AI Generated Fake Celebrity Nudes (not deepnude/deepfake)

[fudefrak]

Some may notice that I previously had a "Kate Beckinsale 2" post, last month, but I noticed that around the beginning of december, something changed in my process that had been resulting in worse models, so I went back and deleted the images I posted from that point onward and have been creating new models since then. It wasn't as obvious with some celebrities, because the default Stable Diffusion is decent with some of them like Kate Beckinsale, but once I trained models on people I know IRL, it was clear the new models looked nothing like them in most of the generated images, so I looked closer at newer celebrity models and noticed the same degrading quality there as well. It wasn't a huge effect on most because it was averaged with other good models, but it was reducing the quality of my images, so I decided to start over and create new models for those celebs, and the results are looking really good imo. With those new models, I've now posted new images of Jenna Ortega, Sabrina Carpenter, Taylor Swift, Kristen Bell, and now Kate Beckinsale, and will keep doing more as I keep training new models.

Btw, I know it's been a while since my last new celebrity (Rachel McAdams at the end of November). I've been a little busy over the past few weeks, but I've so far gathered over 600 images of Emma Watson and am getting near the end of that process, so I should have some nudes of her up fairly soon I would think. It just depends on how much time I have to work on it.

 

[fudefrak]

Emma Watson

I think my initial results for Emma Watson are fantastic, but I think I'm going to modify the captions in my dataset to make her short hair less likely to be generated. I personally prefer her having longer hair a lot more, and I know that's a somewhat common opinion, so if I go through and include "with short hair" in the images where she has short hair, and then retrain, it should result in a model that's less likely to automatically generate her short hair without me specifically including those words in the prompt.

Original model:



tweaked the dataset. The new model does do the short hair less often but still does it on occasion without prompting, although none of the super short at least which I think looked the worst on her. There were some images in the dataset from red carpet appearances where it was difficult to tell whether she actually had short hair or it was just pulled back or in a bun or something, so I may still go back and see if I want to make any further changes, but any more models I make will be merged with this one:

 

[fudefrak]

The next celebrity I plan to train a model on is Hayley Williams

 

[Shoestring]

Emma Watson

I think my initial results for Emma Watson are fantastic, but I think I'm going to modify the captions in my dataset to make her short hair less likely to be generated. I personally prefer her having longer hair a lot more, and I know that's a somewhat common opinion, so if I go through and include "with short hair" in the images where she has short hair, and then retrain, it should result in a model that's less likely to automatically generate her short hair without me specifically including those words in the prompt.

Original model:

View attachment 2277109View attachment 2277110View attachment 2277111View attachment 2277112View attachment 2277113View attachment 2277114View attachment 2277115View attachment 2277305View attachment 2277306View attachment 2277307View attachment 2277308View attachment 2277309View attachment 2277310View attachment 2277311View attachment 2277312View attachment 2277313View attachment 2277314View attachment 2277315View attachment 2277316View attachment 2277317View attachment 2277318View attachment 2277319View attachment 2277320View attachment 2277321View attachment 2277322View attachment 2277323View attachment 2277324

tweaked the dataset. The new model does do the short hair less often but still does it on occasion without prompting, although none of the super short at least which I think looked the worst on her. There were some images in the dataset from red carpet appearances where it was difficult to tell whether she actually had short hair or it was just pulled back or in a bun or something, so I may still go back and see if I want to make any further changes, but any more models I make will be merged with this one:

View attachment 2281524View attachment 2281525View attachment 2281526View attachment 2281527View attachment 2281528View attachment 2281529View attachment 2281530View attachment 2281531View attachment 2281532View attachment 2281533View attachment 2281534View attachment 2281535View attachment 2281536View attachment 2281537View attachment 2281538View attachment 2282548View attachment 2282549View attachment 2282550View attachment 2282551View attachment 2282552View attachment 2282553View attachment 2282554View attachment 2282555View attachment 2282556View attachment 2282557View attachment 2282558View attachment 2282559View attachment 2282560View attachment 2282561View attachment 2282562

Pretty good. And you've made her tits about the right size.

 

[ornek7]

Here Is My More Fakes Of Maria Papadakis (Blonde Youtuber) Including His Husband, Chris Konopka.






More Fakes To Come...

 

[fudefrak]

Pretty good. And you've made her tits about the right size.

Well, I had some good reference photos to train from

 

[Gargoyle521]

They are on the list

Daisy Ridley?

 

[fudefrak]

Daisy Ridley?

Yes she's on the list. Reminder, I have over 500 names on this list, and it can take me a while to gather the images I need to create a model, so just because they're on the list doesn't necessarily mean I'll get to them. Every time I make a new model, I go through the whole list and do a sort of tournament, randomizing the order and picking a winner between each pair, and then doing that several times until I have a winner for who I most want to do next, but obviously that's going to be based on my own biases.

Daisy Ridley does seem like one that's more likely than some of the others to be picked at some point, but it's impossible to say when. I just do these one at a time. I've done 18 celebrities in about 9 months of training these models, and I think I've picked some good ones, but obviously I won't be able to do what everybody wants, so if any of you have a 12GB or larger GPU, I would encourage you to look into learning how to train your own models or at least LORAs.

