Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI generation of fake celeb images

github.com

Post reply on HN
Print view View original

11–20 of 36 posts

Re: AI generation of fake celeb images

#11

Post by 49bc »

Udik wrote: post #5
symphom wrote: post #4

Amazing. And now one only needs a random article generator, which describes marriages, breakups, mishaps, accidents, and plain random appearances of these celebrities. Tada, random fake celebrity news, which is probably even better at wasting people's time than the real thing. This is going to happen really soon, because text generation is much easier than what the Nvidia guys did.

Just came here to say that it's time to start a gossip magazine about completely imaginary people. You beat me to it. However I disagree about text generation, which seems to me to require a perfect equivalent of human intelligence to be at least acceptable. (I'd call it AGI-complete, or maybe HI-complete).

Gossip about people you’ve never heard of or seen completely defeats the allure of gossip doesn’t it?

Re: AI generation of fake celeb images

#12

Post by ttul »

enrmarc wrote: post #6

I read the paper, but I did not understand a thing. What is the path to follow (for example, books or papers to read) in order to at least understand what the paper is talking about? My background is in computer science.

Read the original GAN paper: https://arxiv.org/abs/1406.2661

Re: AI generation of fake celeb images

#13

Post by trebligdivad »

pieterr wrote: post #3

The accompanying video reminds me of the Godley and Creme video ‘Cry’ from 1985. Nvidia article: https://youtu.be/G06dEcZ-QTg Cry: https://youtu.be/KxtPRF6NG7I

They've got a longer video at: https://drive.google.com/drive/folders/1gAb3oqpaQFHZTwPUXHPI... IMHO this looks a lot more like merging between different celebrities

Re: AI generation of fake celeb images

#18

Post by qbrass »

49bc wrote: post #11
Udik wrote: post #5

Earlier quoted context omitted.

Just came here to say that it's time to start a gossip magazine about completely imaginary people. You beat me to it. However I disagree about text generation, which seems to me to require a perfect equivalent of human intelligence to be at least acceptable. (I'd call it AGI-complete, or maybe HI-complete).

Gossip about people you’ve never heard of or seen completely defeats the allure of gossip doesn’t it?

The allure in this case is generating money through clickbait, so no.

Re: AI generation of fake celeb images

#19

Post by SteveJS »

The thumbstamp version of creating fake celeb faces was one of the projects for the Deep Learning Udacity nanodegree. (These get changed over time, so it may be different now.)

The dataset of 200,000 celeb photos with the face nicely centered at a known location is a nontrivial part of making the exercise feasible.

I trained on windows with a 6Gb 1060, and went off script from the DCGAN paper, by using upscaling rather than transpose convolutions. Once all the fiddling details are set correctly, the results are quite amazing. It didn’t even require a complete single pass over that dataset.

Re: AI generation of fake celeb images

#20

Post by prions »

Really interesting article seeing how I'm finishing up my own DCGAN project!

Generative models like GANs are fascinating, but very temperamental to train. Some of the findings in this paper mirror my own observations - increasing the complexity of the GAN adds a lot of instability. My solution was to keep things as simple as possible. I spent a lot of effort trying to increase the size of the network to get better results, but in the end my smallest implementation worked the best.

This bit is interesting: "Without progressive growing, all layers of the generator and discriminator are tasked with simultaneously finding succinct intermediate representations for both the large-scale variation and the small-scale detail. With progressive growing, however, the existing low-resolution layers are likely to have already converged early on, so the networks are only tasked with refining the representations by increasingly smaller-scale effects as new layers are introduce"

Post reply on HN