Although there is one higher res image available, which is better than usual. Of course it's high enough res to show that there's visible artifacting. But this is pretty impressive.
I wonder if an easy hack would be to train a second separate neural network to clean up the kind of artifacting that you get out of the first neural network...
"I wonder if an easy hack would be to train a second separate neural network to clean up the kind of artifacting that you get out of the first neural network..."
Shhhh, don't give the evil web overlords ideas for new nasty captchas :)
My understanding is that this is exactly how these images are generated. One network makes the image, and another tries to find flaws... They both get better together.
Here's the first 2 Google results for "GAN" meaning "Generative Adversarial Network"
would this mean that outside of runway models, you wouldn't need models to showcase your clothing anymore since you can just "wrap" your clothes over these AI humans?
Exactly. If you're Gap and have a lineup with thousands of articles of clothing, why would you go through the trouble of procuring models? You have to deal with modeling agencies, photographers, set managers, etc... When the AI gets good enough, it will be even better than the alternative. It will serve ads showing only your body type. Maybe the models will even have....your face.
That would be great. You don't need a floor length mirror and changing rooms if you can just have your rendered body and face to exchange clothes on. Need to get accurate measurements for the right dimensions though.
3D body scanning to get a representation of your body. Than use software to automatically generate and cut clothing patterns to get the exact fit you're looking for. TNow all that's left is stiching, which would be fairly difficult to automate when patterns are variable so would still be a significant cost point for custom clothing.
That would depend on very accurate cloth physics simulation as well. This is way beyond what the article is showcasing, it's not even in the same ballpark.
It could lead to more than just putting casual models out of work. Fewer stylists and designers would be needed.
Let the AI generate the color patterns (sticking with Gap as an example, it might retain their chosen /size as constraints) and boom, on demand styling
Not to mention you wouldn't need photoshop anymore to give the models unrealistic proportions. Adopt this system and proudly declare that you don't photoshop the models! Like fat-free soda.
Somehow they'll have to find a way around lookalikes. A real human who believes the rendering is actually their image and likeness. So they'll have to have a way to prove that there was no "contamination".
Funny enough, there was a case[1] of a real person thinking a model on a website was him but it turned out the image was that of an altogether different person that just looked like them, uncannily.
For illustration, let's say the AI generated a "body" that looked eerily similar to Kim Kardashian or the president of Burundi and used it to promote products or causes.
I can imagine the liability of _not_ having a human to say "this is me" miiiiight keep this from becoming a go-to for big brands.
Or we could put it this way: a corporation might see this as a choice between A) creating a whole new branch of case law to test in the court system, fueled by highly paid lawyers, or B) just pay a part-time model to be able to say "this wasn't you nor inspired by you, because that's the the model and we entered this contract together"
There will definitely be cases, if this becomes mainstream. I’m sure the companies developing this will come up with a solution proving “independent” genesis of the image/likeness.
I imagine they'd have to have a curating pass that cross-checks the generated models against public figures. For the less famous, as with your example, people are just going to have to get used to the fact that their appearance isn't necessarily unique and that they don't own the appearance of other people (real or fictional) who coincidentally look like them.
We simply use `bod2vec` to enforce a perimeter around trademarked personas. One simply chooses a suitable metric and embedding, and a safe distance, like (kDash-prezBurundi)², and any corporate avatar closer than that to a trademarked bod has to pay royalties at an inverse-square rate.
I don't think this will work because the AI is not going to recreate what a specific article of clothing will look like on a human. Or at least not yet.
This tech generates random images of models in random clothing. Maybe it could be instructed to do 'male' and 'brown' and 'jacket' - but never with the specificity required of a specific piece of clothing.
All clothes fit and drape in a unique way.
Also - models for regular clothing are a commodity and the process for getting generic imagery is industrialized and cheap.
Getting the 'photos of clothing on the model' is a small part of the cost.
Finally there is of course the other aesthetic choices, i.e. what's in the background that have to do with a particular design choice for whatever reason i.e. season choices. That won't be reproduced by AI either.
No because the pictures are randomly generated. You can control some things like age, gender, and in this case probably things like dress length, but there's no way to say "here's an item of clothing, make them wear this". At least not yet.
Some brands that sell lots of variants of similar items, like t-shirt stores, already do something close : they take a few shots of models in various poses, and then somehow "map" the pattern and color of the piece of clothing on those few shots, so really they need a model once and then they can do without.
