Random Transformer Model News: Text2Human

[Undiscussed Horrific Abuse, One Victim of Many]

People abuse energy resources by avoiding the use of self-designing
algorithms in new ways every day.

I think it's cool that it looks like researchers are intentionally
hitting the uncanny valley now, instead of going for deceptive
realism. I think that's a really important cultural safety choice, one
of many things that many people will have thought of but that
crucially needs to be actually put in practice.

It's not that you can't make a clone of my wife: it's that it's rude, man.

https://github.com/yumingj/Text2Human

We synthesize full-body human images starting from a given human pose
with two dedicated steps. 1) With some texts describing the shapes of
clothes, the given human pose is first translated to a human parsing
map. 2) The final human image is then generated by providing the
system with more attributes about the textures of clothes.