TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

This person does not exist

321 pointsby angrygoatover 5 years ago

53 comments

RodgerTheGreatover 5 years ago
It has been interesting to see images clearly generated by this service (same artefacts, same resolution) start to flood online dating apps and social media profiles. Previously, fake accounts tended to use photos which could be reverse-image-searched to detect them.<p>Luckily, it doesn&#x27;t seem that this approach can be sensibly extended to generate entire scenes, or multiple entire-body photos from different angles. Believability breaks down tremendously in less constrained datasets- see <a href="https:&#x2F;&#x2F;www.thiscatdoesnotexist.com" rel="nofollow">https:&#x2F;&#x2F;www.thiscatdoesnotexist.com</a> for example.
评论 #22265671 未加载
评论 #22267723 未加载
评论 #22267292 未加载
评论 #22267410 未加载
评论 #22269016 未加载
ackshuallyover 5 years ago
There was a pic of an older guy, but what was unsettling was the woman peeking over his shoulder; like a friend or a family member, leaning into the photo.<p>Her eyes were melting into black and white streaks curling down over her sagging cheeks; her smile was perfectly white, and just a little too long.<p>I refreshed on instinct, and haven&#x27;t seen anything like it since.
评论 #22264681 未加载
评论 #22264800 未加载
评论 #22266286 未加载
评论 #22265955 未加载
评论 #22265883 未加载
angrygoatover 5 years ago
Here’s the Guardian article which linked the site: <a href="https:&#x2F;&#x2F;www.theguardian.com&#x2F;culture&#x2F;2020&#x2F;feb&#x2F;07&#x2F;ai-in-the-adult-industry-porn-may-soon-feature-people-who-dont-exist" rel="nofollow">https:&#x2F;&#x2F;www.theguardian.com&#x2F;culture&#x2F;2020&#x2F;feb&#x2F;07&#x2F;ai-in-the-ad...</a><p>To my mind there is a massive need for us in the software world to pause and think about the ethics of all of this. Engineers more broadly have well developed ethical codes, we should too.
评论 #22265568 未加载
评论 #22269306 未加载
评论 #22267294 未加载
评论 #22267091 未加载
评论 #22265310 未加载
nineteen999over 5 years ago
I was messing with the demo of Character Creator 3 the other week:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=tnviGWO0wbU" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=tnviGWO0wbU</a><p>It has a &quot;machine learning&quot; based projection mode where you can project a single photo of a face on the head of a character mesh and it will create somewhat believable set of 3D features from the photograph on the model. It was fun to take a couple of the generated faces from this site and apply them to the models.<p>I imagine you could do a lot with just those two things if you had the talent of the artist in the video I posted above. You could create fully rigged and clothed characters for games in a fraction of the time it would take to make them entirely from scratch, and for much less expense and cleanup (I would have thought) than full body scanning.
评论 #22267365 未加载
tomrodover 5 years ago
So, the specific person may not exist, but likely someone very, very similar in appearance does.<p>I&#x27;ve come across people in life that I would have sworn were twins. I&#x27;m curious how combinatorically low the number of facial features need to be before people resemble one another.
评论 #22266823 未加载
评论 #22268601 未加载
评论 #22266957 未加载
评论 #22266834 未加载
评论 #22266407 未加载
ijpsudover 5 years ago
You can play with the code[0] for this really easy if you&#x27;ve got a Nvidia GPU with nvidia-docker[1] installed:<p><pre><code> docker run --gpus all -it anibali&#x2F;pytorch:cuda-10.1 bash # copy images to container with `docker cp` pip install stylegan2_pytorch stylegan2_pytorch --data .&#x2F;images </code></pre> [0] <a href="https:&#x2F;&#x2F;github.com&#x2F;lucidrains&#x2F;stylegan2-pytorch" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;lucidrains&#x2F;stylegan2-pytorch</a><p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;NVIDIA&#x2F;nvidia-docker" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;NVIDIA&#x2F;nvidia-docker</a>
jonplackettover 5 years ago
I have a question -<p>When generating a new person (or whatever it is that does not exist) can you know that it isn’t like any of the images that went into the training data set?<p>How likely is it for it to actually exist after all?
评论 #22264734 未加载
评论 #22264466 未加载
评论 #22264556 未加载
credit_guyover 5 years ago
Now try this:<p><a href="http:&#x2F;&#x2F;whichfaceisreal.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;whichfaceisreal.com&#x2F;</a>
评论 #22266423 未加载
评论 #22265262 未加载
评论 #22265289 未加载
评论 #22268504 未加载
评论 #22265298 未加载
beefieldover 5 years ago
Now, the next obvious question is, how do you pick one of these non-existing persons and generate images of him&#x2F;her doing different things in different places? (Or, of course, real persons. Is there a service where I can upload my photo and it starts to generate images of me doing random - or not so random - things?)