This is useful to generate models for clothing shop, or new fashion models.
More general: I'm not surprised to see some day, one AI bot could automatically register a Twitter account, and have "real" conversations there. One day, i might retweet their tweets, too.
Some day more and more movies will have virtual actors, possibly licensing physical/voice tracts from known stars of the past. I would expect also virtual music bands to be created as such.
Or maybe they'll sort through all of the publicly available voice data for any actor and start talking and sounding exactly like them. No need for any actors.
I always wonder about their use as movie extras. Does anyone here know what's happening in the realm of movie-making? I had friends who did that as a lark, but there were pay minimums, so I imagine it's a substantial expense to studios.
One wonders if the people whose photos were used to build this system were compensated appropriately for their contribution. Something tells me that royalties were not discussed.
Uncompensated, or grossly under-compensated, use of personal data for AI systems is a serious issue that one no one seems to want to address.
> One wonders if the people whose photos were used to build this system were compensated appropriately for their contribution.
Stock photos exist. It's not as if researchers are trawling facebook to build their AI models.
Just looking at the output, and the unnaturally specific body poses, I'd guess they just put in an order for 50,000 stock photos and went on from there.
If you negotiate, you can trivially get it down to 0.10 per image which is just 5000 dollars. And by trivially, I mean just email several sources saying your budget is in the low thousands.
So most likely, everyone got compensated. All rights were preserved.
While AI models might replace catalogue models for small labels that are starting out (maybe) and for e-commerce companies (definitely). I highly doubt it that they will replace real models for large companies and fashion boutiques now or ever. Because what people (women and men) are buying is aspiration wrapped in dead plant fibers. The reason why I buy a dress from Hervé Leger is because I want to look like old school Crawford making body-con a thing in the ‘90s https://media.glamour.com/photos/56959302d9dab9ff41b2a79b/ma... and make the painful process of getting into that shape and look seem “easy” while doing it.
Fashion isn’t about looking good in of itself. It’s about social proof-of-work. Knowing what to wear and pulling it off isn’t easy. It’s the raison d’être of the multi-billion dollar fashion and fitness industries. Women eat grass all day everyday and go on ridiculous juice cleanses while contorting their body into shapes that would put a pretzel to shame. If the world endures so much pain to look effortlessly good, Why should manufacturers be allowed to forego the pain? If the root of aspiration is making the impossible look like a breeze, then why would anyone want to buy from a computer generated perfect model that never had to feel the pull of a difficult stretch and stare in the mirror with guilty eyes?
The suspension of disbelief necessary for the social economy to function crumbled as soon as something is too perfect. Like Instagram photos. It’s not cool to slap on a filter anymore and stage a perfect photo. It’s too easy now. Just like Prisma was. What’s cool is to put in the work and make something imperfect so that everyone knows that you put in the effort and looked unflappably blasé while doing it.
Most models that are hired today are hired partly on their social presence. Having an audience, even a micro-audience, is essential for getting high paid gigs, because brands aren’t just selling the look; they’re selling the whole package associated with the look. Women like to buy from other women (and men like James Charles) whom they can aspire to. Tweens and teens want to look like the models on tik-tok. Young-adults and grown women want to look like their favorite YouTuber and Instagram celeb. They all want to participate in making something cool happen with their friends.
All of this and more is intrinsically social and human.
All of this and more means that as long as humans buy from other humans, brands will hire models to appeal to what’s most human; sexy, sexy crazy-making envy.
This may be true, but I'm sure the vast, vast, vast majority of people employed as models are these kinds of print and e-commerce models whose jobs are now at risk.
> Because what people (women and men) are buying is aspiration wrapped in dead plant fibers
In this case I agree. If someone buys the watch that Elon Musk wears, it's not just about wanting to look like Elon, it's about want to BE him. This effect works even if rationally people know that they are not him. Emotionally, they just want the feeling, however fleeting, that they are him.
> The suspension of disbelief necessary for the social economy to function crumbled as soon as something is too perfect.
Here I disagree and the example of fake Instagram profiles are my counter point. Some of these accounts used real people but the entire "lifestyle" was faked and yet they still had thousands and thousands of followers. What's the difference between creating a fake person to drop into that fake profile and having it be a real person?
