💌 Comments

Oooo tentacleporn *o* Looking forward to the humanboy too! About making more pictures of the same character, not sure how are you going to achieve that with AI... I tried to repeat the character from here and make another pic of him but to achieve that I had to design the whole character in Daz Studio and base it on a 3D render. But never know, maybe you have some ideas... :P

Well I didn't like that his face looked super unfamiliar, so I fixed it. At first I just thought "maybe it's okay" but nope, just didn't feel right and the stare was way too intrusive too. Now it's more neutral and much more familiar.

The tiger looks really good, the muscles, the legs and the patterns, as well as the hair, all makes an amazing character that you instantly want to see more of! He made me think of one of the hookers from Daniel Parker's underworld, a sexy and popular one who likes to do yoga and stretching on webcam to find clients. His room looks just like that, of course it's only a wallpaper plus some purple lights but at least the sexy boy is more than real! You should really give him a name and maybe mention him in one of Daniel's future stories :d

The swamp spirit... would have a lot to discuss with my lake boy. Reminded me of those athletic boys who have really slim waists, looking really thin from the side view but more broad and muscled from the front view. Swimmer boys often have bodies like that I think... Also not sure why he's a swamp spirit, looks more like a tropical fish spirit to me, standing in the lake near a dark forest. The pattern is interesting, was unable to google a real fish with a similar pattern but pretty sure it must exist somewhere.

Thanks! I'm very happy that you thought of this image, I also updated it a bit since the last time, not just the face to look more like Yasha but the details around the waist, a nicer volume for the lower belly and the ribs looking better :3

Other characters must be so mad at Yasha, not only he has every single bone and joint in his body at 400-500% hypermobility, but now can wear a wrist watch on his waist! Something about Yasha is so suspicious, maybe he is indeed a guest from the future like his newest picture suggests :D

The previous version was watches, but this one is a fitness bracelet... :P

By the way I made an archive of my installation of InvokeAI, all you need is create C:\InvokeAI (will NOT work from other directories), unzip, run download_models.bat and make sure it downloads everything successfully and re-run if it gets stuck at 0% or fails. Once all checksums match, try run.bat right away, ideally should just work... Can try update.bat later to get new github updates if needed, it should also work but who knows... mega.nz/file/aJRznD5B#ctzPBHn1TP9TL78vJqaaPrI7eJDSTmsETKQfXZFcEHs

I think it's simple to explain the way I already did with the y=sin(x) example, this function is periodic, meaning it gives the exact same results when x=0° and x=360°, so we only need to consider the period from 0° to 360° when making a neuronet for it. If we make 4 neurons to approximate sin(x) and train it, we get

x1=0°; y1=0
x2=90°; y2=1
x3=180°; y3=0
x4=270°; y4=-1

How do we get those "y1" etc? The training algorithm just generates any random number and stores in y1, then it generates another random number but only stores it in y1 if the new random number is closer to sin(0°) than what's already stored. It keeps doing that over and over, and after many training steps it gets super close to the value y1=0 simply by random guessing.

This is a super simple model, only 4 neurons, but it already lets us calculate sin(x) with some very basic precision. They're called "neurons" because the numbers they contain are not hard-coded by humans but obtained throught the process of training.

Now if we want sin(45°), 45° is halfway between 0° and 90°, so we need to apply the weight 0.5 to y1 and y2, so the result is

sin(45°) = 0.5*y1 + 0.5*y2 = 0.5*0 + 0.5*1 = 0.5

The real value of sin(45°) is 0.707, so not bad for only 4 neurons. With 8 neurons it would be a whole lot more precise, 64 neurons would be probably enough for most needs, unless the use case is heavily dependent on precision. So just a table of 64 numbers and you no longer need that heavy sin(x) function that takes a lot of CPU time to calculate, now you can get the result instantly.

The data in the AI model is stored in a similar way, so it doesn't matter how many images you use to train it, they don't enlarge the model, they just change the numbers stored in the neurons, while the count of neurons is fixed. The more images you use and more training steps, the more precise model you get. For example if we only used 10-15 training steps in the 4 neurons above, we wouldn't get a very precise sin(x) model, it would be very random, noisy... So more training steps help to fine-tune the model, get it closer to the original "source", while only storing it in the form of neurons.

They allocated 4 GB of neurons because that's how much you can fit into most of modern video cards, they could have easily made it 16 GB, it would be way more precise but very few people in the world could use it. Video cards are much faster as they have 8000 (for example) cores that can calculate things at the same time while CPU has only 16 cores for example.

But this is the stuff I learned as a schoolboy in the 90s, so I only know how to make a neuronet for the sin(x), don't ask me how to make a neuronet that can draw boys and tigers XD But I heard it's something based on gradients and vectors...

It's also hard to say what the future will be, but I think it's obvious that the AI works better with some base, so probably the tools will be developed to provide better base images to the algorithms so they could finally do poses, hands, etc. Right now it can be somewhat done, but takes a lot of manual work that all seems like it could be done automatically. OR maybe they will do something completely different again that nobody expects and will be way better than expected XD

Big plans for the little navel 😜

The Mysterious Island holds many secrets, maybe like Lovecraft had that city that gave people insanity, this island gives people masturbatory insanity XD The very air smells of fish... the balls getting painfully big like potatoes if not emptied frequently... on top of it cum is incredibly delicious after a lot of sun and tropical diet... oh the whorror! XD

Thank you so much! It was one of very early pictures, still can't believe how much time it took, over 12 hours, but of course nothing compared to how long it would take to paint it in real life, not even counting many years in art academy and a time machine to travel back to the 19th century Europe because I doubt it's possible to learn a classical style like this in any modern art school...

The twist was the most difficult part, many layers of cloth and a lot of guessing how to make it more twisted... But I think the legs were just as difficult, specially making both legs look more or less the same... But in the end was worth all the time, because really enjoyed the ideal 180° twist, almost like the woman keeps telling him to keep his chest and butt straight and stop tilting them, and the boy looks so focused and determined to be perfect...

This picture also started as another homage to Alexey based on one of his famous pictures but it went so far from the original...

Thank you! I was thinking if he got a red belt, would want to see their boys who have black belts 😜 Always loved the idea of tight-belted martial arts, almost as nice as belted bellydancing...

Glad you enjoyed the story! I'm trying to gather new ideas for the lore from everywhere: comments, my own stories, even AI art 😄 I mean I wasn't even thinking about it before this picture but now can imagine a whole monastery of dedicated wasped monks...

Well I shared it just because I liked the result... This photograph of Alexey always reminded me of an oil painting, so was very happy that it was possible to make this version of it...

Alexey in contortion is like Mozart in music, much like Mozart he was already making world-famous masterpieces at a very young age, so if I only could, I would of course make a real oil painting but unfortunately I'm not a 19th century painter and didn't graduate an art academy...

Hands are such a give away 😂 In the future there will be Anti-AI police who will be checking every picture's hands, if the hands are bad it will be insta-banned...

AI art: "I trained my hands for 6 months, learned to do them perfectly... But in the end I got a combo with an unusual pose I wasn't trained for... And they caught me!" 🤣

Haha, so glad it was funny! I just thought it's amusing that every time I run some AI updates and launch it, I always test it with the simple prompt "cat" 😂 So I thought why not take my limited imagination and make some actual pictures with cats already... or even tigers 😜

Bet he went to Heaven ONLY to get a smooth crotch before going to Hell for the main fun :D