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'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://www.thiscatdoesnotexist.com" rel="nofollow">https://www.thiscatdoesnotexist.com</a> for example.
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't seen anything like it since.
Here’s the Guardian article which linked the site: <a href="https://www.theguardian.com/culture/2020/feb/07/ai-in-the-adult-industry-porn-may-soon-feature-people-who-dont-exist" rel="nofollow">https://www.theguardian.com/culture/2020/feb/07/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.
I was messing with the demo of Character Creator 3 the other week:<p><a href="https://www.youtube.com/watch?v=tnviGWO0wbU" rel="nofollow">https://www.youtube.com/watch?v=tnviGWO0wbU</a><p>It has a "machine learning" 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.
So, the specific person may not exist, but likely someone very, very similar in appearance does.<p>I've come across people in life that I would have sworn were twins. I'm curious how combinatorically low the number of facial features need to be before people resemble one another.
You can play with the code[0] for this really easy if you've got a Nvidia GPU with nvidia-docker[1] installed:<p><pre><code> docker run --gpus all -it anibali/pytorch:cuda-10.1 bash
# copy images to container with `docker cp`
pip install stylegan2_pytorch
stylegan2_pytorch --data ./images
</code></pre>
[0] <a href="https://github.com/lucidrains/stylegan2-pytorch" rel="nofollow">https://github.com/lucidrains/stylegan2-pytorch</a><p>[1] <a href="https://github.com/NVIDIA/nvidia-docker" rel="nofollow">https://github.com/NVIDIA/nvidia-docker</a>
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?
Now, the next obvious question is, how do you pick one of these non-existing persons and generate images of him/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?)
Originally submitted just on 12 months ago:<p><a href="https://news.ycombinator.com/item?id=19144280" rel="nofollow">https://news.ycombinator.com/item?id=19144280</a><p>(872 points, 242 comments)
What'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?
An artist friend of mine is using this technology in an interesting way .. she'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'm looking forward to her exhibit of this work - especially the live demonstrations.
I'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?
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's face out of drag: <a href="https://leebutterman.com/assets/lsb5-plus-trixie-minus-brian.mp4" rel="nofollow">https://leebutterman.com/assets/lsb5-plus-trixie-minus-brian...</a> )<p>But it can be tricky to encode faces if they look out of the ordinary, where "ordinary" is the 70k faces on Flickr that trained StyleGAN.
This has improved so much since the last time I checked it.<p>It'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.
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's inherently harder for the algorithm?
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's why you should always use example.com).
My humble entry into the this x does not exist pantheon:<p><a href="https://thisbutterflydoesnotexist.com/" rel="nofollow">https://thisbutterflydoesnotexist.com/</a>
What's really amazing to me is the rendering quality, if that's the right word for it, the resolution. This seems different to me than the "structural realism" in the sense of how plausible the face is in it being representative. Not sure if there are terms for this but it's amazing to me how realistic things like skin texture are independent of "higher level" features.
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)
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.
Makes me so happy I took "Computers, Ethics and Social Responsibility" 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.
The background, clothing and especially other people in the image are still a dead giveaway that it's not a real person. It's kind of weird how the algorithm borks something relatively simple as the texture of clothing.
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.
Some people generated there seem oddly familiar. Too bad, I am not good with remembering names or I would frequently go: "oh that is <xyz> from <abc.inc>. How did his/her picture end up here?"
This gynoid was damaged in the vat.<p><a href="https://i.imgur.com/BMoGUVo.jpg" rel="nofollow">https://i.imgur.com/BMoGUVo.jpg</a>
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.
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.