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

Opendream: A layer-based UI for Stable Diffusion

github.com

Post reply on HN
Print view View original

141–150 of 158 posts

Re: Opendream: A layer-based UI for Stable Diffusion

#141

Post by dragonwriter »

_6atf wrote: post #124
GaggiX wrote: post #123

Earlier quoted context omitted.

If I can finetune the model on my face and the model will be able to generate my nudes (even if there is no nude of mine in the dataset), then it can works easily with children too.

Do you understand that adult bodies and child bodies look different? Please show me a model trained on adult humans being fine tuned to generate a child human (fully clothed).

> Do you understand that adult bodies and child bodies look different?

SD-based models can generate child bodies just fine, based on lots of training with non-porn images.

> Please show me a model trained on adult humans being fine tuned to generate a child human (fully clothed).

That's going to be hard in the SD space since there are, AFAIK, no models trained exclusively on adult humans (not even the base models), so you'd have to scratch-train a new base model to do this. (A model fine-tuned on adult images is still going to have the influence of base-model training, and unless massively overfit—usually very much an anti-goal, the exception being age-filter models whose entire focus is controlling apparent age [0]—will not have lost much of the generalization capability of the base model.)

The generalization abilities of models are good enough in other contexts that its plausible that realistic nude children could be generated by a model with no nude children in its training data that was otherwise trained on both clothed children and nude adults. I have no plans on testing this, however.

[0] e.g., https://civitai.com/models/65214?modelVersionId=74332

Re: Opendream: A layer-based UI for Stable Diffusion

#143

Post by _6atf »

dragonwriter wrote: post #141
_6atf wrote: post #124

Earlier quoted context omitted.

Do you understand that adult bodies and child bodies look different? Please show me a model trained on adult humans being fine tuned to generate a child human (fully clothed).

> Do you understand that adult bodies and child bodies look different? SD-based models can generate child bodies just fine, based on lots of training with non-porn images. > Please show me a model trained on adult humans being fine tuned to generate a child human (fully clothed). That's going to be hard in the SD space since there are, AFAIK, no models trained exclusively on adult humans (not even the base models), s…

> SD-based models can generate child bodies just fine, based on lots of training with non-porn images.

I have not stated anything contrary.

> The generalization abilities of models are good enough in other contexts that its plausible that realistic nude children could be generated by a model with no nude children in its training data that was otherwise trained on both clothed children and nude adults. I have no plans on testing this, however.

Stable Diffusion has failed me for much simpler interpolations than the one you're describing. I don't believe this would work based on previous interpolations I have seen in Stable Diffusion. You can convince me by showing an example, but not by stating that it is possible without one.

Re: Opendream: A layer-based UI for Stable Diffusion

#145

Post by dragonwriter »

_6atf wrote: post #143
dragonwriter wrote: post #141

Earlier quoted context omitted.

> Do you understand that adult bodies and child bodies look different? SD-based models can generate child bodies just fine, based on lots of training with non-porn images. > Please show me a model trained on adult humans being fine tuned to generate a child human (fully clothed). That's going to be hard in the SD space since there are, AFAIK, no models trained exclusively on adult humans (not even the base models), s…

> SD-based models can generate child bodies just fine, based on lots of training with non-porn images. I have not stated anything contrary. > The generalization abilities of models are good enough in other contexts that its plausible that realistic nude children could be generated by a model with no nude children in its training data that was otherwise trained on both clothed children and nude adults. I have no plans…

> > The generalization abilities of models are good enough in other contexts that its plausible that realistic nude children could be generated by a model with no nude children in its training data that was otherwise trained on both clothed children and nude adults. I have no plans on testing this, however.

> Stable Diffusion has failed me for much simpler interpolations than the one you're describing

Its succeeded for me in much more complex ones. SD (even with the same exact set of checkpoint, LoRa, etc., and other workflow elements) isn't consistent across apparent-to-humans complexity levels in its generalization ability, and there are a very large combination of potential combinations.

> You can convince me by showing an example

Yeah, I'm not going to try to make simulated child porn for you, and while I would have sided with you in the debate over whether your earlier proof request amounted to a request for that, this one very clearly does.

Re: Opendream: A layer-based UI for Stable Diffusion

#146

Post by _6atf »

dragonwriter wrote: post #145
_6atf wrote: post #143

Earlier quoted context omitted.

> SD-based models can generate child bodies just fine, based on lots of training with non-porn images. I have not stated anything contrary. > The generalization abilities of models are good enough in other contexts that its plausible that realistic nude children could be generated by a model with no nude children in its training data that was otherwise trained on both clothed children and nude adults. I have no plans…

> > The generalization abilities of models are good enough in other contexts that its plausible that realistic nude children could be generated by a model with no nude children in its training data that was otherwise trained on both clothed children and nude adults. I have no plans on testing this, however. > Stable Diffusion has failed me for much simpler interpolations than the one you're describing Its succeeded f…

Jesus, what is wrong with you? I clearly asked for an example of complex interpolations. How am I "very clearly" asking for CP when we're talking about complex interpolations, not CP?

Please, explain how I am "very clearly" asking for it. Please. Literally both sentences preceding the one you quoted (as in, the entire paragraph containing this sentence) are talking about interpolation. How do you jump from interpolation to CP??

Re: Opendream: A layer-based UI for Stable Diffusion

#147

Post by Zuiii »

__loam wrote: post #116
Zuiii wrote: post #99

Earlier quoted context omitted.

It's comments like this that really highlight the extent of damage copyright has caused. It has conditioned people to think that they can own information once released, and that they can treat it like property. It's a notion that's ridiculous and silly that it gets threatened each time we make a leap in technology (tapes, computers, internet and streaming, and now generative AI). I wonder how long society will tolera…

Until we have an economy where people don't starve to death from lack of food or die of frostbite from being homeless, we have to figure out ways for people who actually make things to benefit from that work. Copyright is currently protecting people who rely on the product of their labor to make ends meet. Until we have the fairy tale economy you envision where artists can have the work stolen and still live, this is…

The true fairy tale is the intellectual "property" nonsense you people deluded yourself into believing. As I said, reality will continue to slap you across the face with each jump in technology. How I wish these slaps were enough to wake you up from your delusions but alas.

Re: Opendream: A layer-based UI for Stable Diffusion

#149

Post by samstave »

SV_BubbleTime wrote: post #94
nomel wrote: post #78

Earlier quoted context omitted.

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"

Re: Opendream: A layer-based UI for Stable Diffusion

#150

Post by kleiba »

GaggiX wrote: post #137
wsintra2022 wrote: post #129

Earlier quoted context omitted.

“Neither am I a pedophile myself, nor do I know anyone who is“ Glad you cleared that up for the readers at home.

We live in a world where the author of parent post would be unironically accused of being a pedo by several people for having that opinion so don't be surprised.

Unfortunately, this.
Post reply on HN