💌 Comments

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

I think it's a custom sleeveless Cheongsam with a heart-shaped cut on the chest to show the nipples 😛

I doubt that any of my works are chronological, this pic for example seems to be from the period when he worked on the Silk Road, I mean he's 800 years old and every 100 years becomes a boy again, so I bet there was a lot of things to tell.

Still wanna do more with his separation curse, just was looking at his 3 separation pics and thought they're not incredibly imaginative, just laying around while split in half, so was trying to think of something more interesting instead of making another one like that 😅

Thank you so much! I think it's the first time I put Yasha in a black rubbersuit, he always preferred something white... but as they say "once you go black, you never go back" 😜

Yeah I guess thats the only way to go beyond 360 degrees... looks like there's even room for more haha 😅

Very glad you liked it! Some of his hard-working friends must be wearing black belts by now but he's not in a hurry with the practice... the red belt is way prettier :D

谢谢
____
Thank you

Thank you so much!! I'm very happy you liked, also just noticed I did his shoulder wrong... or should I keep him armless? Hmm, an armless mage sounds interesting and I think gives more ideas for a story of why he decided to learn magic 😅

😝

😌

谢谢
____
Thank you

感谢
____
Thanks

Thank you so much! 😁

Should have saved that comment for my actual fanarts of Chat Noir 😂