Sora AI unleashes new demo videos, equally amazing

Readers help support Windows Report. When you make a purchase using links on our site, we may earn an affiliate commission.

Tooltip Icon

Read the affiliate disclosure page to find out how can you help Windows Report effortlessly and without spending any money. Read more

Recently, we have told you a few things about a new text-to-video tool called Sora AI, and why it will change the ad and video industry as a whole.

While it’s still in the testing phase, Open AI released a lot more demo videos that are equally amazing, showing the new LLM capabilities.

The new Sora AI clips are breathtaking

In the clip above, you will see only a few examples collaged by AI-nstein, but there are a lot more featured on the Open AI’s Sora webpage you can browse and watch.

It’s pretty hard to talk about all of them, but as you can see, the AI bot managed to recreate the image of the world globe into a virtual character’s eye and it has drawn a very realistic alien roaming through New York as it belonged there.

But that’s not all. Sora AI can combine cartoon charters and blend them into realistic representations and depict virtual animals playing and acting.

The text-to-video bot still has weaknesses. Some, as described by the Open AI team, are the difficulty of getting the right spatial details, mixing directions and following the camera path:

The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory.

Open AI

As there is a lot of fuss nowadays about the legitimacy of AI-generated content, the Sora AI team wants to include C2PA metadata in the clips to prevent misleading these videos with actual real footage, or to prevent any inappropriate prompts:

Once in an OpenAI product, our text classifier will check and reject text input prompts that are in violation of our usage policies, like those that request extreme violence, sexual content, hateful imagery, celebrity likeness, or the IP of others. We’ve also developed robust image classifiers that are used to review the frames of every video generated to help ensure that it adheres to our usage policies, before it’s shown to the user.

Open AI

Besides that, the new Sora AI demo clips are amazing and show a promising future for video-generated content. However, this might be bad news if you’re working in the film industry.

What do you think about Sora AI? Share your thoughts in the comments section below.

More Reading

Post navigation

Leave a Comment

Leave a Reply

Your email address will not be published. Required fields are marked *