One side effect of that is that while modeling has always been very hard to pierce into, at least there are modeling opportunities for non celebrities. As the practice of using AI to generate models for all but higher end stuff grows, it will get harder and harder to pierce into. It’ll go from an industry with tens of thousands of workers - some paid a lot, some much less - to just a few hundreds of highly paid models who have every incentive to prevent newcomers from taking their spot.
It’s not a phenomenon unique to fashion, and it’s entirely problematic when tech kills the long tail of this sort of occupation. How will those people pay their bills now? Not all of them can become AI engineers, that’s for sure.
I find it frustrating how eager AI supporters are to dismiss legitimate concerns using the reasoning "Oh, well, it's always worked out before, I'm sure it'll work out again". What if it doesn't? And if it doesn't, it'll be too late to make changes and prevent suffering.
At the point where you can't distinguish between real/organic and generated, this argument collapses though.
What feels "human" can be manufactured. Imperfections can be artificial, too.
We like to believe we're flawless arbiters of what's human, but we can be fooled in almost all cases. Most of all in photos. The soul remains an abstract concept.
You buy the dress because you want to convince yourself you look like old school Crawford or you want others to be convinced that you look like old school Crawford.
The point of models 99% of the time is to show the clothes. This isn't going to get rid of super models, but it's going to step on the turf of all but the most popular models.
>The reason why I buy a dress from Hervé Leger is because I want to look like old school Crawford making body-con a thing in the ‘90s
This aspect of fashion gives you narratives you can use to weave the story you tell about yourself and present to others. AI generated characters can tap into this with created narrative while constantly also posessing the supernormal stimuli currently achieved by using photoshop on real models. That coupled with the switch in the focus of mass media from films to games and I think that while real models will not die away, digital models will not just be used in catalogue settings. I wouldn't be surprised if 2-D from the Gorillaz became the model for a clothing brand for instance, so it isn't even a question of photorealism.
The ability of the wealthy to transmit this to their heirs, the tendency of children to enter the same professions as their parents. Social proof-of-work.
How much of our life is just social proof-of-work...
Take for example Japan - the land of anime girls on every piece of advertising. How much would the demand for human models expand if illustrated characters were not an alternative?
There's a scarcity in the type of human beauty that's sought after by the fashion industry. What if that scarcity didn't exist?
If people grow up with this new economic model of beauty and scarcity, maybe it would change the landscape of fashion entirely.
Anime is used in subculture in Japan, but on TV (except for very specific time windows) and in the streets you dont see much of it. I live in Japan btw.
I will say the demographic deeply into fashion and those familiar with anime girls doesn't feel like it overlaps too much -- yet.
That said, one recent interesting development I saw is VRoid Wear, a collaboration between fashion brands and an anime-style 3D avatar creation tool. The brand Chloma is releasing the same apparel for avatars and real people simultaneously. The avatar-wear is not a mere promotional giveaway for the physical-wear: both are treated equally as products for sale, as they are selling the model data and textures for the former at around $50. (The physical version goes at something closer to $500, but still.)
https://hub.vroid.com/wear/chloma
I’m posting this message from a local train in rural japan. The sides are plastered with ads but nowhere where i look at can i see anime girls.
While i know few instances where they exist, that’s just not the reality in japan. Akihabara is as much of a japan as Silicon Valley is Usa. At certain level yes but on the other hand not at all.
It was pretty damn hyperbolic. I seriously haven’t seen that much of an anime advertisements anywhere except near konbinis and stores related to them.
There might be an collaboration with some anime and product once in a while but from my experience (and this is an experience of an foreigner living in japan) it’s far from norm.
>> brands will hire models to appeal to what’s most human; sexy, sexy crazy-making envy
You’re assuming that brands won’t create their own personas that drive that same result.
In fact, this has already happened - the best known one isn’t even a human - he’s a mouse, and millions of people buy t-shirts and other things with his picture on them. The company that owns him is rather large, and very good at appealing to humans with non-human characters: Disney.
This is the beginning of the end for models. Actors are next.
I don't know that we'll go full-tilt computer generated. The truth is probably somewhere between, where some companies and brands retain humans as a more honest and authentic way to connect with consumers. Then you'll also see ML models that go far into the spectrum of being impossibly perfect and inhuman.
It's honestly exciting to imagine where we'll be in twenty years. I don't think we'll resent it - it's got fascinating artistic potential and will probably be quite liberating to finally realize that the things we strive for are artificially distilled.
