I couldn't help noticing that half the female poses are seriously CFM ("Come hither"), whereas the male poses are The Thinker, or Man-spreading, or other things that manly men do. But then I tried generating some male images. Turns out that The Thinker can be seriously CFM as well. For some reason, all the images I have generated so far are unexpectedly sexualized even I when i try to give it completely benign prompt…
AI real-time human full-body photo generator
241–250 of 421 posts
Re: AI real-time human full-body photo generator
#242Earlier quoted context omitted.
Looking at the poses, it feels optimized for generating porn, but one example someone showed had a child's face (good god please don't let your "AI" system generate child anything if you want to sell it for porn purposes), and another user noted that their attempt error'd out because it "detected nudity", even though other users get given a nude model by default.
I don't know if the thing in the crotch is a penis or a scrotum, but it is definitely NSFW: https://images.generated.photos/0wV1dBnZ15hGneEfqfZT7SdEIill... My prompt was simply "Standing in front of a rocket.".
Re: AI real-time human full-body photo generator
#243I couldn't help noticing that half the female poses are seriously CFM ("Come hither"), whereas the male poses are The Thinker, or Man-spreading, or other things that manly men do. But then I tried generating some male images. Turns out that The Thinker can be seriously CFM as well. For some reason, all the images I have generated so far are unexpectedly sexualized even I when i try to give it completely benign prompt…
Re: AI real-time human full-body photo generator
#244Earlier quoted context omitted.
No, I'm not. BigGAN did fine on scaling up to JFT-300M with basically no changes beyond model size and a simple architecture. This is also what we were observing, even with a buggy BigGAN implementation. GigaGAN is the best quality, but that's mostly because it's also the biggest; as Table 1 shows most of the gains come from various kinds of additional scaling. (And this is moving the goalposts from the usual asserti…
Researchers have spent several years try to even create a GAN that can fit well a distribution made of aligned faces (resulted into StyleGAN1/2); with a simple unet with e-objective and cosine schedule you can fit much complex distributions, still using one loss: L1/L2. Reading your comments make me feel like that you believe that just every researchers (even extremely smart dude like Karras) just switch to diffusion…
> for example your buggy BigGAN implementation
The bug was that the batchnorm gamma was initialized to zero instead of one, so all the model params were being multiplied by zero instead of one. Literally any model that uses batchnorm is susceptible to this bug, and it certainly has nothing to do with GANs.
I think it’s too easy to spout dogma, and calling gwern delusional is something I’ve learned from experience will prove foolish as t approaches infinity.
Re: AI real-time human full-body photo generator
#245Earlier quoted context omitted.
I can count on one hand the number of ways these photos fail. That's right, 6 ways.
If you encode a binary digit for each biological digit on your hand you can count up to 32 on one hand.
assuming you have the dexterity to hold each of your 10 fingers in one of 3 different positions—e.g.: up, down and crooked—you could technically count up to 3^10 or 59,049
if you mastered that, you could add a fourth or even fifth position. 4^10 is just over 10^6, so you could hold any 6 digits, and 5^10 is just under 10^7, so almost any 7 digits
you can compress really heavily using high bases, but for it to make practical sense the atomic medium of storage has to have that number of states
if you just convert binary to a high base and back again, unsurprisingly the space used works out exactly the same, as the number of symbols used to represent a number may be fewer, but the length of the symbols themselves balances it out exactly
e.g. in base 1000 you may be able to represent the number 999 with a single symbol, but you need 1000 unique symbols to show every number up to 999, each of which of course takes up significantly more digits than a bit; however, if you had a storage cell that could reliably store and display 1000 unique states, then it would be a different matter. whether that's possible or would/could even take up less physical space than ~log_2(1000) binary cells I do not know
Re: AI real-time human full-body photo generator
#246Re: AI real-time human full-body photo generator
#247Has the same problems as midjourney et al: you can feed it pictures of a friend or yourself or a celebrity, and the result is always off - not recognizable as them
That's pretty easily fixable if you train a LoRA or similar so that the model has a specific likeness in mind. (You can look at - and despair at - Civitai if you want proof.) It's harder to do at inference time without training, but I wouldn't assume it'll be impossible forever, especially with the existence of ControlNet.
Re: AI real-time human full-body photo generator
#248I get that most of these are hilarious (this is my favorite comment on HN in some time, https://news.ycombinator.com/item?id=37239909 ). But still, I find this incredibly frightening. These are only going to get better. Does anyone doubt that in a couple years time (if that) we'll be able to put the image of any known public person into whatever generated photo we want, which would be indistinguishable from reality?…
We're basically there right now betweem Deepnude[1] and Photoshop. [1] (NSFW, seriously.) https://deepnude.cc/
This is just disgusting. I thought it would just be a uncensored generative AI but certainly wasn't expecting peeping-tom as a service. And advertise it so blatantly as being able to virtually strip any girl you have pictures of just makes me sick.
Re: AI real-time human full-body photo generator
#249Earlier quoted context omitted.
We're basically there right now betweem Deepnude[1] and Photoshop. [1] (NSFW, seriously.) https://deepnude.cc/
> The most powerful image deepfake AI ever created. See any girl clothless with the click of a button. This is just disgusting. I thought it would just be a uncensored generative AI but certainly wasn't expecting peeping-tom as a service. And advertise it so blatantly as being able to virtually strip any girl you have pictures of just makes me sick.