Hacker News Reader

Comment by argella | Hacker News Reader

Bummer. AI porn is fun.

The future is probably models trained almost exclusively on porn.

Porn has driven many tech advances. I predict that models trained on specific porn genres will appear as soon as training a good model is doable for under $5000. They’ll get here much quicker if we get video to that mark first.

You could probably already get people to pay for a subscription to generate images. Wouldn't be surprised if someone is already working on it.

The entire NovelAI drama had already demonstrated this.

> Porn has driven many tech advances.

This is an urban myth.

Which happens to be true.

Yes and now. Yeah the VHS VS Beta situation was exaggerated, but you'll be surprised on how much on Netflix, and youtube UI tricks were stolen from innovation made in adult sites.

I'll even say that the high bandwidth push in the public was highly related to that. Even HTML5 video players, adult websites were faster to implement it than big streaming websites that still used flash or similar tech.

What tech advances would those be?

print magazine, cinema, VHS, Internet

How much did porn actually contribute to innovation in any of those though?

Let me ask you this in reply:

Have you ever seen a non-porn DVD that had multiple camera angles (a feature defined in the standard DVD spec)?

And all it took was the ritual degradation and abuse of women.

They’re already out there, although they’re hard to find via Google - people are doing wild things like “merging” hentai models with models trained on real life porn to get realistic poses and lighting with impossible anatomy.

The scary thing is that you can then train it further with things like DreamBooth to start producing porn of celebrities… or, even more worrying, people you know.

Seriously folks, we are within a year or less of this being trivial. It’s already possible with a lot of work today.

I have no idea how it works but I have seen people talking about models trained to draw furry art. And I assume no one spent the millions on AWS to train a full model from scratch.

I believe what they do is take the released version of stable diffusion and then continue training from there with their own image sets. I came across their attempts when looking into how to train the model based on some images of my own; their data set so far reaches between tens of thousands and hundreds of thousands images.

All the difficult parts (poses, backgrounds, art styles) has already been done by the SD researchers, the porn network only needs reference material for the NSFW description/tags/details. This is significantly cheaper.

A similar project, training SD to output images in the style of Arcane, is incredibly successful in replicating the animation style with what seems to be very little actual training data.

I don't think you need to start from scratch at all if you use the SD model as a base, all you need to do is to train it on specific concepts, styles and key words that the original doesn't have.

No. The whole point of these models is that they combine information across domains to be able to create new images. If you trained something just on, say baseball, you could only generate the normal things that happen in baseball. If you wanted to generate a picture of a bear surfing around the bases after hitting a home run, you'd need a model that also had bears and surfing in the training data, and enough other stuff to understand the relationships involved in positioning everything and changing poses.

Even if porn is what you want, it's not clear that's what you want. It can probably generate better porn if it has a little context about what, say, a bedroom is.

What's more interesting, is that there's evidence (from public posts, I haven't tried these models myself) that models trained on some porn get better at non-porn images too.

Reply on news.ycombinator.com