Sony Presents newest AAA game: DEAF STANDING. (AI generated)

db2 , 5 months ago

Don’t give them ideas…

0x4E4F , 5 months ago

Is it normal for AI to not spell correctly?

gibmiser OP , 5 months ago

The bing one does constant typos, but if you mean the your vs you’re I did that on purpose

0x4E4F , 5 months ago

No, I meant everything… but, it’s good to know that not all typos are AI made 😂.

Mr_Fish , 5 months ago

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.

ignotum , 5 months ago

Thus is the best text over seen a model generate thus far, the model i usually use generates text like this:

https://lemmy.world/pictrs/image/b4394bfe-27ae-4c6a-8981-c165d1eac311.jpeg

And the earlier versions of the models were even worse :P

0x4E4F , 5 months ago

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.

ignotum , 5 months ago

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

0x4E4F , 5 months ago

Damn graphics people are lazy 😂.

ignotum , 5 months ago

All people are lazy, work smart not hard and all that

0x4E4F , 5 months ago

While we’re at it, could you generate something for this?

!linuxwarez

I really have no idea how this AI image thing works 😂.

0x4E4F , 5 months ago

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.