[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


File: 1661898032623175.jpg (25 KB, 275x274)
25 KB JPG
How hard is to train a 3D low poly generator based on my own dataset of my own 3D low poly models I made over the years?
>>
>>108888171
>kmb fan
Hi again!
You're gonna need a lot more, billions must be used as ai food
>>
>>108888171
I don't know. But I'll bump this thread for you.
>>
>>108889086
this
>>
>>108888171
Right now impossible
>>
>>108892599
prove it digitsfag
>>
>>108888171
There are no known models capable of doing that at the moment. However, I am very strongly certain that is widely because of lack of funding in the area. I would think an af3-style model refurbed to 3d model generation should be able to do the task nowadays.
How many models do you have available though? Af is trained with ~250k quality models (and a bunch of trash on the side) but covers a lot more complicated things, so it should be possible to do it with 50k or maybe even less models to train on.
Other than that, go learn yourself some gnn stuff.



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.