Forum Replies Created
-
Posts
-
i don't think there will be a G10 anytime soon, for now they are more than busy with DS6 aka 2025. it's still in alpha stage and we are at the end of august now, the pressure to get a proper release version out until 2025 is over must be huge. so they already have trouble with too much work, adding the development of a new figure on top wouldn't be smart at this point. i'm pretty sure G9 will stay at least another 2/3 years. on top are a huge amount of people who are still on G8, for them G9 is literally brand new ... adding another figure at this point wouldn't bring any benefit for the marketplace. another aspect is that a potential G10 would need something really new, something state of the art, which would give a reason to switch. something what G9 is lacking ... and that's something you don't develop alongside while your dev's have trouble getting the base program out of alpha stage.
@joem well said, it makes you feel like driving the car, while in fact just sitting on the back seat.
@legolas18
90 - 95% consistency (with luck) isn't enough and you will see that the last 10% will be incredibly hard to achieve, like the last 10% in quality/photorealism in 3D. that's exactly what it will make unusable for professionals and will break its neck. in the end AI will face the same problems as 3D, it needs computing power itself and if you want it to truly understand and rebuild 3D space it needs to do what current 3D programs do on top of its own computing. so it will need even more computing power than 3D programs alone.current 3D is still a approximation and simplification because of limited computing power and this will count for AI too. there is no magic bypass for AI if it comes to accuracy and in comparison you lack the amount of control over the result you have in 3D. the 90-95% consistency wobbly morphing like aesthetics of AI may be suitable for hobbyists, but not really for professionals.
by the way, if you want to see what 90-95% consistency mean search for “Create a replica of this image. Don’t change anything” AI trend ...
“Create a replica of this image. Don’t change anything” AI trend takes off
what brings us to the next problem, the web is flooded with imperfect AI content and sooner or later this will contaminate the AI training data itself and where this leads you can see in the example above. nevertheless, the coming years will be interesting ...
the way AI currently works will never give really consistent results across multiple shots or camera angles because for this AI would need a true understanding of 3D space and memorize a shier impossible amount of details. the way it works now is more like a very skilled cartoonist or painter with an incredible ability to observe and reproduce ...
to be able to really compete with 3D it would not only need to observe and recreate, it would need to understand the observation completely like we do when we see something and from that point we are still very far away. the main limitation for that is the same as for every 3D related stuff, the limited computing power of nowadays hardware.
absolutely pointless to compare AI to DAZ, all you can get out of AI is random "one takes" and if you try to achieve something specific and useful, meaning 100% consistent across several shots, angles, locations etc. then what ...
current AI is a toy for people with a very limited creative vision, the "make art" button for the lazy that don't know what they really want to achieve. it's good to surprise yourself with something, but god forbid you want something very specific.
AI won't replace 3D anytime soon ...
**''**NVIDIA has confirmed that support for Blackwell architecture GPUs begins with Iray 2024.1.0. The RTX 50 series are therefore not supported by earlier Iray versions like the one used in DAZ, which is Iray 2023.1.4**''**
but don't worry, they are already working on it at DAZ ...
you mean roblox cube, yeah ... if you need ugly, garbage, low poly models with the topology of a failed 3d-scan then that's the next big thing ...
It's no G9 issue, it's just created wrong ... which means the vendor doesn't care, or doesn't know how to do it right. In this case it's obvious that the rigging is messed up and since the eyes are locked to the head rigging, exchanging them doesn't change anything. G9 is a little more demanding for artist but if you know what you are doing, it's no magic to do it the right way ...
If it gets slow then in most cases it's the CPU fallback of iray, means your scene is to big for your VRAM. Install afterburner and check your VRAM and GPU utilization ...
well, some in here seems to have problems to distinguish between ideas and their technical realization. having ideas is easy, but make it work is a whole other thing ...
The end of structure shrinking in chips?
Of course, we are now at 5/4 nanometer and it's already getting more difficult to go smaller as we can see in less performance gain of newer generations of GPUs and CPUs. A silicon atom is 0.2 nanometers wide, which puts the gate length of 2 nanometers at roughly 10 silicon atoms across. At these scales, controlling the flow of electrons becomes increasingly more difficult as all kinds of quantum effects play themselves out within the transistor itself. The end of shrinking is between 2nm and 1nm and it isn't far away.
What world you live in?
We all know that what we as a public can buy today, are the left over pieces the industry developed many years ago.They never bring out their latest developments in consumer products, what we get today is already at least 10 years behind of what they are doing behind the scenes.
That's just bullshit, TSMC has just started 4nm production in January 2025 and current nvidia GPUs of the 50 series are manufactured in 5nm. As soon as a new manufacturing process is mature it's implemented everywhere ... 10 years behind LOL, of course they are already developing but what comes after (if ever) we reach 1 nm is completely unclear, mores law is already slowing down and you have to be blind to not recognize it.
Quantum computing ...
Quantum computing is fail, after fail, after fail ...
@mogli
From artist to artist, stop being ridiculous ...
@ADAM
I don't think AI is able to replace 3D Artists in the near future, because the limiting factor will be computing power. As we can see with the latest GPU generation, we're almost at the end of structure shrinking in chips and with that, computing power won't increase with the same speed as before which will affect AI development.
...