评论 #22267497 未加载
评论 #22265095 未加载
merricksbover 5 years ago
Originally submitted just on 12 months ago:<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=19144280" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=19144280</a><p>(872 points, 242 comments)
评论 #22264514 未加载
评论 #22264577 未加载
shrubbleover 5 years ago
I remember the site hotornot.com ; will there be another one, BotOrNot.com ?
评论 #22267972 未加载
评论 #22266450 未加载
6gvONxR4sf7oover 5 years ago
What&#x27;s the current state of the art on controllable GANs? Like if you wanted to build a thispersondoesnotexist but with the ability to control e.g. gender, smile, sunglasses, ethnicity?
评论 #22269855 未加载
fit2ruleover 5 years ago
An artist friend of mine is using this technology in an interesting way .. she&#x27;s drawing regular street portraits of people she meets, and then using that as the seed to generate new pictures of people who do not exist.<p>It has produced some extraordinarily disturbing art, especially for those of us who were her subjects. Some of the images are so wild and out there, it really is an adventure into ones own psyche. I see so much in the generated images that creates an intense emotional response, and its very difficult to differentiate between the lines of the artist and the lines of the code, at least in a way that is easily discernible. Her art as the seed definitely amplifies things - the emotions of eyes, the despair of cheeks and lips - in a way that the generative programming enhances, 1000x ..<p>Very interesting stuff, and I&#x27;m looking forward to her exhibit of this work - especially the live demonstrations.
评论 #22265456 未加载
Angosturaover 5 years ago
I&#x27;m intrigued about the possibility of using these as stock photos - it dies away with the need for model permissions (or does it?). Presumably the copyright on the image resides with the person who ... programmed the neural net? Trained the neural net? Is running the server?
评论 #22265306 未加载
评论 #22264610 未加载
评论 #22265060 未加载
评论 #22264886 未加载
lsbover 5 years ago
StyleGAN (v2, which is this, and v1 before it) is spectacularly high quality.<p>Even more interestingly, you can interpolate between faces very smoothly. (For instance, I was able to give some face off the street a drag makeover, by interpolating that face plus or minus the face of a drag queen minus that performer&#x27;s face out of drag: <a href="https:&#x2F;&#x2F;leebutterman.com&#x2F;assets&#x2F;lsb5-plus-trixie-minus-brian.mp4" rel="nofollow">https:&#x2F;&#x2F;leebutterman.com&#x2F;assets&#x2F;lsb5-plus-trixie-minus-brian...</a> )<p>But it can be tricky to encode faces if they look out of the ordinary, where &quot;ordinary&quot; is the 70k faces on Flickr that trained StyleGAN.
speedgooseover 5 years ago
This has improved so much since the last time I checked it.<p>It&#x27;s interesting to see so high quality on image generation using neural networks, while text generation using gpt2, which seems a lot easier at first, is glorified nonsense.
评论 #22265190 未加载
OscarCunninghamover 5 years ago
I noticed there are very few black people and none with very dark skin. But there are lots of people of many other ethnicities. Was dark skin avoided because it&#x27;s inherently harder for the algorithm?
评论 #22265866 未加载
评论 #22269895 未加载
mmahemoffover 5 years ago
Meet the social media pundits for the next presidential election.
thdrdtover 5 years ago
What is the likelihood that the generated person does exist?<p>I got the feeling this could turn out the same as people using fake email addresses to later discover that the domain in fact exists (that&#x27;s why you should always use example.com).
评论 #22265241 未加载
robgaover 5 years ago
My humble entry into the this x does not exist pantheon:<p><a href="https:&#x2F;&#x2F;thisbutterflydoesnotexist.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;thisbutterflydoesnotexist.com&#x2F;</a>
skat20physover 5 years ago
What&#x27;s really amazing to me is the rendering quality, if that&#x27;s the right word for it, the resolution. This seems different to me than the &quot;structural realism&quot; in the sense of how plausible the face is in it being representative. Not sure if there are terms for this but it&#x27;s amazing to me how realistic things like skin texture are independent of &quot;higher level&quot; features.
ogre_magiover 5 years ago
I use this to generate faces for NPCs in my TTRPGs.
achowover 5 years ago
Ask HN - Any equivalent - &#x27;This Voice Does Not Exist&#x27;?<p>It would be awesome to have that for a project that I&#x27;m thinking of.
