OpenAI’s new text-to-video model will melt your brain

Just a heads up, if you buy something through our links, we may get a small share of the sale. It’s one of the ways we keep the lights on here. Click here for more.

OpenAI, maker of ChatGPT, is kicking things up a notch with the introduction of Sora, a generative AI that transforms written AI prompts into ridiculously life-like videos.

Sora’s not just another tool in the shed. We’re talking about a video generation model that makes videos straight out of your imagination.

According to an OpenAI blog post, Sora can create detailed scenes with many characters, accurate movements, and realistic depictions of both the subject and background.

In simpler words, it can pretty much do whatever you prompt it to do.

Additionally, the model can understand objects and props to create vivid characters with different emotions. Here, take a look for yourself:

So, you write down what you’re picturing, and Sora turns those words into a video that looks just like the real thing

Still not convinced? Check out this video below, prompted by a single sentence: “Tour of an art gallery with many beautiful works of art in different styles.”

But hey, no invention’s perfect right out of the gate. According to TechCrunch, Sora’s got a couple of kinks to iron out, like getting physics right and keeping things spatially accurate.

But OpenAI isn’t throwing in the towel. They’re already chasing after fixes, including tools to spot Sora-made content, keeping an eye out for folks who might want to misuse it.

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.

So, what’s the big picture here? OpenAI diving into video magic with Sora speaks volumes. And with footage like this, it looks like they’re only scratching the surface of what its AI can do.

The distinction between reality and AI-generated content continues to blur, raising questions about what lies ahead in this ever-evolving landscape.

Have any thoughts on this? Drop us a line below in the comments, or carry the discussion to our Twitter or Facebook.

Editors’ Recommendations:

• OpenAI rumored to be developing a search engine with Microsoft Bing
• OpenAI addresses ChatGPT account security breach
• New York Times sues Microsoft and OpenAI over AI training data
• Dropbox unveils features that shares your data with OpenAI

Kevin Raposo

Kevin is KnowTechie's founder and executive editor. With over 15 years of blogging experience in the tech industry, Kevin has transformed what was once a passion project into a full-blown tech news publication. Shoot him an email at kevin@knowtechie.com or find him on Mastodon or Post.