Namecaller
Well-Known Member
Not to mention the Barbie fannies?
AI Generated Fake Celebrity Nudes (not deepnude/deepfake)
- Thread starter fudefrak
- Start date
My guess is those images likely used one of those models that takes one of the newer stable diffusion versions (2.x, XL) and tries to train it to allowing nudity. The problem is, those models are heavily censored unlike the 1.x models, so if you want to be successful, you will need a MASSIVE dataset of nude and porn images, very good captions for the images, and aggressive and lengthy training sessions. Lora also won't cut it.
These also don't seem to be trained to focus on the celebrities being generated here, so they have a poor likeness, unlike my models which were trained specifically on each individual celebrity, as well as a large collection of nude photoshoots and porn.
In my experience, the newer SD models are going to be more trouble than they're worth, until I'm able to get a more powerful GPU and increase the size of my nudity datasets. While the newer models can render higher resolutions with less need for upscaling, it's just going to take a LOT more work to train them to doing what we want with them to a quality level that is satisfying, so I'd rather focus on the older models and using careful ControlNet parameters to upscale the results. I specifically include a lot of closeup shots in my datasets because I think that will help with the details when rendering larger resolutions. Without those closeups, the model may not have a clear idea of what certain features look like at high resolutions. I do need to add some more closeups to focus more on hands and open mouths though I think.
That being said, I keep all of my dataset images in their highest resolution possible, so whenever I end up upgrading to a new GPU (could still be years away) I'll be able to start training with the new generation of models, and come up with training parameters that are aggressive and lengthy enough to work.
These also don't seem to be trained to focus on the celebrities being generated here, so they have a poor likeness, unlike my models which were trained specifically on each individual celebrity, as well as a large collection of nude photoshoots and porn.
In my experience, the newer SD models are going to be more trouble than they're worth, until I'm able to get a more powerful GPU and increase the size of my nudity datasets. While the newer models can render higher resolutions with less need for upscaling, it's just going to take a LOT more work to train them to doing what we want with them to a quality level that is satisfying, so I'd rather focus on the older models and using careful ControlNet parameters to upscale the results. I specifically include a lot of closeup shots in my datasets because I think that will help with the details when rendering larger resolutions. Without those closeups, the model may not have a clear idea of what certain features look like at high resolutions. I do need to add some more closeups to focus more on hands and open mouths though I think.
That being said, I keep all of my dataset images in their highest resolution possible, so whenever I end up upgrading to a new GPU (could still be years away) I'll be able to start training with the new generation of models, and come up with training parameters that are aggressive and lengthy enough to work.
LittleMouse1
Well-Known Member
This is my first post here, so apologies in advance if this is out of place. I have liked watching the growth of AI posts here. It seems to be one of the leading sites for quality stuff and realistic feedback.
This is my shot at Milana Vayntrub, in two photoshoots that started out legit and just went a little further.
This is my shot at Milana Vayntrub, in two photoshoots that started out legit and just went a little further.
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
You must be registered for see links
fappeningdandini
Well-Known Member
Great story telling, i really like the genuine/ai non-nude photoshoot which then leads onto fake/ai nude shots, but they all appear part of the same photoshoot
LittleMouse1
Well-Known Member
So, wow, you nailed that right out of the gate. Thank you for that. I'm not criticizing anyone with what I'm about to say. For me personally, I always have to know why the pics are happening or I have a hard time even trying to make them. My brain just gets into it if the content is somehow "believable." I don't know if that makes sense, since I don't think like other peeps.
Shoestring
Well-Known Member
Thanks for Alison. I'd never have thought of asking for her. But she's so cute she's a obvious choice.
NoahArketype
Member
Can I humbly request Jemima rooper and Angela Rayner please? Big thanks in advance.
Outstanding - thank you
Priesty_89
Active Member
Good man
Love these
| Thread starter | Similar threads | Forum | Replies | Date |
|---|---|---|---|---|
|
Random AI generated Pictures | Erotic / Porn / XXX | 3 | |
| N | Billie Eilish Deepfake Porns | Deepfake Porn | 0 | |
| S | Ai generated videos | Fake Celebrity Nude and Deepfakes | 0 | |
|
AI Generated Videos | Fake Celebrity Nude and Deepfakes | 2646 | |
|
PromptHub - AI Generated Celebs + Requests (Nude/NSFW) | Fake Celebrity Nude and Deepfakes | 153 |
