[wruza]

Same with SD prompts and especially Lora training. The best thing you can do is to count any piece of information as clueless babbling best case and any result as a temporary niche result best case.

Because too much depends on randomness and accidental sources of randomness and in it there are whole pockets of multidimensional stability, just until you cross some invisible border you couldn’t even comprehend. This is a natural religion fuel.

So when you read any turorial, guide, best practice, etc, and there is not a hard proof of hours of thorough testing behind every claim, you may freely consider most claims religious, because they are.

[Iulioh]

I even remember the fact that a prompt for a CGPT app had a spelling mistake and some people were wondering if that spelling mistake performed better than the right spelling