We live in the future. I just hope we consumers get easy access to these video tools at some point. I want to make personal movies from my favorite books
Meta Movie Gen
71–80 of 1001 posts
Re: Meta Movie Gen
#72Impressive. It's only going to get better, faster, cheaper, easier.[a] Sooner than anyone could have expected, we'll be able to ask the machines: "Turn this book into a two-hour movie with the likeness of [your favorite actor/actress] in the lead role." Sooner than anyone could have expected, we'll be able to have immersive VR experiences that are crafted to each person. Sooner than anyone could have expected, we won…
You sound like two minute papers.
Re: Meta Movie Gen
#73Earlier quoted context omitted.
Are we only a few years away from one person/small group made movies where the dialog, acting, location and special effects can be tweaked endlessly for a relatively low cost. If I was a studio exec I'd be worried.
If I was a human I'd be worried.
These are tools by and for humans
Re: Meta Movie Gen
#74Some of these look really obviously bad, like the guy spinning the fire and the girl running along the beach. And it completely failed at the bubbles
doesn't need to be movie quality, just needs to be tiktok quality and this totally passes the bar. Are you ready to become a penguin in all of your posts to maximise aquatic engagement? I am.
I've become a robot and a demon to maximise engagement, its called being a vtuber
Re: Meta Movie Gen
#75I'm not impressed with the quality. Did they mean to make it look so cartoony?
Re: Meta Movie Gen
#76Earlier quoted context omitted.
Are we only a few years away from one person/small group made movies where the dialog, acting, location and special effects can be tweaked endlessly for a relatively low cost. If I was a studio exec I'd be worried.
I wouldn't be. How is any of this going to lead to meaningful art? I don't think you get "The Green Mile" from something like this.
There are plenty of great outsider storytellers and artists. Youtube is proof of this. People mostly do comedy on youtube because that's what the medium supports on a low budget, but AI is going to change that.
Re: Meta Movie Gen
#77Earlier quoted context omitted.
Are we only a few years away from one person/small group made movies where the dialog, acting, location and special effects can be tweaked endlessly for a relatively low cost. If I was a studio exec I'd be worried.
I wouldn't be. How is any of this going to lead to meaningful art? I don't think you get "The Green Mile" from something like this.
I'd love to see what'd happen if someone dumped the entire text of the Silmarillion or the Hobbit into one of these models. Assuming context windows and output capacity become large enough.
Re: Meta Movie Gen
#78Yet another one-shot, single-clip Instagram machine that can't do a follow-on shot natively.
As it stands, the only chance you have of depicting a consistent story across a series of shots is image-to-video, presuming you can use LoRAs or similar techniques to get the seed photos consistent in themselves.
Re: Meta Movie Gen
#79All the vids have that instantly recognizable GenAI "sheen", for the lack of a better word. Also, I think the most obvious giveaway are all the micro-variations that happen along the edges, which give a fuzzy artifact.
It's my understanding that the AI sheen is done on purpose to give people a "tell". It is totally possible right now to at least generate images with no discernible tell.
Re: Meta Movie Gen
#80Impressive. It's only going to get better, faster, cheaper, easier.[a] Sooner than anyone could have expected, we'll be able to ask the machines: "Turn this book into a two-hour movie with the likeness of [your favorite actor/actress] in the lead role." Sooner than anyone could have expected, we'll be able to have immersive VR experiences that are crafted to each person. Sooner than anyone could have expected, we won…
Are we only a few years away from one person/small group made movies where the dialog, acting, location and special effects can be tweaked endlessly for a relatively low cost. If I was a studio exec I'd be worried.
I'm not sure, I see a common pattern with autonomous vehicle, text to image, llms: the last 10% are hard to achieve