Yeah, it's pretty normal for image generation. It has no real understanding of language. All it knows is, "This shape is often near this shape." Honestly, it's surprising that nearly all the shapes in these are actually letters, even if they're in the wrong order. You'll often see half of a letter missing, two letters merged, or other weird letter-like shapes.
Thus is the best text over seen a model generate thus far, the model i usually use generates text like this:
And the earlier versions of the models were even worse :P
Why not just make it generate the image and you add in the text. It's far simpler than generating the entire image yourself, the text alone is like an hour, tops, in Photoshop.
Yeah if i was going to make something like this i'd just add the text myself, would be convenient if the models eventually got good enough to make the finished thing in a single step though
Damn graphics people are lazy 😂.
All people are lazy, work smart not hard and all that
While we're at it, could you generate something for this?
I really have no idea how this AI image thing works 😂.
Why not just make it generate the image and you add in the text. It's far simpler than generating the entire image yourself, the text alone is like an hour, tops, in Photoshop.
The bing one does constant typos, but if you mean the your vs you're I did that on purpose
No, I meant everything... but, it's good to know that not all typos are AI made 😂.
Is it normal for AI to not spell correctly?
Yeah, it's pretty normal for image generation. It has no real understanding of language. All it knows is, "This shape is often near this shape." Honestly, it's surprising that nearly all the shapes in these are actually letters, even if they're in the wrong order. You'll often see half of a letter missing, two letters merged, or other weird letter-like shapes.
Thus is the best text over seen a model generate thus far, the model i usually use generates text like this:
And the earlier versions of the models were even worse :P
Why not just make it generate the image and you add in the text. It's far simpler than generating the entire image yourself, the text alone is like an hour, tops, in Photoshop.
Yeah if i was going to make something like this i'd just add the text myself, would be convenient if the models eventually got good enough to make the finished thing in a single step though
Damn graphics people are lazy 😂.
All people are lazy, work smart not hard and all that
While we're at it, could you generate something for this?
!linuxwarez@lemmy.dbzer0.com
I really have no idea how this AI image thing works 😂.
Why not just make it generate the image and you add in the text. It's far simpler than generating the entire image yourself, the text alone is like an hour, tops, in Photoshop.
The bing one does constant typos, but if you mean the your vs you're I did that on purpose
No, I meant everything... but, it's good to know that not all typos are AI made 😂.
Don't give them ideas...