[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / 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
/3/ - 3DCG

Name
Options
Comment
Verification
4chan Pass users can bypass this verification. [Learn More] [Login]
File
  • Please read the Rules and FAQ before posting.

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]


[Advertise on 4chan]


File: 6nc0AkpHNq.png (789 KB, 1023x1265)
789 KB
789 KB PNG
This shit can't even generate cars for 3D blueprints, what are y'all worried about?

All of the AI today is 90% marketing and 10% functionality, most it can do is generate some references for you to use or retopologize if fine with the result
>>
>>1020056
>worried
im not, this is just a hobby to me
>should i be though
maybe. AI is shit now, but its stronger and older than you think. even before neural networks these kinds of systems and algorithms have been tweening and easing animations in 2d for over a decade now. Its easy to ignore little things like the automatic edge detection on your magic wand in photoshop, but how much of the work are you actually in control of using one click to pick all those unmatching pixels? do you know how retopo works, or how an automatic UV unwrap figures out where to put the islands?

that car looks like shit because they're trying to make a magic want that poofs a car from nothing, but if i were developing the tools i would be looking at something like a smart edge fixer or model symmetrizer, and when you have enough of those tools all chained together...

maybe we'll never get there, or maybe its easier than we think and we'll get there in a year. but if we do, and its anything like how 2d is used right now...
>>
>>1020056
Reminder that AI videos used to look like absolute comical shit that blended eyeballs together and made all limbs look like spaghetti before OpenAI accounted Sora 1. With AI it is 90% unpredictable, you can have a thing that you think it will never automate, or that the results are so bad it will take another decade, and then BOOM, some lab made model that blows your entire life journey out of water. The only 10% certainty we have is that all impressive and scary AI advancements had to have at least one dogshit model before that as a proof of concept.

You need AI that can get second place at math Olympiad before you get AI that can solve the millennium problem. You need a clumsy robot that can finally fold clothes properly before you get robot that can replace all trades. You need LLM that works as Stack Overflow replacement before you have AI agent that makes 99% of programmer obsolete. And this dogshit that people keep posting here, that makes kind of impressive looking high poly models that are textured terribly and have to be remodeled for proper retopology are the proof of concept AI 3D generators. This whole jobby is 1 breakthrough away from going the way of 2D animation with Sora 2.
>>
>>1020061
>do you know how retopo works, or how an automatic UV unwrap figures out where to put the islands
I do and they're not neural networks or any of that AI shit.

>>1020065
>just two more weeks bro I promise, burn another 5 billion $ please bro
laughable
>>
>>1020072
by the way AI now uses 2% of world's electricity, ain't that concerning, at least to someone?
>>
>>1020056
There's like five other AI threads you can go to for that shit, you waste of blender cubes



[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.