You don't have anything to backup your assertion (or even have the possibility of evidence, before what you are assertion is what's in the mind of people).
When I browse through a fashion magazine, most models are unknown to me, they might as well be AI-gen.
The people that you know that tries to sell you cloth comprise a small fraction of people-images that you are exposed to.
You make a good point and I think the upper-end of models will continue to be in demand (besides, these computationally generated images were trained at least in part from human photos).
However, if I were just an above-average model, where the main function is to display clothes rather than weave a narrative, I might be worried about this technology because many use-cases of models may be in jeopardy from this technology.
In the future we are going to have neural fashion. People will use the knobs of an autoencoder to generate the clothes they like, preview them on artificial models , and then order them for manufacturing.
> Because what people (women and men) are buying is aspiration wrapped in dead plant fibers.
I suppose it's possible that there's a man out there somewhere who thinks like this, but I've never met him and this is the first time I've heard of him.
If anything, most men probably prefer the opposite -- clothing that hasn't been worn by some obnoxious socialite.
Super interesting. How soon does this tech become the next 6-7 figure instagram start? Curious if anyone can take this soon to build a following around a fake beautiful person doing fake interesting things.
They are not something new, they've been in the news in the last 5 years. I'm talking about GANs. Their 'father' Ian Goodfellow, has been recently poached by Apple from Google. Even NVIDIA is into GANs [1]. Thousands of papers have been written on the topic [2].
Is this really generating anything new or is it essentially just morphing between existing photos that it's been trained on?
It would be interesting to take some of these GAN demos and write a utility where for each output, have it find the closest-matching training input, and see how similar it is.
Typically these animations that look like morphings are generated by auto-encoders. Contrary to automatically generated morphings, you'll notice that all intermediate person is realistic.
I don't think GAN work that way (I haven't followed it last year though). My understanding is that a GAN simply tries to determine if an image is generated or authentic. I suppose they used one there.
One way to do what you propose would be to plot all the training pictures in the kernel space of the autoencoder and match the closest one to the generated picture.
This similarity of model output to training data, by pixel to pixel similarity, is often included in ML papers. The GAN here will very likely be producing uniques images in each case, some will be closer to the training data. But in general GANs are very capable and can for instance imagine a person with red hair wearing a green jacket even if it has never seen this combination of things before.
>Is this really generating anything new or is it essentially just morphing between existing photos that it's been trained on?
To answer this one would need to invest time into researching something that might potentially deflate the AI hype, so no one is doing it. Training dataset similarity analysis I usually see in these papers is downright laughable.
They can use this technology to generate a model to fit a particular user profile. Filter bubbles are going to get even better! Or maybe they can ask user to upload his photo and feed that as a prior to the model so it can generate visuals of that person wearing different dresses. That would be cool!
That would be neat. Imagine going to a site, adding some photos of yourself and seeing all the clothes as they would look on you based on your actual dimensions. You'd never have to wonder if something would look good on you. I imagine this would save a ton of shipping costs on returns.
The AI showed here is not even a step in that direction. If you want photo-realistic images of how a piece of clothing would look on your body you need:
- very accurate measurements of your body
- a very accurate representation of the materials used in that piece of clothing, including weight, tensile strength etc.
- a very accurate physics simulation matching the materials to your body measurements
The technology showcased here does nothing similar. It could perhaps generate pictures of what someone who looks sort of similar to your general body shape, as seen in your pictures, looks in clothes. It would be no better than what you currently have: look at the picture, and try to guess how well that fits your actual body.
Even worse, you would completely miss details like "the material is very stretchy, it looks good on the model's abs but it might look bad on my belly fat" because the AI would NOT be doing a simulation of how that clothing actually fits a human body - it's always producing an idealized simulation.
Edit: and to make this clear, I'm not saying that "the AI can't do that yet". I'm saying that the technique they are using can't achieve the goal you are talking about. There is nowhere near enough detail in pictures of clothing to get the kind of simulation you are looking for.
Amazing! This pretty much enables clothing brands to generate extremely targeted ads on the fly. Models can have similar body shape, hair style, skin colour to the user. Based on past photos the advertiser can figure out preferred colours, patterns and possibly even styles.
