One of the most highly-anticipated AI-related products has just arrived: OpenAI's AI video generator Sora launchedon Monday as part of the company's 12 Days of OpenAIevent.
OpenAI has provided sneak peeks at Sora's output in the past. But,Sister how different is it at launch? OpenAI has certainly been hard at work to update and improve its AI video generator in preparation for its public launch.
YouTuber Marques Brownlee had a first look at Sora, releasing his video review of the latest OpenAI product hours before OpenAI even officially announced the launch. What did Brownlee think?
According to Brownlee, his Sora testing found that the AI video generator excels at creating landscapes. AI generated overhead, drone-like shots of nature or famous landscapes look just like real-life stock footage. Of course, as Brownlee points out, if you are specifically well-versed in how the surroundings of a landmark look, one might be able to spot the differences. However, there's not too much that looks distinctly AI-generated in these types of Sora-created clips.
SEE ALSO: How to try OpenAI's Sora right nowPerhaps the type of video Sora is best able to create, according to Brownlee, are abstract videos. Background or screensaver type abstract art can be made quite well by Sora even with specific instructions.
Brownlee also found that Sora-generated certain types of animated content, like stop-motion or claymation type animation, look passable at times as the sometimes jerky movements that still plague AI video look like stylistic choices.
SEE ALSO: 7 wild Sora videos blowing up social media after its launchMost surprisingly, Brownlee found that Sora was able to handle very specific animated text visuals. Words often show up as garbled text in other AI image and video generation models. With Sora, Brownlee found that as long as the text was specific, say a few words on title card, Sora was able to generate the visual with correct spelling.
Sora, however, still presents many of the same problems that all AI video generators that came before it have struggled with.
SEE ALSO: OpenAI's Sora is officially hereThe first thing Brownlee mentions is object permanence. Sora has issues with displaying, say, a specific object in an individual's hand throughout the runtime of the video. Sometimes the object will move or just suddenly disappear. Just like with AI text, Sora's AI video suffers from hallucinations.
Which brings Brownlee to Sora's biggest problem: Physics in general. Photorealistic video seems to be quite challenging for Sora because it can't just seem to get movement down right. A person simply walking will start slowing down or speeding up in unnatural ways. Body parts or objects will suddenly warp into something completely different at times as well.
And, while Brownlee did mention those improvements with text, unless you are getting very specific, Sora still garbles the spelling of any sort of background text like you might see on buildings or street signs.
Sora is very much an ongoing work, as OpenAI shared during the launch. While it may offer a step up from other AI video generators, it's clear that there are just some areas where all AI video models are going to find challenging.
Topics Artificial Intelligence OpenAI
Robinhood now says you can buy one GameStop share, as a treatDisney+ greenlights Wakanda series from Ryan CooglerJeff Bezos as Amazon scandals, a thread12 best TV and movie recipes from 'Binging with Babish'Mariah Carey already has her Christmas tree upThe internet tricked me into believing I can multitaskMariah Carey already has her Christmas tree upDad finds out the hard way to not swear in front of his toddlerHere's what Donald Trump had to say in response to the Las VegasTom Price criticized 'reckless government spending'Facebook and Apple's PR war seriously heats up'Passing' is a riveting exploration of identity: Movie reviewHere's how to transfer stocks out of your Robinhood accountThe internet tricked me into believing I can multitaskWhatsApp is using Status to make users feel better about privacyNetflix's 'Spycraft' takes an uncomplicated look at complex issuesThe internet tricked me into believing I can multitask'A Glitch in the Matrix' digs into simulation theory: Movie reviewHow to unlock your iPhone with Face ID while wearing a face maskArmy vet who knelt before Trump shares why, you know, protests are important CNN plans to fly drones over crowds to capture news from above Typhoon Lan poised to become a giant super typhoon, take aim at Japan Newspapers 'slut New York and Las Vegas cabs start accepting China's biggest mobile payment mode Diana Ross is adding another illustrious award to her long list Nude app hides your dick pics, but it still has kinks 2017 will be one of Earth's 3 warmest years on record, scientists say Tom Jones speaks about his own experience of sexual harassment Google Calendar for web just got a pretty new update Rose Leslie forced Kit Harington to wear a spectacularly embarrassing Halloween costume Alphabet's Sidewalk Labs to build futuristic community in Toronto What the inside of Google's Pixel 2 XL looks like, including those weird squeeze sensors Mashable got a peek inside Google's New York City pop Obsessively checking social media during a crisis might harm your mental health Ron Howard announces Han Solo movie title Restaurant slammed on Yelp after getting called out for selling Popeyes chicken Chelsea Handler won't do another season of her Netflix show so she can focus on activism The next big Star Wars game is in trouble One man, a 300 Photographer creates a 'dudeoir' photoshoot to perfectly capture the essence of autumn