
Andrea Intg.
@andreintg • 6,580 subscribers
game dev / tools - cofounder @unbound_io with @rianflo made @clayxels, @nauticrawl , and lots of failed stuff. ex DreamWorks, MPC VFX, Lionhead Studios
Shorts
Videos

I was a bit hesitant about showing stuff like this just a month ago 😅 When we started showcasing real-time AI + SDF sculpting, I was afraid professionals would laugh if I showed no effort on the input models. The shape strength slider was also hidden in our first iteration, so I had no choice but to at least try and knock some more interesting shapes together. Now that we're starting to focus on more powerful features and shape strength is finally unlocked, I'm starting to appreciate just playing with simple shapes. Different stages of production have different needs. Sometimes you want full authoring over your creations, while other times you just want to quickly explore new ideas.
Andrea Intg.342,959 görüntüleme • 3 ay önce

the way I see it it's ok if you don't have time for a donut tutorial or if your art teacher traumatised you and you need a bit of motivation 😌 If used right, this tech can be great for newcomers and handy for professionals. Building walls around it won't put it back in the box.
Andrea Intg.264,785 görüntüleme • 5 ay önce

We debated internally whether to delay Unbound's new product release a little longer to close the loop. I'm talking about this loop: Sculpt ➡️ Augment ➡️ Generate ➡️ Repeat. I was worried mesh-to-SDF would take too long, but Florian just went ahead and did the thing 😂 The video below shows a very common use case for why mesh-to-SDF is great for 3D gen. Removing and splitting parts exactly how you need them.
Andrea Intg.20,551 görüntüleme • 2 ay önce

"create assets in seconds" is an overhyped thing. The future shouldn't be about culling the process, as much as letting creators decide what they want to spend time on. (Unbound Loop low-poly 3D gen sneak peek at the end of the video) This bike didn't take seconds, it actually took a few minutes. Yeah it just has a handful of SDF primitives, but that's not even the point. I had an idea for this sci-fi bike that I wanted to explore. I cranked the AI slider, got some ideas, tried more combinations and then finally settled for the final design to generate the low-poly mesh. I enjoy exploring and creating, I don't want to give it up, I don't think anybody wants that. Having the possibility to get a boost from AI where and when is needed, that's the future direction I want for these kinds of tools.
Andrea Intg.10,104 görüntüleme • 1 ay önce
Daha fazla içerik yok.