transformer model as Sora and uses its own model that can support aspect ratios and range of shot types

In addition to the generation feature, Kling explained on its website that advanced 3D face and body reconstruction is possible to improve full representation and limb movement in the video

What we don't know yet is whether Kling, or even other big Chinese AI video model Vidu, will be released outside China It may be the grace of OpenAI's salvation in the West

The most striking part of the video is photorealism Some clips suffer from similar blurring seen in other AI videos, but not on the same scale 

There are 1 clip of parrots that you struggle to say are not real, and we still don't know if they're not faking the burger video

One type of video I've played many times is to pour liquid— the most struggle, but Kling seemed to get it right, at least in one demo of milk getting into a glass of coffee

Overall, Kling seems to have the ability to create precise movements, better model real-world movements and physics, and create realistic depictions of the world

Competition is good for creativity and innovation, so we hope the company will consider a broader release and make it available outside of China By releasing it, we hope that OpenAI will release Sora sooner than it is currently planned

OpenAI is also facing competition from existing players like Runway and Pika Labs, both of which are enhancing the game Newcomers such as Haiper, LTX Studio and Higgsfield have also taken different approaches to AI video, and Google has a new Veo model

The reality is that OpenAI delays are 1 of safety rather than 1 of technical availability The company says it wants to ensure that the model can not be used for false information or malicious purposes before it is available to the public They also need to make it faster and cheaper