Y
Hacker News
new
|
ask
|
show
|
jobs
by
jetter
82 days ago
try modelrift.com ? Llms are bad at spatial understanding but you can steer them using annotated screenshots ("annotation mode" of modelrift) and get something working:
https://modelrift.com/models/cable-conceal-box-with-wall-mou...
https://modelrift.com/models/customizable-liquid-funnel