Industries first open source A.I. 3D world generation model

Oh shit, in the next decade I'll be able to tell AI the kind of game and game world I want and I'm off. Bye bye developers and your store front loaded with worthless pixels.

At least now, I'll be called a bigot, ists of every form, and phobes by a computer instead of other humans working for these companies. Win.
 
Last edited:
A GPU draws an image to your monitor as well when gaming. Why would it matter how that image is drawn? Processed by a GPU or processed by an AI?
Because whats gonna make this into a game, is interactivity. But if its just a render system, its not that interesting.

We need to see a character doing stuff in the game world, not just drawing graphics.
 
Oh shit, in the next decade I'll be able to tell AI the kind of game and game world I want and I'm off. Bye bye developers and your store front loaded with worthless pixels.

At least now, I'll be called a bigot, ists of every form, and phobes by a computer instead of other humans working for these companies. Win.
So, how exactly is AI going to give you the game exactly how you thought in your head? If you said I want a shooter in space and ends up cloning No Man's Sky or Starfield, or some weird hybrid of the two or any space game? what exactly are you going to do if it didn't design it the way "you" want it? You think it's going to give you the controls, the mechanics , the systems and somehow make it work for you? If not, will you just playtest your game until it finally give you something close to your prompt, or will you you just accept whatever it throws at you?
 
This is nuts.

We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image.

It's the industry's first open-source 3D world generation model, compatible with CG pipelines for full editability & simulation. Set to transform game development, VR, digital content creation and so on. Get started now👇🏻

Project Page:https://3d-models.hunyuan.tencent.com/world/
Try it now:https://3d.hunyuan.tencent.com/sceneTo3D
Github:https://github.com/Tencent-Hunyuan/HunyuanWorld-1.0
Hugging Face:https://huggingface.co/tencent/HunyuanWorld-1


Clearly smoke and mirrors.

The potential for tech in this space is industry re-defining. However this incarnation is fake as all fuck.

It seems to demonstrate such a severe perspective skew as the camera rotates, that it's as if it's not generating a 3D landscape at all but a simple spherical skybox.

There seems to be only partial scene elements generated into 3D objects but the rest seems to get baked flat into the skybox.

This seems almost entirely useless for a proper games development pipeline.

I think they'd be far better placed devoting time into developing the models to generating fully realised individual 3D props from reference images or text.

If they can get to the point where you can do that with fully realised rendering into a stable 3D model, with fully decomposed materials (albedo, specular, roughness, lightmaps, normals etc), complete with generated reference shaders, and could also cope with a very wide variety of visual styles (from super hi-fidelity UE5 PBR assets, to stylised Genshin style assets etc) then I think you'd have something truly epic indeed.

Imagine a production process that skips 3D modelling & rigging entirely, and jumping straight from concept artist output > AI 3D asset generation + unwrapping + rigging > a combo of AI-supported + hand-crafted/finessed animation work > designer placement and setup in the game > playtesting.

You'd literally save studios from having to pay for teams of 200-400 3D artists (in-house + offshore), in favour of a handful of "touch up" 3D artists to quality control + fine tune what's coming out of the AI pipeline. You'd also save incredible amounts of time, & allow for wildly more creative iteration, without significant costs for rework (since "pre-vis" asset work basically goes away, and you can master assets at a fraction of the time+cost of today).
Cost + time of 3D art + animation is probably the biggest, most influential factor to the reason modern games average ~5-8 year production cycles.

Imagine being able to collapse that entirely.

Finally, think about the control and empowerment this puts into the hands of indies...

A small independent team could make titles at the same or higher level of quality we see in the AAA arena today, providing them with far more leverage, more scope for risk taking and creative freedom, more opportunity to grow their businesses without selling their souls to greedy, malicious and risk averse publishers, in favour of $200m production financing contracts. They can retain IP control which means more control over profits, which will ultimately lead us to I hope another golden age of games made almost entirely by gamers for gamers (less IAPs, less gatcha, loot boxes, less GaaS and other bullshit purely financial data-lead trend-chasing), with significantly less influence from talentless bean counters in the equation.

A man can dream...
 
So, how exactly is AI going to give you the game exactly how you thought in your head? If you said I want a shooter in space and ends up cloning No Man's Sky or Starfield, or some weird hybrid of the two or any space game? what exactly are you going to do if it didn't design it the way "you" want it? You think it's going to give you the controls, the mechanics , the systems and somehow make it work for you? If not, will you just playtest your game until it finally give you something close to your prompt, or will you you just accept whatever it throws at you?
Seeing I haven't bought a game since Elden ring launch, I can wait plenty of time. The reason I don't want developers anymore is because they make you grind their trash to push you to their stores. So, no I won't be playing anything I am not interested in.

I got a couple decades left to breath fresh air, maybe, and plenty of patience to wait for a gaming crash. Or hell, I die and it doesn't matter.

I don't do the technical wizardry, I'm a consumer that has to be made happy to buy a product. This is a hobby that can be left behind just like any other hobby I have.

Also, play testing my own thought up game world and mechanics sound pretty sweet.
 
Seeing I haven't bought a game since Elden ring launch, I can wait plenty of time. The reason I don't want developers anymore is because they make you grind their trash to push you to their stores. So, no I won't be playing anything I am not interested in.

