This person does not exist
thispersondoesnotexist.com
This person does not exist
1–10 of 185 posts
Re: This person does not exist
#2I have a question -
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?
How likely is it for it to actually exist after all?
Re: This person does not exist
#3Originally submitted just on 12 months ago:
https://news.ycombinator.com/item?id=19144280
(872 points, 242 comments)
Re: This person does not exist
#4I have a question - 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? How likely is it for it to actually exist after all?
Just from a dozen refreshes I'm pretty sure Zuckerberg is in their training set.
Re: This person does not exist
#5I was messing with the demo of Character Creator 3 the other week:
https://www.youtube.com/watch?v=tnviGWO0wbU
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.
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.
Re: This person does not exist
#6But can you do it from DNA?
Re: This person does not exist
#7Originally submitted just on 12 months ago: https://news.ycombinator.com/item?id=19144280 (872 points, 242 comments)
Seems like it has been vastly improved since then [1].
The results are much better than when originally posted in HN.
Re: This person does not exist
#8StyleGAN (v2, which is this, and v1 before it) is spectacularly high quality.
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: https://leebutterman.com/assets/lsb5-plus-trixie-minus-brian... )
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.
Re: This person does not exist
#9I have a question - 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? How likely is it for it to actually exist after all?
The model has 18x512 parameters, and all 9000 parameters are 32-bit floats.
Even assuming only 16 bits of randomness for each parameter (to keep them small enough, so you don't get too wild, because the center of 0 is a pretty homogenized face), 16^9000 is a lot of permuations of faces.
They will, of course, borrow from all of the 70k faces on Flickr that power StyleGAN, in varying degrees.
Re: This person does not exist
#10I'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?