The AI images we rejected turned out to be useful references. We showed the model what to avoid alo
The AI images we rejected turned out to be useful references. We showed the model what to avoid alongside the style we wanted and our first-try success rate went from around 5% to over 95%. I didn’t expect that much of a difference. Try it with a few of your rejected images. Just label them clearly as examples to avoid. #short
Discussion
Rejoignez la communauté pour réagir et poser vos questions.
Aucun message pour l'instant. Lancez la discussion !