Who hard wired shoes with socks into the text to image generator (I am even in the right compunity?)
Who hard wired shoes with socks into the text to image generator (I am even in the right compunity?)
So yesterday no problem, Anti-Description: socks, but today any shoes have to have socks no matter where I try. Prompts tried: no socks; sockless. And the Anti-Description socks. A seed will generate properly but any prompt changes and socks magically appear.
I really don't think some one did it. The generator learnt it in the past day or so, and I want to know if i can get it to learn that socks and shoes are two independent things.
Thx for any help, even if it is to say I am in the wrong spot, or long winded.
4/6 outputs worked. You probably have to drill down into your prompts and figure out what is causing the problem. Juggle the priority of different terms. Those closest to the top of the list are emphasized by the AI. You can get drastically different renders by just rearranging prompts.
Also, neg prompts don't work the same as they did. They work, but not quite the same... I can't explain it any differently.