Yeah, though would it be issue with the training data rather than the model? For example details on her hair and face are almost 10/10, and it’s not like those are easy to get right
I suppose you’d have to feed it a critical mass of every kind of detailed object. Which isn’t viable if you’re trying to create a general-purpose image or video generator. If you want to forgo perfection to get a product that’s just ‘good enough’ that’s what you’d do, and that’s what model trainers are doing.
Still can’t do hands.
if you cross your eyes and hit yourself in the head repeatedly they look fine
Or keyboards, apparently
Details are where most image gen models still lack understanding
Yeah, though would it be issue with the training data rather than the model? For example details on her hair and face are almost 10/10, and it’s not like those are easy to get right
I suppose you’d have to feed it a critical mass of every kind of detailed object. Which isn’t viable if you’re trying to create a general-purpose image or video generator. If you want to forgo perfection to get a product that’s just ‘good enough’ that’s what you’d do, and that’s what model trainers are doing.
they’re dreaming. Details are not necessary for dreams.
Dreams don’t make for a good product. Unless the models produce useful outputs, it’s either a research project or a waste of GPU/CPU cycles.
“product”
“useful”
“waste of GPU/CPU cycles”
we don’t speak the same language.
Oh didn’t they tell you? Making a profit is the most important thing in this world. Stop doing stuff that does not increase shareholder value!
There’s nothing to suggest they’re sentient, if that’s what you’re getting at.