News for hackers. Stuff that matters.

A comment on Expressive Text-to-Image Generation with Rich Text. Parent comment

Re:Expressive Text-to-Image Generation with Rich Text by yorwba on Thursday October 05, 2023 @03:39AM (#37775831)
I get now that using the side-by-side "plain text"/"rich text" comparisons you're trying to highlight how similar they are, only differing in the regions that are annotated in the rich-text version. But my first impression was that you're comparing against a weak baseline, which doesn't look so good.

Not sure how this could be communicated better.

[ Parent | on HN ]
Re:Expressive Text-to-Image Generation with Rich Text by simbolit on Thursday October 05, 2023 @06:29AM (#37776870)
This!
[ Parent | on HN ]
Re:Expressive Text-to-Image Generation with Rich Text by jbhuang0604 on Thursday October 05, 2023 @08:08AM (#37777567)
Got it! Thanks for the feedback! This is definitely something we can improve.
[ Parent | on HN ]