AI generated fetish images

I am back with a new overpriced and even more power hungry gpu but more interestingly some AI advancements you can run at home as long as you have spent money on a gpu that is 😊

Let me introduce ControlNet. Its a new technique which allows the insertion of extra generation parameters in the form of images but not in the same way as img2img. Images are first run through a selected model to create said parameters, this can be a depth map, normal map, or even a detected pose as you can see from the example images on the github repo.

In my opinion the "openpose" detection is the most interesting and useful for generating realism with depth map being a close second. It allows you much more natural (or kinky) poses in generation without impacting the quality through a different method like basing a generation on img2img. You could even take a quick phone photo of yourself in the perfect pose you want to generate!

The next couple of years are going to be absolutely bonkers.
You won't be able to trust your own eyes.

I already don't trust them. I think of myself as someone with a pretty good eye for this sort of thing but I have second guessed multiple twitter posts recently.



There are still some tells here and there in my generations but I am confident I could fool the casual scroller which puts us into the "danger zone" as I like to call it. 99% of people aren't pixel peeping every image they see or zooming in on clothing straps to see if that's how they would really sit on someones shoulder. We have blown straight past uncanny valley and I have no idea where we ended up.

Within 40 seconds I am now able to create four photos that could pass as real photos as long as you don't start zooming in or pixel peeping which you can see below (I've also attached some latex ones just for fun)

   



Slightly off topic but there is an AI focused video from Tom Scott which really interested me and got me thinking about where we could end up. If you are browsing this thread it may also interest you. He mentions the sigmoid curve of tech development and I must wonder just where we are and where we will end up. It will be a very interesting year...

Source: https://www.youtube.com/watch?v=jPhJbKBuNnA

[Like Ra]

I am back with a new overpriced and even more power hungry gpu

What did you buy? I'm looking now at 4070, which is to be released in April. Nvidias with 12GB are expensive ... 😕

there is an AI focused video from Tom Scott
. . .
I removed the link because I'm not too sure how to get it to link but not embed the title is "I tried using AI. It scared me." for anyone interested)

Just post it, who cares about the title!

What did you buy? I'm looking now at 4070, which is to be released in April. Nvidias with 12GB  are expensive ... 😕

I went big and bought a 4090, its ridiculously fast and completely unnecessary. I wouldn't recommend it as a purchase to anyone unless you want to have the best of the best regardless of other factors.
I had an early model 3080 before so I wasn't really lacking in graphics power but the 10GB of VRAM was giving me a few issues even outside of AI generation. It still goes for quite a bit on ebay (only £70-80 less than what I paid for new two years ago!!) so I plan to put it up later this month or early march to offset some of the cost of the 4090.

Just as a speed comparison my 3080 would generate at ~15 it/s on DDIM 512x512 which was already really fast but the 4090 achieves ~32 it/s in single images and a technical ~48 it/s with a batch size of 4. The 24GB of VRAM lets me really push the resolution too without any performance degrading options.
Currently upgrading my PC into the "dream rig" but the final piece of the puzzle hasn't came out yet...

In my opinion the "openpose" detection is the most interesting and useful for generating realism with depth map being a close second. It allows you much more natural (or kinky) poses in generation without impacting the quality through a different method like basing a generation on img2img. You could even take a quick phone photo of yourself in the perfect pose you want to generate!

Here are a few non cherry picked openpose examples I generated on my own machine using images I found on google and this webui extension. The process goes as follows:
The input image is a pretty simple model pose:
   
The OpenPose model was able to create this pose map:
   
And finally SD was able to generate this image:
   


Overall generation quality still relies heavily on your model but gone are the days of trying to intricately craft a pose through a prompt. The only descriptor I gave in the prompt was "1girl" the rest was my cookie cutter base prompt with the quality keywords.
Seems ideal for getting tricky or unique bondage poses into generations without needing to spend time training that concept into the model

[Like Ra]

I went big and bought a 4090

YEAH!!! 👍 COOL!!!!!

Currently upgrading my PC into the "dream rig" but the final piece of the puzzle hasn't came out yet...

More info, please!

