71–80 of 84 posts
This is using meshes which seem a lot easier, and I'm unsure who's working on BREP or at least models that have some feel for dimensions and physics.
ie It could still be meshes, but the designs would be physically reasonable like how a skilled tradesperson may make a device with their intuition without running FEA, etc.
I was able to use this to go from an AI generated image to 3d print. Steps documented here: https://x.com/ryanlanciaux/status/1866163343788007619
Earlier quoted context omitted.
> I want to walk worlds that arose in the minds of others, not just worlds A significant portion of game developers hate level design and the only reason they don't do procedural is because it's hard, so they are forced to build hand-crafted worlds. I'm one of those and I would find it pretty hilarious if anyone played my game thinking the levels "arose" in my mind, like I'm some kind of profound artist. I take great…
> A significant portion of game developers hate level design And that shows, that really, really shows :) Now they get to make even more of the soul-less trash in shorter time.. I'm not putting this tool down, it's an amazing technical achievement, and the results are absolutely mind-blowing, but, to me, it is what it is, and it's just like, my opinion, dude, not some statement of absolute truth. You hating level des…
Is it soulless when a sculptor doesn’t source their own clay and marble directly from the earth?
Or when a musician uses an instrument made by someone else, or a composer uses digital sounds recorded by someone else?
There are many different forms of artistic expression and many rely on relatively mechanical and “soulless” work being done for us by someone or something else.
Tools like this can open up new and creative world building options to people who previously didn’t have access to 3D models. It increases the opportunities for creative expression rather than diminishing them.
Earlier quoted context omitted.
> I want to walk worlds that arose in the minds of others, not just worlds A significant portion of game developers hate level design and the only reason they don't do procedural is because it's hard, so they are forced to build hand-crafted worlds. I'm one of those and I would find it pretty hilarious if anyone played my game thinking the levels "arose" in my mind, like I'm some kind of profound artist. I take great…
I poured ten years of my life into a open source game near nobody played. Screw all that handcrafted lovechild of artist-brain shit. My 2nd game was using store-assets and i was free to get things done.
Wow, that's amazing.. I think this is the first time I've felt sick to my stomach watching AI generated content.. A sadness rush over me. Because these look so good, like every soul-less super-high quality shovel-ware asset ever made. I'm not putting it down, it truly is an amazing achievement, and it feels like it marks the end of hand-made assets. I don't even feel bad for the artists, I just feel bad for myself, b…
Think of it this way: AAA games will now have to do something MORE than just "amazing graphics" in order to set themselves apart. Because if I'm honest, almost all of the newest games coming out is just the same gameplay + updated graphics. Well, guess what, very soon even I could do that. So what do these studios have in store to make us come back to them?
This shifts the attention to story development and away from graphic designers. It does not mean cheaper games. It means more successful indie games with fewer team members. It also means fewer games because as I understand it right now, the only reason new games are pumped out is to keep the larger industry perpetually employed and other more time consuming projects funded enough to be developed.
Earlier quoted context omitted.
>The next step is to automatically add "nodes" to the 3D images where the model can pivot, rotate and whatnot and then boom, you have on-demand animated, interactive content. The next step is to generate models with higher quality mesh topology that allows animation and editing without breaking the mesh. I've done a lot of retopologizing and if I (or AI) were to rig these models as-is there would be all kinds of shad…
Anywhere you'd recommend a hobbyist can learn more about remeshing or feature detection?
Anyone see anything like this for GenAI for BREP CAD? This is using meshes which seem a lot easier, and I'm unsure who's working on BREP or at least models that have some feel for dimensions and physics. ie It could still be meshes, but the designs would be physically reasonable like how a skilled tradesperson may make a device with their intuition without running FEA, etc.
With mesh faces now supported in BREP, I'm more optimistic about a mixed modeling approach, where you can do the braindead find-the-cylinders conversion but keep the rest mesh, not needing to force it into some eldritch contortion of BSurfs.