It’s fascinating how in the 80s and 90s we imagined virtual worlds being populated by 3D graphics built on modeled / digitized wireframes — and then this technology comes out of nowhere in the past decade. The holodeck seemed so implausible in its ability to just synthesize things. Doesn’t seem so implausible anymore. “Computer: Sherlock Holmes, in his study, speaking with Albert Einstein.”
Stop peddling meaningless hype. Current 3D rendering technology is lightyears ahead[1] of these AI toys and you can trivially parametrize it. Many games already do. So if you want to generate people, you already can do that while having full control, instead of some glitchy sliders.
Something genuinely useful might, perhaps, be achieved by applying GANs to parameters of those 3D models to allow easier customization, but I haven't seen any work in that direction.
Looks better to me than a lot of what is on your video. The video is very nice and it's really good, however it's often not really photorealistic when it's supposed to be and I also don't believe it'll be possible to do raytracing at such performance it'll be usable for most people (mobile phones), for VR. This approach is a new way that sidesteps the issues of raytracing.
With all the work on making these ML models controllable it seems like they now have a decent concept of things like "tall person" or "wears glasses". I assume it would be entirely possible to replace the last few layers and generate 3d models instead of images. Nobody is doing that right now because nobody has training data for that, and generating such training data is hard (or expensive). But it seems like it should be in reach of someone with a profitable use case.
I expect that data to grow quickly over the next decade, assuming things like the 3D selfie camera on iPhones end up on the main camera too. (I expect they will end up on all the cameras, just for the value they’d add to AR).
I do wonder if we'll ever reach a liberal enough society to be OK with machine-generated porn of all types, especially those taboo or illegal now (child pornography, sadism, zoophilia, etc). I could foresee it being banned before it even gets commercialized, which in my opinion would be unfortunate because I could see it as the methadone of porn to the "real stuff's" heroin.
> Child pornography under federal law is defined as any visual depiction of sexually explicit conduct involving a minor (someone under 18 years of age). Visual depictions include photographs, videos, digital or computer generated images indistinguishable from an actual minor, and images created, adapted, or modified, but appear to depict an identifiable, actual minor.
But that's not so in Japan. So one ought take care when torrenting Japanese films in the US.
Interesting moral implications. Should e.g. child porn still be illegal if no child is harmed? I think most people's natural reaction would be of course it should be illegal, it's child porn!
In the US there is a 1st amendment exception for obscenity under which these kind of prohibitions leverage.
Obscenity itself requires an average expectation of what obscenity is, otherwise the exception dissipates entirely.
It is therefore easy for me to see that the technological availability of this would change it. there would be attempts by executive branch and legislature that are obliged to simply say something “should” be illegal, and a court wouldnt be able to agree with that on constitutional grounds
Ditto with 3D printed flesh robots of each of the above. Bonus question: what about an adult engaging in self-insert roleplay of any of the above by remote controlling an avatar (virtual or physical) with a 3D headset? I think this question will stop being theoretical before 2030.
I think Denmark briefly allowed “all” pornography. Zoo was legal there until a few years ago, even had commercial production.
I've tried a couple of times to do this. The latest tech at the time had trouble with longer range structure, so things would start to look weird, with limbs just not looking right. I think it's totally doable, a way that I think wold work is use a nn to get the pose data from the graph and then generate the image from that pose data. Pretty sure it work, if you know what you are doing. Marketed right it will make big big money in the coming years. I just can't bring myself to invest the 100s of hours to get it running and into a marketable product. Can't stand programming anymore.
This makes me think about descartes' devil, if in such a short time we are able to generate fake bodies. What if we could generate fake people (not necessarily conscious but behaving as if they are.) in the future.
and with enough advances in brain/computer interfaces one could live a whole life without meeting a real human . In fact, in that case, one wouldn't even need accurate models since there would be no baseline to compare to.
Or maybe, we could implement surgical lenses that applies a filter on other people generating a fake person.
You can basically, eliminate _ism(s) in the workplace by making everyone look and sound the same.
People can pay to make their images in others' eyes different. Or one can pay to make their spouse look like a their true love in their eyes.
114 comments
[ 2.5 ms ] story [ 153 ms ] threadI wonder if an easy hack would be to train a second separate neural network to clean up the kind of artifacting that you get out of the first neural network...
