661–670 of 1001 posts
Earlier quoted context omitted.
> Also nobody cares about music without good lyrics Well, that's an exaggeration if I've ever seen one. Firstly, so much of current chart music has atrocious lyrics. And secondly, instrumental music is very popular.
You got me, I exaggerated on the internet. Sorry.
> Upload an image of yourself and transform it > into a personalized video. Movie Gen’s > cutting-edge model lets you create personalized > videos that preserve human identity and motion. A stalker’s dream! I’m sure my ex is going to love all the videos I’m going to make of her! Jokes aside, it’s a little bizarre to me that they treat identity preservation as a feature while competitors treat that as a bug, explicitl…
Pretty much anyone that I’ve talked to that somewhat works in AI industry, the attitude is “let it rip right now, and deal with the consequences as it’s going to happen one way or another”. I’m not sure where I stand on this issue, but the reality is, it’s inevitable whether we want it or not.
The "inevitability" of it is mostly a function of the (self-serving) belief that it is inevitable.
Basically, you just cited a bunch of moral cop-outs.
My kids both have creative hearts, and they are terrified that A.I. will prevent them from earning a living through creativity. Very recently, I've had an alternate thought. We've spent decades improving the technology of entertainment, spending billions (trillions?) of dollars in the process. When A.I. can generate any entertainment you can imagine, we might start finding this kind of entertainment boring. Maybe, at…
Are you?
My kids both have creative hearts, and they are terrified that A.I. will prevent them from earning a living through creativity. Very recently, I've had an alternate thought. We've spent decades improving the technology of entertainment, spending billions (trillions?) of dollars in the process. When A.I. can generate any entertainment you can imagine, we might start finding this kind of entertainment boring. Maybe, at…
Earlier quoted context omitted.
But it uses AI only for audio, right? Script for the vid seems to be written by human, given the unusual humor type of this channel. I started watching this channel some time ago.
It's hard to tell whether they use AI for script generation. After having seen enough of those recaps, the humor seems to be rather mechanical and basic humor is relatively easy to get from an LLM if prompted correctly. The video titles also seem as if they were generated. That said, this channel has been producing videos well before ChatGPT3.5/4 so at the very least they probably started with human written scripts.
I feel like it might actually be quite complex for AI to pull up the perfect clips and edit them with the script, including timing and everything. Maybe it could be made automatic, but nonetheless it would be a complex process and I don't think possible few years ago. I know Gemini and possibly some others can analyze video if fed to them, but I'm still skeptical that this channel in particular would have done it, when they have always had this frequency of uploads and similar tone.
Also I think there's far better TTS now with ElevenLabs and others so it could be made much more human like.
Earlier quoted context omitted.
> Creativity isn’t magic, it’s a skill I don't agree. There's some skill, some theory, behind it. But mastering this alone is almost worthless. There's a huge overlap between creatives and mental illness, particularly bipolar disorder. It seems perfectly mentally stable people lack that edge and insight. To me, that signals there is some magic behind it. And it's magic because then it must not be rationale and it mus…
All artists I have known have spent most of their lives practicing. Just as I have practiced programming. That's the biggest edge, commitment. To think that you _need_ to be neurodivergent to be an artist is non-sensical and stating mastering the craft itself is worthless is indicative of a lack of respect for their work. I'm baffled by this type of comment here in all honesty. Really, broaden your horizons.
We'll be over here trying new things, making new art, and expanding the horizon bye
Why do these video generation ones never become usable to the public. Is it just they had to create millions of videos and cherry pick only a handful of decent generations? Or is it just so expensive there's no business model for it? My mind instantly assumes it a money thing and they're just wanting to charge millions for it, therefore out of reach for the general public. But then with Meta's whole stance on open ai…
There are a few available to the public. runway.ai and kling are a couple that I see heavily used on Twitter. I pay for runway right now for experiments and it works. The problem is that maybe 1 out of 10 prompts result in something useable. And when I say useable I have pretty low standards. Since the model pumps out 5 or 10 second clips you have to be pretty creative since the models still struggle with keeping any…
They also just added the ability to do lip sync to a moving head and it gets the lighting right too - runways lip sync breaks if there’s any movement at all.
I’m gonna stop pumping Kling on this comment thread now - until they start paying me to advertise!
Are any image / video generation tools giving just the output or the layers, timelines, transitions, audio as things to work with in our old fashioned toolsets? The problem: In my limited playing of these tools they don't quite make the mark and I would easily be able to tweak something if I had all the layers used. I imagine in the future products could be used to tweak this to match what I think the output should b…
A lot of folks in this thread have mentioned that the problem with the current generation of models is that only 1 in (?) prompts returns something useful. Isn't that exactly what a reward model is supposed to help improve? I'm not an ML person by any means so the entire concept of reward models feels like creating something from nothing, so very curious to understand more.
Luma is by far the worst and relatively compared to Runway and Kling by far produces the worst quality and unstable video. Runway has that distinctive "photo in the foreground with animated background" signature that turns many off.
Kling and Runway share that same "picture stability" issue that is rampant requiring several prompts before getting something usable (note I don't even include Luma because its output just isn't competitive imho).
This Meta Movie Gen seems to make heavy usage of SAM2 model which gets me super excited as I've always thought that would bring about that spatiotemporal golden chalice we always wanted, evident by the prompt based editing and tracking of objects in the scene (incredible achievement btw).
Until I have the tool ready to try I will withhold any prejudgements but from my own personal experiences with generative video, this Meta movie gen is quite possibly SOTA.
I simply have not seen this level of stability and confidence in output. Resolutional quality aside (which already Kling and Runway are at top of the game), the sheer amount of training data that Meta must have at disposal must be far more than what Kling (scrapes almost the entirety of Western content, copyrights be damned) and Runway can ever hope to acquire, plus the top notch talented researchers and deep learning experts they house and feed, makes me very optimistic that Meta and/or Google will achieve SOTA across the board.
Microsoft on the other hand has been puttering along by going all in on OpenAI (above, below and beside) which has been largely disappointing in terms of deliverability and performance and trying to stifle competition and protect its feeble economic moat via the recently failed regulatory capture attempt.
TLDR: this is quite possibly SOTA and Meta/Google have far more training data then anybody in the existing space. Luma is trash.
All 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.
The ATV turning in mid air was a giveaway as well. Physics seems to be a basic problem for these type of videos.
But overall the physics are surprisingly good. In the videos from text we a person moving covered in a bedsheet, a mirror doing vaguely mirror-like things, a monkey moving in water and creating plausible waves, shadows moving over a 3d object with the sloth in the pool and plausible fire. Those are all classic topics to tackle in computer-generated graphics, all casually handled by a model that isn't explicitly trained on physical simulation.
In a twist of irony it's the simplest of those (the mirror) that's the most obviously wrong.