 

[Gargoyle521]

Yes she's on the list. Reminder, I have over 500 names on this list, and it can take me a while to gather the images I need to create a model, so just because they're on the list doesn't necessarily mean I'll get to them. Every time I make a new model, I go through the whole list and do a sort of tournament, randomizing the order and picking a winner between each pair, and then doing that several times until I have a winner for who I most want to do next, but obviously that's going to be based on my own biases.

Daisy Ridley does seem like one that's more likely than some of the others to be picked at some point, but it's impossible to say when. I just do these one at a time. I've done 18 celebrities in about 9 months of training these models, and I think I've picked some good ones, but obviously I won't be able to do what everybody wants, so if any of you have a 12GB or larger GPU, I would encourage you to look into learning how to train your own models or at least LORAs.

Hey, you’re all good. I appreciate your work. You do you. I just wanted to see if she was on your radar at all. Thank!

 

[fudefrak]

Wasn't sure if I wanted to post this or not since she's not exactly a celebrity, but I did do a model for Cascina Caradonna. Youtuber/actress/musician, but most well known as being the face model for the character of Dina in The Last of Us 2. I'll put it in spoiler tags to avoid cluttering the thread.

Spoiler: Cascina Caradonna

 

[Sigmatorn]

Wasn't sure if I wanted to post this or not since she's not exactly a celebrity, but I did do a model for Cascina Caradonna. Youtuber/actress/musician, but most well known as being the face model for the character of Dina in The Last of Us 2. I'll put it in spoiler tags to avoid cluttering the thread.

Spoiler: Cascina Caradonna

View attachment 2286716View attachment 2286717View attachment 2286718View attachment 2286719View attachment 2286720View attachment 2286721View attachment 2286722View attachment 2286723View attachment 2286724View attachment 2286725View attachment 2286726View attachment 2286727View attachment 2286728View attachment 2286729View attachment 2286730View attachment 2286731View attachment 2286732View attachment 2286733View attachment 2286734View attachment 2286735View attachment 2286736View attachment 2286737View attachment 2286738View attachment 2286739View attachment 2286740View attachment 2286742View attachment 2286743View attachment 2286744View attachment 2286745View attachment 2286746View attachment 2286747View attachment 2286748View attachment 2286749View attachment 2286750View attachment 2286751View attachment 2286752View attachment 2286753View attachment 2286754View attachment 2286755View attachment 2286756View attachment 2286757

Are this models available to download?

 

[fudefrak]

Are this models available to download?

No, sorry

 

[fudefrak]

Hayley Williams

Honestly, this didn't turn out as well as I would have hoped. I probably needed more images to match the quality of some other the others, although I have done some models with similar number of pics that turned out better, so perhaps just with training more models and merging them together I can sort out some of the issues, but if not I do have some ideas to tweak my settings which shouldn't impact most celebrities with higher image counts, but may help a little for those with less. It's also just possible my dataset just may not have contained enough variety for the training to learn her face as well. It's nowhere near as bad as default Stable Diffusion, just not quite up to my standards. Although a few photos still looked pretty good.



Edit: Yeah, merging with a second model has seemed to improve the likeness quite a bit

 

[fudefrak]

The next celebrity I will be training a model from is Yvonne Strahovski

 

[fudefrak]

I was recreating my Emma Stone model yesterday after

You must be logged-in or registered for see links

, and I thought the results were a little underwhelming, so I decided to make the change to my training settings that I was considering earlier while training the Hayley Williams model, and the results turned out to be really good. You can see the new images posted after the edit in the

You must be logged-in or registered for see links

Spoiler: Technical details on what I did

Basically, I was modifying the number of training epochs based on the dataset size, with the idea that the more images in my dataset, the more blending of concepts start happening, so you shouldn't need as many epochs, as long as the total number of steps still increases. So basically, my training steps were calculated by the square root of the number of images, multiplied by a constant value of 2700, plus 5 epochs for warmup. So with 1396 images included in the dataset for Emma Stone (673 images of Emma and 723 nude/porn images) that was coming to 77 epochs. I think the main issue is that I use a polynomial learning rate scheduler, starting at a high learning rate and getting smaller and smaller each step, almost like an exponentially decaying learning rate, focusing on learning smaller and smaller details, to really get those precise details, and the problem is you don't get through as many epochs before the learning rate drops considerably if the total epochs is 77. So while the number of training steps total does increase with a bigger dataset, the number of epochs was decreasing by too much when datasets got too big. So I just went ahead and reset it to the more typical default of 100 epochs, with the first 5 epochs being the warmup, and the results were much better. 30% more training time (which can be hours) but it was worth it.

Of course I'll be resetting my Emma Stone model again whenever high quality Poor Things screencaps come out anyway, lol, but this will still be useful for other new models I train, or further revisions on existing models.

 

[SDMASTER]

Ana De Armas

 

[ishmael1978]

You must be logged-in or registered for see links

Any chance of a re-up? Thanks in advance

 

[teeny345]

Anyone got the taylor photos that have gone viral on X?

 

[fudefrak]

Sabrina Carpenter 2

 

[dovifo6483]

Jennifer Lopez