Hi,
I am using Nanobanana 3 to make superheroes.
The first prompt creates too much lack of detail around the eye; so it is hard to see where the eye ends and where the skin begins - I hope that makes sense.
I solve it by using the output as a reference image into prompt 2:
"Good. Can the skin be more detailed. Can the lighting show less contrast on the skin?"
I wonder if you could have a sort of CLIPBOARD APPEND so that any prompt I do in my work, Nanobanana will append that extra instruction or even know to do a follow up batch task of doing the seconf generation for me?
Thanks