Shhhh, don't give the evil web overlords ideas for new nasty captchas :)
Here's the first 2 Google results for "GAN" meaning "Generative Adversarial Network"
https://skymind.ai/wiki/generative-adversarial-network-gan
https://en.m.wikipedia.org/wiki/Generative_adversarial_netwo...
3D body scanning to get a representation of your body. Than use software to automatically generate and cut clothing patterns to get the exact fit you're looking for. TNow all that's left is stiching, which would be fairly difficult to automate when patterns are variable so would still be a significant cost point for custom clothing.
Let the AI generate the color patterns (sticking with Gap as an example, it might retain their chosen /size as constraints) and boom, on demand styling
Basically start by changing colors around.
Until 3D printed textiles get there anyway.
Or perhaps there will be manufactured AIs that star in films and model clothing.
Funny enough, there was a case[1] of a real person thinking a model on a website was him but it turned out the image was that of an altogether different person that just looked like them, uncannily.
For illustration, let's say the AI generated a "body" that looked eerily similar to Kim Kardashian or the president of Burundi and used it to promote products or causes.
[1]https://www.npr.org/2019/03/10/702063209/man-inadvertently-p...
Or we could put it this way: a corporation might see this as a choice between A) creating a whole new branch of case law to test in the court system, fueled by highly paid lawyers, or B) just pay a part-time model to be able to say "this wasn't you nor inspired by you, because that's the the model and we entered this contract together"
This tech generates random images of models in random clothing. Maybe it could be instructed to do 'male' and 'brown' and 'jacket' - but never with the specificity required of a specific piece of clothing.
All clothes fit and drape in a unique way.
Also - models for regular clothing are a commodity and the process for getting generic imagery is industrialized and cheap.
Getting the 'photos of clothing on the model' is a small part of the cost.
Finally there is of course the other aesthetic choices, i.e. what's in the background that have to do with a particular design choice for whatever reason i.e. season choices. That won't be reproduced by AI either.
So it's all very cool, but still mostly novel.
https://www.cadcrowd.com/blog/why-ikea-uses-3d-renders-vs-ph...
Doing it for clothes on humans seems like a reasonable next-step.
https://www.youtube.com/watch?v=pTFE8cirkdQ
More general: I'm not surprised to see some day, one AI bot could automatically register a Twitter account, and have "real" conversations there. One day, i might retweet their tweets, too.
“AI tech generates [images of] entire bodies of people who don't exist”
Uncompensated, or grossly under-compensated, use of personal data for AI systems is a serious issue that one no one seems to want to address.
Stock photos exist. It's not as if researchers are trawling facebook to build their AI models.
Just looking at the output, and the unnaturally specific body poses, I'd guess they just put in an order for 50,000 stock photos and went on from there.
If you negotiate, you can trivially get it down to 0.10 per image which is just 5000 dollars. And by trivially, I mean just email several sources saying your budget is in the low thousands.
So most likely, everyone got compensated. All rights were preserved.
BRB next startup idea.
Fashion isn’t about looking good in of itself. It’s about social proof-of-work. Knowing what to wear and pulling it off isn’t easy. It’s the raison d’être of the multi-billion dollar fashion and fitness industries. Women eat grass all day everyday and go on ridiculous juice cleanses while contorting their body into shapes that would put a pretzel to shame. If the world endures so much pain to look effortlessly good, Why should manufacturers be allowed to forego the pain? If the root of aspiration is making the impossible look like a breeze, then why would anyone want to buy from a computer generated perfect model that never had to feel the pull of a difficult stretch and stare in the mirror with guilty eyes?
The suspension of disbelief necessary for the social economy to function crumbled as soon as something is too perfect. Like Instagram photos. It’s not cool to slap on a filter anymore and stage a perfect photo. It’s too easy now. Just like Prisma was. What’s cool is to put in the work and make something imperfect so that everyone knows that you put in the effort and looked unflappably blasé while doing it.
Most models that are hired today are hired partly on their social presence. Having an audience, even a micro-audience, is essential for getting high paid gigs, because brands aren’t just selling the look; they’re selling the whole package associated with the look. Women like to buy from other women (and men like James Charles) whom they can aspire to. Tweens and teens want to look like the models on tik-tok. Young-adults and grown women want to look like their favorite YouTuber and Instagram celeb. They all want to participate in making something cool happen with their friends.
All of this and more is intrinsically social and human.
All of this and more means that as long as humans buy from other humans, brands will hire models to appeal to what’s most human; sexy, sexy crazy-making envy.
