

Good Luck.
Good Luck.
The future is P2P
Anything can run on anything if you have enough storage. Computing power is not a problem if you don’t care about frame rate and resolution. We first jumped from 24 FPS to 30, next to 60 and soon we will jump to 120. We jumped from black and white to gray scale to colors, from 16 colors to 256 then to 16bit and so on. From 320x240 to 800x600 to 1024x768 to full hd to 4k and we’re near to 8k. Rendering speed is the real limit.
But they are literally killing people. I’m to scared to ask what is definition of “bad” by those delusional morons.
Like they know what they’re doing now. They combine 1-5TB of tokens with random numbers.
Only thing Artificial in AI are profits from companies that sell this shit or give that shit for free like drug dealers. Intelligence is stolen.
Waiting for first global suicide in the name of ChatGPT.
no shit Sherlock
download gimp, copy picture, replace head, they should ban youtube for showing those tutorials
https://www.youtube.com/watch?v=btc8uXTVggg
Can be also loras that doesn’t change the fact that those are not models. VAE is just easier to train. Also saying something is simple is very subjective.
Also ban photo editors because it’s lower margin of entry. Those are not models in first place but VAE that modify model output. To use it you need some sort of understanding how to connect correct VAE to correct models so you need to setup tools to do it or write code. If you can set up tools you can as well train your own VAE on any small subset of pictures of any person on any hardware in under an hour with those tools.
Not that I support generating naked pictures of people but this is how it works and has always worked. It’s not models ! https://en.wikipedia.org/wiki/Variational_autoencoder
He could say that he is doing AI research and AI training and reviews are just part of his scientific documentation.
They suppose to say they need more people to work because they get more calls because of executives decisions.