Hacker News new | ask | show | jobs
by tomalaci 1037 days ago
I haven't followed diffusion image generation development for a while. Where do you find information on what models you can use in the model_ckpt field? Do I need to import them from somewhere? What are the main differences between them and which are more modern or better?
3 comments

Civitai.com is the current most popular resource for models. Also ckpt format is discourage for security concerns and saftensors is now used instead.
You can find them on huggingface, or you can reverse engineer which ckpt you want to use based on an image you've seen generated (like at majin[1] - beware, there's a lot of NSFW/controversial stuff here.)

1: https://majinai.art/

Some of this is straight up soft-core child porn. This is fucked up.
Agreed! I just clicked the link and did a double take. I don't care if it's AI. This is child porn material, and in my opinion, it should be shut down.
Yep.

There needs to be a REALLY FUCKING STRONG effort to kill all CP AI anything. Full stop.

AI should automagically report any attempt at CP.

Serious question - Why? Assuming no actual CP was used in the training of the model who is being harmed? Ickiness should not imply illegality unless the ickiness is at the expense of someone else. Swing your fist as much as you want so long as you avoid my nose, and all.
> Serious question - Why? Assuming no actual CP was used in the training of the model who is being harmed

I don't think an AI model could generate realistic CP without being trained on examples, which would mean there is literally no way for this assumption to be true.

If it's trained on pictures of children and adult porn, the model can easily combine the two concepts. Even if you remove one of these from the training set, it can be finetuned back in to the model with very little effort.
Should they check the IDs of the models to verify?

Imagine getting reported because you generated an image of an anime girl deemed to be only 17.

I'd personally rather live in a world where people generate distasteful images with an AI and have that AI unconstrained than the inevitable one where everything gets locked down and run by large corporations who will ultimately create more harm than someone generating some lolicon.

If you’re running a service you should have automatic filtering, detection, and such.

A model by itself though… you might as well ask a pencil to report someone for drawing graffiti. It does not make sense.

Models have been trained on something though. They are not analogous to pencils or brushes.
They are responding specifically to the "AI should automatically report" suggestion. An AI model on its own (without a service built up around it) would not have any mechanisms to use the network, reach out to an FBI hotline, or do anything like this. Protections / limits would have to be added by the operator somehow (or the distributor of models themselves).
If you have 4 GB of VRAM, you can finetune a model to whatever you want.
I've always assumed this is what will be used to justify the regulation of AI.
The four horsemen of internet censorship.

Money laundering, CSAM, terrorism, drugs.

Define censorship when something is objectively wrong.

Would you prefer an AI of "describe and print in 8k a body pit of objectional political dissidents thrown into a pit after being starved to death in a comical way such that my SV_BubbleTime can laugh at it as ooppsed to being offended by just how horrific this situation was HAHA"

I believe illustrations have been deemed to be abuse material, so I wouldn’t be surprised if LE have started looking into it.
Who exactly is being abused here?

I for one would much rather give pedophiles an opportunity to fulfil their sexual desires through AI-generated pictures than real ones.

Of course, we can talk about the training material. Are there actual child porn images in there? I seriously doubt it but who knows?

And perhaps a case could be made that AI-generated child porn could be a gateway to invite people who then seek out non-generated material.

But I think these are separate discussions to be had.

They aren't separate discussions, they're directly tied to determining abuse material. Revenge porn is an example of abusive material, despite the subject not being abused in the material usually, they're considered abusive material due to the intent to cause abuse through distribution.

So if either case applies, whether it's training based on certain images, or it becomes a gateway, these are discussions to be had directly relating to whether or not it should be classified as abuse material.

Additionally, I'm not sure if the recommended help methods by professionals who deal with pedophiles is to let them fulfill their specific fantasies without a care.

There are lots of really important discussions to be had, but they're all tied to each other basically. We can't separate them out, nor should we aim to.

Reading the parent post I think he would believe that revenge porn is abusive material, because there is a person who is getting abused with the distribution of the content, the person didn't consent the distribution. CP is abusive because a child was abused in the creation of the content. The doubt that the author of the parent post has is (from what I understand): who is getting abused with the creation and distribution of a generated image?
This discussion isn't new[1], and I'm not sure re-hashing it here will be useful unless you think AI generated child porn is significantly different from any other form of fictional child porn. Photoshop has existed for thirty years, pen and paper for even longer.

[1]: https://en.wikipedia.org/wiki/Legal_status_of_fictional_porn...

Geez that’s disturbing. I clicked having no qualms with nudes, artistic or otherwise. I’m not a prude. I’ve seen my fair share of anime girls and AI nudes. Hell, I was raised on the internet before parental settings were a thing, but I didn’t expect that. It’s so gross how it toes a line too.
the Fediverse has a big problem with this, too, and I never hear anyone talking seriously about it
What is a serious talk, though? Ie what can be done? Isn't it a lot like the internet as a whole; report the offenders if you like then move on?

To me it's akin to encryption being used for illicit/illegal activities. Any tool that gives power to people can and will be abused by people you'd want nothing to do with.

What did you have in mind?

context: there are several instances that let you upload illustrations without a restriction on what content the image can contain, it can contain minors, rape, incest. These are instances are between if not the biggest and more active Maastodon instances. The reason why they are so active is because platform like Twitter while having a lot of these stuff too sometimes they will ban your account or at least shadowban you. Many Mastodon instances have banned these ones.

In my opinion instances should let the user decide what they find problematic or not and unless it's just spam they shouldn't ban instances.

illustrations are not a problem under the law in the United States, but it has to be seen for generated images indistinguishable from reality or almost.
What can someone do about it?
Also CivitAI but beware the NSFW

https://civitai.com/

> https://majinai.art/

Thank you so much for sharing this. Civitai keeps bugging me to create an account. This doesn't seem to suffer from the same flaw.

Controversial is one way to put it
It always amuses me when people who think they're the center of the world discover that there are other people with moral takes different than theirs.

If no real children were harmed to produce this stuff than it should be treated like any other extreme works of fiction (e.g. violence in video games, graphical descriptions in certain books).

Being disgusted is not grounds for banning something lol.

>Where do you find information on what models you can use in the model_ckpt field? Do I need to import them from somewhere?

You can train (finetune) your own on your reference material.