Grlee
New Member
why do their faces look like that, such a demonic look
AI Generated Fake Celebrity Nudes (not deepnude/deepfake)
- Thread starter fudefrak
- Start date
This was a much older AI tool that I haven't used in a long time. I kept those posts up for comparison purposes, but most of them are not great.
Grlee
New Member
what are you using now, and how can i get a hold of it, i have a couple of pics id like to try that AI on.
As explained in the first post, I now train my own models. I start with a variation of Stable Diffusion called Realistic Vision, and I train it using hundreds of images of the celebrity, plus hundreds of images of nude woman and porn. Every one of the images used in training has been personally gathered by myself. I either crop the images to a square, or shrink the image somewhat to fit inside a square, and I type my own descriptions of every image. Then training typically takes anywhere from 8 to 10 hours on my GPU, for a single iteration. I often go back and re-train these models, and average them with my existing trained models for even better accuracy. I try to gather at least 25 images every night for my dataset, so it can take a couple of weeks sometimes before I have a new model ready, but I'm always training new iterations of existing models every night if I don't have a new model to train yet.
Unfortunately, these models are 4GB each, so I won't be uploading them anywhere, but you're free to experiment with learning how to train models yourself. Beware, you really need a 12GB+ GPU in order to do what I do. There are some methods that use less, but the quality is not as good.
Also, note that using it on existing pics would be a "deepnude" which has a thread over here. I also use these models to make deepnudes from time to time.
Last edited:
I've noticed something while setting up my datasets that has caused me to start over with some models. When I started I would just describe everything, be as detailed as possible, hoping that the more information I provide, the more concepts the AI can learn, and this is technically true, but if you don't plan to use as many words when prompting this can become an issue. Like, I would describe when an outfit was tight and was showing off the shape of their boobs or butt, but then I learned that the model did a poor job learning the shape of their body without including words like that in my prompt. Same thing for if I mentioned that an outfit showed cleavage, where some models were only learning the correct shape of their boobs when associated with the word cleavage, which I obviously wouldn't use when describing someone who is naked.
Another one I've noticed that it's a good idea not to describe is hair style, length, and color, UNLESS it's specifically in a style or color that you don't want the AI to ever automatically generate without you specifying it, like for example with Karen Gillan looking bald, or Katy Perry with short blonde hair, or Taylor Swift when she went platinum blonde. Personally, I didn't like those styles as much as their other looks, so I'd prefer for those styles to only be generated if I specifically mention them. So I've been going back through my datasets, trimming them down, and retraining models, and I think the results are better than they were before.
Rachel McAdams is a good example where I did both of these things. Especially with her hair, since she's often switched between blonde and brown hair, and some red, and so I've let the model learn all of those styles in context with her name, so that the model will decide which hairstyle to use when, based on the context of the rest of the picture, rather than needing to specify it myself, which I think is pretty cool.
By the way, for those wondering, my next model will be Emma Watson. I've gathered almost 200 images so far but still have a lot to go.
EDIT: Oh and another thing I learned to stop mentioning was if they were smiling, because then the generated images never had a smile unless I specified it. Now the models learn when it makes sense for them to smile or make other facial expressions, rather than needing to specify it
Another one I've noticed that it's a good idea not to describe is hair style, length, and color, UNLESS it's specifically in a style or color that you don't want the AI to ever automatically generate without you specifying it, like for example with Karen Gillan looking bald, or Katy Perry with short blonde hair, or Taylor Swift when she went platinum blonde. Personally, I didn't like those styles as much as their other looks, so I'd prefer for those styles to only be generated if I specifically mention them. So I've been going back through my datasets, trimming them down, and retraining models, and I think the results are better than they were before.
Rachel McAdams is a good example where I did both of these things. Especially with her hair, since she's often switched between blonde and brown hair, and some red, and so I've let the model learn all of those styles in context with her name, so that the model will decide which hairstyle to use when, based on the context of the rest of the picture, rather than needing to specify it myself, which I think is pretty cool.
By the way, for those wondering, my next model will be Emma Watson. I've gathered almost 200 images so far but still have a lot to go.
EDIT: Oh and another thing I learned to stop mentioning was if they were smiling, because then the generated images never had a smile unless I specified it. Now the models learn when it makes sense for them to smile or make other facial expressions, rather than needing to specify it
Last edited:
This isn't the thread for deepfake/deepnudes. There are other threads for that. This is for photos generated entirely with AI.
I'd say the post above yours looks like it doesn't belong here either, as it does look like a deepnude to me.
PongoBanks
Well-Known Member
You've perfectly captured her absolutely dead eyes
bleepedyblorpedy
New Member
Do Elisabeth Moss and Jessica Pare! Your work is outstanding!
Craigechanning10
New Member
These are amazing! How did you make them? Is it using an app?
Craigechanning10
New Member
Can you please make some of Antonella Roccuzzo (Messi’s wife). She’s so underrated
No, the AI models I use aren't public. I train my own models by finding hundreds of pictures of the celebrity, fitting each image to square dimensions either by cropping or by adding borders. I also have hundreds of images of naked women and various porn positions and did the same for those photos too. I run them through a training process using Dreambooth, which creates a custom AI model, specifically tuned to generate that particular celebrity. I often then repeat this process multiple times and average the models together to improve the accuracy over time, although I have recently restarted that process after making some changes to the captions in the dataset, so this particular Kate Beckinsale is two models merged together. In the past I've gone up to 6, and which each merge, the accuracy to their likeness tends to improve, but further models are especially important for certain types of images too, as one or two models merged together tend not to be as reliable for certain prompts.
I generate using the Stable Diffusion WebUI, using my own GPU. All of my models start with RealisticVision 5.1 as a base, but the final models I make are considerably better for the particular celebrity I'm focused on.
I have a list of 507 celebrities that I choose from, by running a quick tournament by myself each time I'm ready to start grabbing more images. The whole process from grabbing the first image to generating the first model can potentially take weeks, depending on how many images I need to gather and how much free time I have each night. Right now I'm working on Emma Watson for my next model. I've gathered over 300 images so far, but it feels like there may still be a lot more I will be grabbing before I feel like I have everything I want from my sources.
Unfortunately, I'm not very familiar with that person, or the ones requested by bleepedyblorpedy above, so I won't be adding them to my list right now, and even if I did, I'd probably never get to them because I have so many more people I'm interested in creating AI models for.
Last edited:
Craigechanning10
New Member
Okay understood. Are you able to add Dua Lipa or Hailey Bieber to the list if they’re not already on there?
They are on the list
JigglyMuffin
Active Member
quite the process, how well does it fare with multiple celebs at once. to generate group pictures?
Wow, that’s some dedication! So at what point did your hobby become your job and your job become your hobby
