Neural networks in plain words
Short answers to the questions that come up in the first half hour of work. No jargon and no theory: only what changes your result.
What tokens are
Why one generation costs more than another and what to do when you run out of tokens.
First run
Four steps from an empty screen to a finished image.
What a prompt is
What a description is made of and why “beautiful” and “8k” do not work.
How a neural network works
Where the image comes from and why the result is different every time.