> Because what people (women and men) are buying is aspiration wrapped in dead plant fibers
In this case I agree. If someone buys the watch that Elon Musk wears, it's not just about wanting to look like Elon, it's about want to BE him. This effect works even if rationally people know that they are not him. Emotionally, they just want the feeling, however fleeting, that they are him.
> The suspension of disbelief necessary for the social economy to function crumbled as soon as something is too perfect.
Here I disagree and the example of fake Instagram profiles are my counter point. Some of these accounts used real people but the entire "lifestyle" was faked and yet they still had thousands and thousands of followers. What's the difference between creating a fake person to drop into that fake profile and having it be a real person?
One side effect of that is that while modeling has always been very hard to pierce into, at least there are modeling opportunities for non celebrities. As the practice of using AI to generate models for all but higher end stuff grows, it will get harder and harder to pierce into. It’ll go from an industry with tens of thousands of workers - some paid a lot, some much less - to just a few hundreds of highly paid models who have every incentive to prevent newcomers from taking their spot.
It’s not a phenomenon unique to fashion, and it’s entirely problematic when tech kills the long tail of this sort of occupation. How will those people pay their bills now? Not all of them can become AI engineers, that’s for sure.
The same way the luddites paid theirs I suppose
What feels "human" can be manufactured. Imperfections can be artificial, too.
We like to believe we're flawless arbiters of what's human, but we can be fooled in almost all cases. Most of all in photos. The soul remains an abstract concept.
You buy the dress because you want to convince yourself you look like old school Crawford or you want others to be convinced that you look like old school Crawford.
The point of models 99% of the time is to show the clothes. This isn't going to get rid of super models, but it's going to step on the turf of all but the most popular models.
There are some people who are famous, but the vast majority of working models are unknown people who will usually stay that way.
This aspect of fashion gives you narratives you can use to weave the story you tell about yourself and present to others. AI generated characters can tap into this with created narrative while constantly also posessing the supernormal stimuli currently achieved by using photoshop on real models. That coupled with the switch in the focus of mass media from films to games and I think that while real models will not die away, digital models will not just be used in catalogue settings. I wouldn't be surprised if 2-D from the Gorillaz became the model for a clothing brand for instance, so it isn't even a question of photorealism.
The ability of the wealthy to transmit this to their heirs, the tendency of children to enter the same professions as their parents. Social proof-of-work.
How much of our life is just social proof-of-work...
Take for example Japan - the land of anime girls on every piece of advertising. How much would the demand for human models expand if illustrated characters were not an alternative?
There's a scarcity in the type of human beauty that's sought after by the fashion industry. What if that scarcity didn't exist?
If people grow up with this new economic model of beauty and scarcity, maybe it would change the landscape of fashion entirely.
That said, one recent interesting development I saw is VRoid Wear, a collaboration between fashion brands and an anime-style 3D avatar creation tool. The brand Chloma is releasing the same apparel for avatars and real people simultaneously. The avatar-wear is not a mere promotional giveaway for the physical-wear: both are treated equally as products for sale, as they are selling the model data and textures for the former at around $50. (The physical version goes at something closer to $500, but still.) https://hub.vroid.com/wear/chloma
While i know few instances where they exist, that’s just not the reality in japan. Akihabara is as much of a japan as Silicon Valley is Usa. At certain level yes but on the other hand not at all.
There might be an collaboration with some anime and product once in a while but from my experience (and this is an experience of an foreigner living in japan) it’s far from norm.
You’re assuming that brands won’t create their own personas that drive that same result.
In fact, this has already happened - the best known one isn’t even a human - he’s a mouse, and millions of people buy t-shirts and other things with his picture on them. The company that owns him is rather large, and very good at appealing to humans with non-human characters: Disney.
This is the beginning of the end for models. Actors are next.
It's honestly exciting to imagine where we'll be in twenty years. I don't think we'll resent it - it's got fascinating artistic potential and will probably be quite liberating to finally realize that the things we strive for are artificially distilled.
You don't have anything to backup your assertion (or even have the possibility of evidence, before what you are assertion is what's in the mind of people).
When I browse through a fashion magazine, most models are unknown to me, they might as well be AI-gen.
The people that you know that tries to sell you cloth comprise a small fraction of people-images that you are exposed to.