dr_j_over 5 years ago
I wonder could the generated faces now be used to actually do further training? Even from scratch for other, similar GANs? Doing so might remove any privacy concerns about real world data being used to train these things (going forward)
thepete2over 5 years ago
They don&#x27;t let you download the image unless you have the right user agent. How impolite of them.
bagacrapover 5 years ago
I looked at about 50 faces trying to find one with a strong jawline or hard cheekbones. Although the features and hair are very realistic, the algorithm does seem to stray away from distinctive features. The women especially have uniformly round and soft faces.
tommahoover 5 years ago
I can&#x27;t spot the fake human faces on mobile, but man some of those cats are nightmare fuel!
sub7over 5 years ago
Makes me so happy I took &quot;Computers, Ethics and Social Responsibility&quot; in college.<p>These algorithms are tools and at their worst they are powerful weapons - much more dangerous than some nuclear bomb that wipes out a few hundred square miles.
ChrisMarshallNYover 5 years ago
It&#x27;s improved.<p>I used to be able to tell the fakes by the ears, but that seems to have been fixed.
评论 #22265681 未加载
dep_bover 5 years ago
The background, clothing and especially other people in the image are still a dead giveaway that it&#x27;s not a real person. It&#x27;s kind of weird how the algorithm borks something relatively simple as the texture of clothing.
评论 #22265210 未加载
nautilus12over 5 years ago
I just realized the potential this has for ruining dating apps by filling up the majority of people on the program with fake generated people that just waste enough of the participants time that they never get anywhere.
MichaMeierover 5 years ago
Some people generated there seem oddly familiar. Too bad, I am not good with remembering names or I would frequently go: &quot;oh that is &lt;xyz&gt; from &lt;abc.inc&gt;. How did his&#x2F;her picture end up here?&quot;
teddyukover 5 years ago
It would be really funny if someone managed to use someone’s phone camera to take a photo and make it look like the site was showing their own face.
kmeadeover 5 years ago
This gynoid was damaged in the vat.<p><a href="https:&#x2F;&#x2F;i.imgur.com&#x2F;BMoGUVo.jpg" rel="nofollow">https:&#x2F;&#x2F;i.imgur.com&#x2F;BMoGUVo.jpg</a>
teiloover 5 years ago
Why is it that the eyes are often slightly off on so many of these? Many are fine, but the majority seem to have a slightly lazy eye.
tartoranover 5 years ago
I noticed that some people have some kinf of skin cancer blip or some other weird anomaly. Is the algo not able to filter those out?
clSTophEjUdRanuover 5 years ago
I&#x27;ve seen this.<p>It would be neat to randomly generate faces until it generates a &quot;doppelganger&quot; of yourself.
kstenerudover 5 years ago
I wouldn&#x27;t be surprised if someone soon comes up with a porn generator based on this tech.
fctorialover 5 years ago
This person does not exist <i>in the training database</i>.<p>Imagine seeing your lookalike in here.
评论 #22264967 未加载
boublepopover 5 years ago
Om my book “x doesn’t exist” demonstrations are absolutely worthless if they don’t as a minimum show at least one “closest” member of the training set.<p>You could set up a script that just randomly picked one out of 50 images of my closest family and no one would know the difference from going to it.
评论 #22270113 未加载
meehatpaover 5 years ago
Almost all the women with their ear visible have something shiny in the lobes.
toto444over 5 years ago
They all have the same teeth.
paulpauperover 5 years ago
The fake web is going to be even bigger than the dark web. it may already be
评论 #22264950 未加载
评论 #22264891 未加载
rednerrusover 5 years ago
If you look at enough of these they all start to look alien.
mirimirover 5 years ago
Maybe Mirimir and my other personas should get selfies.
lwi19over 5 years ago
Beautiful fakes but a simple trick can identify them quickly:<p>The right and left side of these faces are too similar. This is not the case with real people.
Simon_saysover 5 years ago
Better: thiswaifudoesnotexist.net
评论 #22267459 未加载
_9cikover 5 years ago
But can you do it from DNA?
miradoover 5 years ago
I love this site and use it for my news. It&#x27;s funny to find this here.
RocketSyntaxover 5 years ago
that robo cat is going to haunt my dreams
Forgivenessizerover 5 years ago
These are not being generated on the fly, are they?
评论 #22265086 未加载
workingkamilover 5 years ago
actually, that‘s a picture of my cousin
ekianjoover 5 years ago
&gt; &quot;Imagined by a GAN&quot;<p>There&#x27;s no imagination involved.