Yeah, that's basically it SlopFinder isnt defining slop, its trying to measure the perceived / averaged version of what humans call slop.
Kind of like human preference data: some of it's obviously objective (broken hands, logical inconsistency, obvious asset-flips like you mentioned), some of it's just taste (what's "enjoyable" varies person to person).
The dataset is the collection of a lot of different definitions like yours.
implemented almost all of these
This is growing pretty fast,I just uploaded another batch, theres now ~115 rows (before 85) ๐ฅ
I will soon make an upgrade for better batching + some big improvements (context & diversity) and maybe some visual upgrade, and maybe auto upload๐
I wonder what improvements you would like to see (maybe an API?) - tho its suposted not to be automated with AI, but voted by humans๐คท๐ป
Update: you can now also add custom conversations and score them!
You should check out benchlabs, we have great text to image models
Thank you for appreciation!
I agree, this is not super impressive, there's room for improvement, and the team will definitely work together to make a better model soon!
You should try it out in the meantime, and let us know for any improvements you'd like.