Much to my surprise, I remember reading some of them. I don't know who you are, but you're a good writer.
However, if I were just an above-average model, where the main function is to display clothes rather than weave a narrative, I might be worried about this technology because many use-cases of models may be in jeopardy from this technology.
Virtual influencers may still work well for some brands/purposes. Here is the digitally generated Colonel from KFC:
https://www.adweek.com/creativity/kfc-created-a-virtual-infl...
I suppose it's possible that there's a man out there somewhere who thinks like this, but I've never met him and this is the first time I've heard of him.
If anything, most men probably prefer the opposite -- clothing that hasn't been worn by some obnoxious socialite.
Just leaving this here: Do tasks, get paid. Join us in the CoinCircle website to start earning crpyto https://coincircle.com/l/50VVxbObg3
[1] https://www.youtube.com/watch?v=XOxxPcy5Gr4&t=56s
[2] http://www.arxiv-sanity.com/search?q=generative+adversarial+...
It would be interesting to take some of these GAN demos and write a utility where for each output, have it find the closest-matching training input, and see how similar it is.
I don't think GAN work that way (I haven't followed it last year though). My understanding is that a GAN simply tries to determine if an image is generated or authentic. I suppose they used one there.
One way to do what you propose would be to plot all the training pictures in the kernel space of the autoencoder and match the closest one to the generated picture.
To answer this one would need to invest time into researching something that might potentially deflate the AI hype, so no one is doing it. Training dataset similarity analysis I usually see in these papers is downright laughable.
- very accurate measurements of your body
- a very accurate representation of the materials used in that piece of clothing, including weight, tensile strength etc.
- a very accurate physics simulation matching the materials to your body measurements
The technology showcased here does nothing similar. It could perhaps generate pictures of what someone who looks sort of similar to your general body shape, as seen in your pictures, looks in clothes. It would be no better than what you currently have: look at the picture, and try to guess how well that fits your actual body.
Even worse, you would completely miss details like "the material is very stretchy, it looks good on the model's abs but it might look bad on my belly fat" because the AI would NOT be doing a simulation of how that clothing actually fits a human body - it's always producing an idealized simulation.
Edit: and to make this clear, I'm not saying that "the AI can't do that yet". I'm saying that the technique they are using can't achieve the goal you are talking about. There is nowhere near enough detail in pictures of clothing to get the kind of simulation you are looking for.
Something genuinely useful might, perhaps, be achieved by applying GANs to parameters of those 3D models to allow easier customization, but I haven't seen any work in that direction.
[1] https://www.youtube.com/watch?v=KZ9mb3Jylb0
Looks better to me than a lot of what is on your video. The video is very nice and it's really good, however it's often not really photorealistic when it's supposed to be and I also don't believe it'll be possible to do raytracing at such performance it'll be usable for most people (mobile phones), for VR. This approach is a new way that sidesteps the issues of raytracing.
Your comment has value, but your tone is unnecessarily harsh. Would you talk to a coworker like this?
https://deepmind.com/blog/neural-scene-representation-and-re...
> Child pornography under federal law is defined as any visual depiction of sexually explicit conduct involving a minor (someone under 18 years of age). Visual depictions include photographs, videos, digital or computer generated images indistinguishable from an actual minor, and images created, adapted, or modified, but appear to depict an identifiable, actual minor.
But that's not so in Japan. So one ought take care when torrenting Japanese films in the US.
0) https://en.wikipedia.org/wiki/Child_pornography_laws_in_the_...
Obscenity itself requires an average expectation of what obscenity is, otherwise the exception dissipates entirely.
It is therefore easy for me to see that the technological availability of this would change it. there would be attempts by executive branch and legislature that are obliged to simply say something “should” be illegal, and a court wouldnt be able to agree with that on constitutional grounds
I think Denmark briefly allowed “all” pornography. Zoo was legal there until a few years ago, even had commercial production.
and with enough advances in brain/computer interfaces one could live a whole life without meeting a real human . In fact, in that case, one wouldn't even need accurate models since there would be no baseline to compare to.
Or maybe, we could implement surgical lenses that applies a filter on other people generating a fake person.
You can basically, eliminate _ism(s) in the workplace by making everyone look and sound the same.
People can pay to make their images in others' eyes different. Or one can pay to make their spouse look like a their true love in their eyes.
Well my wife still respects me I really misused her I am having an affair With a random computer