Also I could see this would be a major breakthrough for Anime industry.
Imagine, gives a initial frame and a reference video on the side, that would be pretty dope.
Make-A-Video: AI system that generates videos from text
161–170 of 399 posts
Re: Make-A-Video: AI system that generates videos from text
#162Earlier quoted context omitted.
For those who are scared about this technology, it’s good to look at what AI has done to Chess. The best chess seems to be when AI is used along with humans. I think image and video AI will best be exploited when human input is also taken into account. There is still something special about human creativity, I think AI will just be another tool to expand that. At least, in the short term I would say 10 years perhaps.…
Don't worry, humans will still be relevant for ~10 years! . (and then regrettably irrelevant thereafter). I think it is a legitimate worry, as the pace of progress is considerable. These tools are impressive, and are only going to get more impressive: more people should be talking about where this is headed.
These models are literally one French court decision away from being banned and investment in them being completely halted. So I wouldn't worry too much about them specifically.
Re: Make-A-Video: AI system that generates videos from text
#163Earlier quoted context omitted.
ozcam’s razor is a human made concept, the universe doesn't obey human laws, it's the opposite > Like in 10 years you could plug this tech into high end VR and get a prompted reality dynamically generated that would be indistinguishable from our own. They said that 10 years ago about VR and it still is dog shit
It’s funny because the last 10 years has seen the most advancement in VR ever. The original Oculus was a step change, and current VR is a step change from that. 8k VR is coming and will be close to indistinguishable from reality visually at least.
8k video games are here and very distinguishable from reality
At the end of the day you're still sitting/standing out there with two tv screens 2cm from your eye balls
Re: Make-A-Video: AI system that generates videos from text
#164Reading the paper, what's interesting is that they really build upon text-to-image models. Instead of generating 1 image with diffusion model, they generate 16, and then use several upsampling/interpolation methods to increase the resolution/framerate. For the text-image model, they use the DALL-E 2 architecture, so in theory just switching to a latent diffusion model (like stable diffusion) would boost training/infe…
One can imagine that resolving this will require a separate model to construct a timeline/keyframe series from a text description then interpolate between them.
Fascinating times, either way this is allegedly being open–sourced, so I'm hopeful others will be able to build on top.
Re: Make-A-Video: AI system that generates videos from text
#165The > A golden retriever eating ice cream on a beautiful tropical beach at sunset, high resolution example is terrifying.
It is, but to make up for it we got a man drifting a horse.[1] [1] https://makeavideo.studio/assets/A_knight_riding_on_a_horse_...
Yeah, put some blue sparks on those hooves and you've got a meme
Re: Make-A-Video: AI system that generates videos from text
#166So how long before we can “Hey music-stable-diffusion-service,” play me “relaxing baroque violin and flute music in the style of game of thrones” ?
My start-up is working on this! We'll be launching a web and downloadable version soon. Eg. https://www.youtube.com/watch?v=r_0JjYUe5jo --> https://vocaroo.com/1hgjjnVNqWjk We're also working on film generation.
I don't understand what I'm seeing here, in ingested the Eminem track and recreated it using a different voice?
Re: Make-A-Video: AI system that generates videos from text
#167Earlier quoted context omitted.
I know some extremely hard working independent filmmakers who struggle so hard to get noticed. After this tech goes mainstream in 5 years and gets really good, I don’t know what they’re going to do
Make blockbusters, because scenes that would be incredibly expensive to shoot now will be practically free with this?
Every 15 year old kid will be making their own blockbusters
Re: Make-A-Video: AI system that generates videos from text
#168As an owner of a Video Production studio, this kind of tech is blowing my mind and makes me equally excited and scared. I can see how we could incorporate such tools in our workflows, and at the same time I'm worried it'll be used to spam the internet with thousands and thousands of souless generated videos, making it even harder to look through the noise. A fun related experiment, I thought it was fun to see what ki…
I know some extremely hard working independent filmmakers who struggle so hard to get noticed. After this tech goes mainstream in 5 years and gets really good, I don’t know what they’re going to do
AI is eating the world, and the vast majority of people are not paying attention.
I don't know what artists, truck drivers, Uber/Lyft/taxi drivers, delivery drivers, programmers, doctors, judges, fast food workers, etc. are going to do.
Re: Make-A-Video: AI system that generates videos from text
#169Meta Inc? no, thanks.
Re: Make-A-Video: AI system that generates videos from text
#170I couldn’t find how long the video generation took
I would guess that it didn't take long running on Meta's servers, but if you were doing this at home with a 3090 it would take at least 6 minutes per 15 second video, assuming your settings take 15 seconds to render a single frame and there are 24 frames per second in the video.