Re:Expressive Text-to-Image Generation with Rich Text
by simbolit on Wednesday October 04, 2023 @07:04PM
(#37772945)
if i understand it correctly, this is an a-priori mapping from font to style, the ml model doesn't interpret the font. I might be wrong tho, the paper isn't super clear.
Re:Expressive Text-to-Image Generation with Rich Text
by jbhuang0604 on Wednesday October 04, 2023 @09:35PM
(#37773950)
Yes, the particular font family was just a "label". We don't really interpret what that font style would look like.
For example, I'm wondering if a prompt written in Comic Sans should be turned into a comic-style illustration, or does it come out as a simplistic and childish drawing? Is a gothic font meant to imply a style of architecture, old Germanic peoples, or goth music and style?
See also https://design.tutsplus.com/articles/the-psychology-of-fonts...