I've to go lie down...
Sora: Creating video from text
411–420 of 1001 posts
Re: Sora: Creating video from text
#412Does anyone know how to handle the depression/doom one feels with these updates? Yes, it's a great technical achievement, but I just worry for the future. We don't have good social safety nets, and we aren't close to UBI. It's difficult for me to see that happen unless something drastic changes. I'm also afraid of one company just having so much power. How does anyone compete?
some light alcohol, relaxing and remembering life is beautiful
Re: Sora: Creating video from text
#413Absolutely unreal. Kinda funny how some people are complaining about minor glitches or motion sickness when this is the most impressive piece of technology I've seen. Way to go, OpenAI.
Re: Sora: Creating video from text
#414This is all very impressive. I can't help to wonder though. How is text-to-video going to benefit humanity? That's what OpenAI is supposedly about, right? We'll get some groundbreaking film content out of this in the hands of a few talented creatives, and a vast ocean of mediocre content from the hands of talentless people who know how to type. What's the benefit to humanity, concretely?
For models to interact with real-world objects, they first need to understand those objects. These videos demonstrate just how advanced that awareness is. The goal is not to generate videos. Of course, they could and likely will build products on this capability, but the long-term goal is bigger.
Re: Sora: Creating video from text
#415I am a CG artist and Director and this made me so sad. I am watching in horror and amazement. I am not anti AI at all, but being on the wrong side of efficiency, for the individual this is heartbreaking. its so much fun to make CG and create shots and the reason its hard (just like anything) makes it rewarding.
Ex colleague then! I'm kind of glad I went out of it all now that I see all of this, but on the other hand it's also an amazing opportunity unfolding, as long as it's directable. What a great toolset! For what you've had to have army of people, freezing ass on location, working with actors.. soon gone. Well, if you want it to. On the other hand, look at what happened to imagery, concept art in general. For the better part it cheapened it. Turned it into this mass produced, easily available thing that it's not special anymore. Skills are still needed to produce exactly what you want, but the special flair is kind of gone. It will need way more energy and creativity now to stand out.
Re: Sora: Creating video from text
#416Countdown to when studios licensing this for "unlimited" episodes of your favorite series. There was Seinfeld "Nothing, Forever" AI parody, but once the models improve enough and are cheap enough to deploy, studios will license their content for real and just have endless seasons. Or even custom episodes. Imagine if every episode of a TV show was unique to the viewer.
If this sounds interesting I’d highly recommend this short story by Ken Liu
Re: Sora: Creating video from text
#417This inside VR goggles would make it amazing. probably it wouldnt even need to render 360, it would generate it on demand. I better go get some feeding tube
Re: Sora: Creating video from text
#418Is this real life?
Or is just a generated fantasy?
Re: Sora: Creating video from text
#419This is insane. But I'm impressed most of all by the quality of motion . I've quite simply never seen convincing computer-generated motion before . Just look at the way the wooly mammoths connect with the ground, and their lumbering mass feels real. Motion-capture works fine because that's real motion, but every time people try to animate humans and animals, even in big-budget CGI movies, it's always ultimately obvio…
Out of all the examples, the wooly mammoths one actually feels like CGI the most to me, the other ones are much more believable than this one.
Possibly because there are no videos or even photos of live wooly mammoths, but loads and loads of CG recreations in various documentaries.
Re: Sora: Creating video from text
#420I see many possibilities for commercials, demos... not to mention kids' animations, of course. Actually, thinking of this from the perspective of a start-up, it could be cool to instantly demonstrate a use-case of a product (with just a little light editing of a phone screen in post). We spent a lot of money on our product demo videos and now this would basically be free.
how will the AI know what your product looks like? You probably already have CAD models, couldn't you import those into blender and make something in an afternoon or two?