(left) an image of a full glass of wine being handed to a tired disgruntled man on a sofa
(right) an image of a full glass of wine, being given by a woman with a TV head to a stout man looking at her angrily on a sofa, wide angle shot, scene from a sitcom
Huh, well that's a weird one. Also, wow I forgot how garish these AI images are with colours by default.
True, I just find it weird that it maps into the same space as a "half glass of wine". The "glass of wine" part is getting a disproportionate amount of attention that its adjectives, and perhaps rightly so, I guess I'm just surprised a little at the lack of imagination
The AI is technically correct: the container object is fully made of glass. It is then filled with a default amount of alcoholic beverage. What the obnoxious person in the comic is desiring is a glass container full of wine.
Thank you for coming to my shitpost. Click like and subscribe, follow me on digggg.
I guess this is the same reason Ai clocks are stuck on ten to two. In case of the clocks it is because ten to twolooks nice on a clock so most images will have it. Ai doesn't understand how time corresponds to how a clock looks, just that something that looks like a clock has two lines there.
So since most depictions of wine glasses are half full, when you ask for a wine glass it will give you one that is half full. Fill level being somewhat irrelevant as it wasn't part of the training data
This clock isn't, for example. Ackchually, I never noticed the artifact you're describing. Might depend on the model you're using, though. Generally speaking, I'd argue that AI depictions of clocks, as well as of hands, have improved as of recently.
10:08 is the other time that is often used for analog clocks in store displays, because like 1:50 it makes the hands into the shape of a check mark. My favorite though is when digital clocks are ALSO set to 10:08 as a reference to that even though there are no hands!