164
So sad...
(hexbear.net)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 25 Oct 2023
164 points (100.0% liked)
the_dunk_tank
15916 readers
4 users here now
It's the dunk tank.
This is where you come to post big-brained hot takes by chuds, libs, or even fellow leftists, and tear them to itty-bitty pieces with precision dunkstrikes.
Rule 1: All posts must include links to the subject matter, and no identifying information should be redacted.
Rule 2: If your source is a reactionary website, please use archive.is instead of linking directly.
Rule 3: No sectarianism.
Rule 4: TERF/SWERFs Not Welcome
Rule 5: No ableism of any kind (that includes stuff like libt*rd)
Rule 6: Do not post fellow hexbears.
Rule 7: Do not individually target other instances' admins or moderators.
Rule 8: The subject of a post cannot be low hanging fruit, that is comments/posts made by a private person that have low amount of upvotes/likes/views. Comments/Posts made on other instances that are accessible from hexbear are an exception to this. Posts that do not meet this requirement can be posted to !shitreactionariessay@lemmygrad.ml
Rule 9: if you post ironic rage bait im going to make a personal visit to your house to make sure you never make this mistake again
founded 4 years ago
MODERATORS
There definitely is, and they've gotten much better. Notice how the focus of the image, the woman, is pretty good, and it gets worse and worse the further out from there. It's really, really hard for AI to do hands given how complex they are and how many poses they can take. Human artists struggle with them too.
Part of the reason is that while these things have billions of images in their training data, few to none of them have a focus on hands, and even fewer bother to describe hands at all. As far as any image AI can tell, a human hand has the following qualities: skin tone, some number of digits, and some number of fingernails. Except humans are crazy good at pattern recognition for hands, and hands are geometrically super complicated with a vast number of possible poses, orientations, lighting conditions, and, yeah, number of fingers.
they need to have an entire separate database that just trains on hands.