💌 Comments

The images you see on the internet are from the TV series, as much as I understand the 3D animation technologies it's a normal thing to keep character designs very simple because practically every 3D animated cartoon has extremely simple toy-like characters. Maybe it's to avoid deformations and texture stretching, or maybe to avoid the uncanny valley by making characters toy-like to begin with, or maybe to easily make and sell figurines or... all of these things XD

Very glad you liked! Yeah, would make quite an exercise to twist with the big toys in, knowing Yasha is so into twisting it's surprising he's still not tried it!

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.

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...

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...