And finally SD was able to generate this image:

... whoa ... !!!!



And please keep the "how tos" coming!!!!

More info, please!

My current specs are:
Ryzen 9 3900x
32gb 3600 cl16
Nvidia RTX 4090
(I also have a spare "burner" AMD GPU for virtual machines and hackintosh, but that's not always running)

I've had some worries about my CPU performance for a while, specifically the single core performance, which was notoriously mediocre on that line of AMD chips. The arrival of the 4090 set it in stone. Even with a +500MHz all core overclock, the CPU just isn't fast enough to keep up, although it can still brute force its way through multicore workloads.
Initially I was thinking of buying a 5800x3d, stupid fast chip and cheap platform cost as I'm already on AM4, but I didn't want to lose cores even if it just was 4, and I wouldn't have any upgrade path in the future. Lucky for me and less so for my wallet AMD are releasing their AM5 x3d CPUs at the end of this month with higher end variants than a 800x part. They are releasing 900x and 950x variants which are both 12 and 16 core parts respectively. It does mean I need to buy a new motherboard and ram along with the CPU though...

The "dream rig" will be
Ryzen 9 7950x3d
64gb 6000 cl30
Nvidia RTX 4090

Right now, I can't think of better hardware or a use case I have which won't run on this PC, which is why I see it as the dream rig. I just need to patiently wait until launch day, so I can pick one up. I just hope CPU power requirements aren't too high, I've already seen my GPU alone draw 550W ❗ 

And please keep the "how tos" coming!!!!

Yeah, for sure I'll keep doing them when I find something interesting, as I enjoy exploring the bleeding edge anyway. I think they are closer to showcases rather than how tos although if anyone curious or stuck does need some guidance I would be happy to help so don't hesitate to ask.

Not too sure what to do next... You (or anyone else) have anything you would like to see? Could always do a realism tips and tricks post or do some training, although I'm not sure what to train either  I'm completely open to ideas.


Also about your 4070. Seems like a reasonable choice. Hard to say where it would land on a benchmark chart but I'm confident it would be able to comfortably generate and even train with optimizations with its 12gb (optimized repos are now just above 10GB which is great although the reduced memory usage does come at a performance cost). A used 3090 is always an option too if you really want that extra VRAM, they are still the go to choice for training. They pretty consistently go for £200 less than what I could buy a 4070ti for which is about where I would expect the 4070 to be priced.

[Like Ra]

nitially I was thinking of buying a 5800x3d, stupid fast chip and cheap platform cost as I'm already on AM4

That's why I bought a 5950X - second-hand, but sealed new. 16 cores, 5.2GHz.

I've already seen my GPU alone draw 550W

What is your PSU?

BTW, are you on Windows?

What is your PSU?

BTW, are you on Windows?

Corsair rm1000x so I have leeway as long as I don't have the AMD GPU going at the same time. OCP almost certainly wont trigger unless I get both GPUs and my CPU to spike at the same time but I would rather not risk that

I am not. Arch linux is my "default" operating system which I do almost everything on including AI but I do have a windows install for when I do windows based software dev or play games.

[Like Ra]

Corsair rm1000x

This one is a cool & quiet! I'm trying to choose between rm850x and the latest be quiet! Dark Power 13 850W. The latter is Titanium certified, and despite it does not have the fan-stop mode, it's almost absolutely quiet. So, I'm leaning towards the be quiet! one.

Arch linux

Oh, cool! I'm on Ubuntu. So, whatever works for you, should theoretically work for me (VRAM aside...)

This one is a cool & quiet! I'm trying to choose between rm850x and the latest be quiet! Dark Power 13 850W. The latter is Titanium certified, and despite it does not have the fan-stop mode, it's almost absolutely quiet. So, I'm leaning towards the be quiet! one.

I would pick the be quiet one as well

Oh, cool! I'm on Ubuntu. So, whatever works for you, should theoretically work for me (VRAM aside...)

Yep, linux gets most of the bleeding edge advancements/features first too so we are at an advantage 😊 I even run ~10% faster in generations than my friend with a 4090 and a faster cpu on windows although 29it/s to 32it/s isn't anything to write home about