Point and clicks have quite a few similar examples, the genre lends itself well to dioramas because even when it's 3D it's often a fixed camera path that you can optimize for.
Lumino City was the first one that came to mind for me as well!
The next one was the Fantasian, by the creators of Final Fantasy (https://youtu.be/ePFgyBtvqQU) - apparently this is finally coming to non-Apple platforms this year, at that.
Same, I was blown away watching the making of video (https://www.youtube.com/watch?v=NLv2uHxygc0) and discovering that these environments were created physically. The whole world had that soft handcrafted feel, and it turned out to stem from actual crafts!
It seems quite obvious that Gen AI will be a major change in the creation of game assets. If not stand-alone then certainly in the form of AIded (get it?) tooling. In particular there's huge potential for the indie market. If you're thinking about starting up a company, that's definitely a space where things are going to be hot IMO.
Every single game dev on Earth has been thinking that since the very first GANs, but the state of the art when it comes to generative AIs that are actually useful for asset generation is still pretty bad.
Much like LLMs are still pretty bad at logic. It seems like we're plateauing in that regard...
The thing about assets is that they have to be coherent with each other. You can't just generate them one at a time in a bunch of different styles and sizes or they'll look terrible. In the simplest case you want to generate at least an entire spritesheet for a single character or object. And that's still fundamentally impossible with modern generative AIs
I’ve been exploring this for a while. Icons are pretty solid with flux these days. Previous models struggled with this.
Sprite sheets are achievable or near achievable imo. SDXL was maybe good enough as a foundational model if you could leverage IPAdapter or a Lora to maintain character consistency. Although the former was never effectively tuned for styles I wanted and the latter requires some actual artist output still. Flux as a base model is far more consistent and has good enough controlnets to do sprite generation but probably still needs some a proper IPAdapter running to be stable enough for production.
Ideally it’s just a productivity tool for an actual artist
Consistency was for sure the biggest issue when I tried this approach last time. Also most of the images were a bit off, like having misaligned limb or some visual glitch. Sometimes fixing those details can be harder than drawing some crappy image from scratch.
I really wish there was a tool where I can select the theme, which objects I need and it would spit out some half decently looking art. I even don't care if it was some simplified, cookie-cutter art as long as it was low-effort and consistent. It could be a real time saver for prototyping.
I accidentally hovered my mouse cursor over the images, and saw a detailed description. It may have been generated by AI, but it's a nice touch that was not expected
Your game would go from playable on a smartphone to requiring an rtx 4090 and 64gb of RAM (ok, slight exaggeration). But it would certainly look amazing.
In true game dev fashion, I think parent meant to do the splatting once at build time, and runtime would just use the resulting data, rather than each scene load involving a dynamic "Splatting the gausses" in order to finish loading.
Oddly enough, some of Cliff Bleszinksi's first titles published by Epic (then Epic MegaGames) were point and click adventures like Palace of Deceit: The Dragon's Plight. They had MSPaint graphics and VB code.
This is a lovely continuation of that same tradition that takes full advantage of your analogue craftsmanship skills.
Point and clicks have quite a few similar examples, the genre lends itself well to dioramas because even when it's 3D it's often a fixed camera path that you can optimize for.
As an example, a nice looking one from a decade ago: https://store.steampowered.com/app/205020/Lumino_City/
Papetura also got a fair bit of attention for a while (for good reason, just look at it): https://youtu.be/ZVhtuKleLuI
Personally I love the hand-crafted "real" look these bring. It tends to consume a ton of disk space, but it looks good pretty much forever.
Lumino City was the first one that came to mind for me as well!
The next one was the Fantasian, by the creators of Final Fantasy (https://youtu.be/ePFgyBtvqQU) - apparently this is finally coming to non-Apple platforms this year, at that.
Same, I was blown away watching the making of video (https://www.youtube.com/watch?v=NLv2uHxygc0) and discovering that these environments were created physically. The whole world had that soft handcrafted feel, and it turned out to stem from actual crafts!
Same, it's such an amazing game. And the mobile port is great too.
Something similar was done for the 1996 game Creatures. A part of the diorama still survives and is on display at the Centre for Computing History in Cambridge (https://www.computinghistory.org.uk/det/42694/Creatures-Deve...).
Wow that's a blast from the past! 12 year old me was absolutely addicted to this game.
There was a nice game in this style called The Neverhood.
That game was made out of 3.5 tonns of clay.
The soundtrack for The Neverhood was also very nice.
It seems quite obvious that Gen AI will be a major change in the creation of game assets. If not stand-alone then certainly in the form of AIded (get it?) tooling. In particular there's huge potential for the indie market. If you're thinking about starting up a company, that's definitely a space where things are going to be hot IMO.
Every single game dev on Earth has been thinking that since the very first GANs, but the state of the art when it comes to generative AIs that are actually useful for asset generation is still pretty bad.
Much like LLMs are still pretty bad at logic. It seems like we're plateauing in that regard...
The thing about assets is that they have to be coherent with each other. You can't just generate them one at a time in a bunch of different styles and sizes or they'll look terrible. In the simplest case you want to generate at least an entire spritesheet for a single character or object. And that's still fundamentally impossible with modern generative AIs
I’ve been exploring this for a while. Icons are pretty solid with flux these days. Previous models struggled with this.
Sprite sheets are achievable or near achievable imo. SDXL was maybe good enough as a foundational model if you could leverage IPAdapter or a Lora to maintain character consistency. Although the former was never effectively tuned for styles I wanted and the latter requires some actual artist output still. Flux as a base model is far more consistent and has good enough controlnets to do sprite generation but probably still needs some a proper IPAdapter running to be stable enough for production.
Ideally it’s just a productivity tool for an actual artist
Consistency was for sure the biggest issue when I tried this approach last time. Also most of the images were a bit off, like having misaligned limb or some visual glitch. Sometimes fixing those details can be harder than drawing some crappy image from scratch.
I really wish there was a tool where I can select the theme, which objects I need and it would spit out some half decently looking art. I even don't care if it was some simplified, cookie-cutter art as long as it was low-effort and consistent. It could be a real time saver for prototyping.
I accidentally hovered my mouse cursor over the images, and saw a detailed description. It may have been generated by AI, but it's a nice touch that was not expected
You could do gaussian splat on the diorama picture and you can have pretty good dynamic camera movements where the player could walk around
Your game would go from playable on a smartphone to requiring an rtx 4090 and 64gb of RAM (ok, slight exaggeration). But it would certainly look amazing.
In true game dev fashion, I think parent meant to do the splatting once at build time, and runtime would just use the resulting data, rather than each scene load involving a dynamic "Splatting the gausses" in order to finish loading.
Oddly enough, some of Cliff Bleszinksi's first titles published by Epic (then Epic MegaGames) were point and click adventures like Palace of Deceit: The Dragon's Plight. They had MSPaint graphics and VB code.
This is a lovely continuation of that same tradition that takes full advantage of your analogue craftsmanship skills.
Engine nille nth 3oeuuendfnx