I got a couple decades left to breath fresh air, maybe, and plenty of patience to wait for a gaming crash. Or hell, I die and it doesn't matter.

I don't do the technical wizardry, I'm a consumer that has to be made happy to buy a product. This is a hobby that can be left behind just like any other hobby I have.

Also, play testing my own thought up game world and mechanics sound pretty sweet.

So you're ok with play testing which requires requires a significant of amount of grind to get it right but you also don't like grinding because it's trash, so which is it?
 
Last edited:
We will shortly be reaching the point where games that do NOT use AI will be labelled as such.

"This game was crafted entirely by original assets and art, no Artificial intelligence was used"

It could be a selling point or we could just reach a point where we accept AI art/assets etc. in every game and are happy enough with it.
AI won't just take jobs. It will shift the way people intake entertainment. What we are seeing now is surface level discovery of what is possible.

In terms of gaming, I see a dystopian future where games are being generated on the fly via an idea or prompt from a user. I see a pay per use model where everything is monetized. For example:
- (Pay per use) Want to use the likeness of a real actor
- (Pay per use) Want to use a specific artist vision (example: Kojima's visionary data source)
 
Last edited:
Stuff like this is going to decimate jobs in game development. It's going to be brutal. I wonder when we will see the first game completely generated by A.I.
Not a bad take but I see things on a more positive note.
Ai can address many of the current issue. Like development time.
The amount of big AAA game this gen are a it's lowest point ever.
It take so long that B teams are doing remaster to keep money coming in.
Dev are doing crunch
Price of games are going up

In the future I can see a ton of indie game size team with great ideas producing AAA game level within a year using Ai.
Price of games will go down and quality offering will go up.
 
I don't mind AI generated assets providing…

- they look high quality
- they perfectly match the artists intent
- they shave years off game development
This. I think that this could lead to a renaissance of game development. Right now, most games take the better part of a decade to make- or longer. Once upon a time, many developers and studios used to release a couple games a year. Now we are lucky if we get one game a generation from them.

Developing a game is such a long process now, and consequently, so cost prohibitive, that that very thing dictates an enormous part of the design itself. It has to be tailored to sell tens of millions or it could likely kill the team behind it.

I'm looking forward to an age where developers can make experimental and thought provoking games that push the medium forward without requiring 10 million sales to achieve profit.

AI is just a new scary boogeyman that we will all come to accept as a normal part of our daily lives soon enough.

I can hear the naysayers crowing about development losing its soul- let me ask you all this. When was the last time you sat down and hand wrote a letter to someone in cursive?

The written word, particularly cursive handwriting, used to be taught in schools and was held in people's eyes with a given level of esteem. That penmanship is all but dead now. Few people can even read cursive, much less write it. What about our very language losing its "soul?" And what contribution to it disappearing has your complacency amounted to?

This is an email world. Text messaging. Phone. Breakthrough internet communications device. And wide screen iPod. Or I guess I could like.. find some paper and a pen that works. Do I have an envelope and stamps? No? Ughhhh I guess I have to go to the store to get a fifty pack of each when I just need ONE.

It all comes down to:
aint nobody got time for that GIF


Decades from now our robot overlords people will look at the cro-magnon coding methods of writing and debugging code by hand that we employ today and balk.
 
If this is what a little team could achieve then imagine what Microsoft with OpenAI are cooking? I still see in OP video that it always looks a bit like image generated and many stretches when moving, but I guarantee someone is making a legit 3D world with actual geometry, no hallucinations.

More layoffs in the future, massives

In fact Jensen Huang a few days ago said that most peoples will lose jobs

So what happens then? If you don't have a strong UBI ala Star Trek, you just end up with hyper poverty

This is not a good thing.
 
We will shortly be reaching the point where games that do NOT use AI will be labelled as such.

"This game was crafted entirely by original assets and art, no Artificial intelligence was used"

It could be a selling point or we could just reach a point where we accept AI art/assets etc. in every game and are happy enough with it.
Yup.

As said elsewhere, digital art isn't worth shit anymore, I've been drawing for like 45 years, can't surpass AI now even if I spent a year on a drawing AI can spit out in a minute.
And AI for concept design is already used, guaranteed. But devs don't want to boast about it. If AI can be used to do 3D modelling as well it's kinda game over for regular artists.

Upside, should mean that games come out faster.

And AI still draw beautiful people. If you tell AI to draw a woman it'll be a pretty one. If you tell an artist to draw a woman it might look like a headswapped man because the artist is pushing a political agenda. Or it'll be an ugly woman because beautiful women are teh evil or whatever.
 
Last edited:
This. I think that this could lead to a renaissance of game development. Right now, most games take the better part of a decade to make- or longer. Once upon a time, many developers and studios used to release a couple games a year. Now we are lucky if we get one game a generation from them.

Developing a game is such a long process now, and consequently, so cost prohibitive, that that very thing dictates an enormous part of the design itself. It has to be tailored to sell tens of millions or it could likely kill the team behind it.

I'm looking forward to an age where developers can make experimental and thought provoking games that push the medium forward without requiring 10 million sales to achieve profit.

AI is just a new scary boogeyman that we will all come to accept as a normal part of our daily lives soon enough.

I can hear the naysayers crowing about development losing its soul- let me ask you all this. When was the last time you sat down and hand wrote a letter to someone in cursive?

The written word, particularly cursive handwriting, used to be taught in schools and was held in people's eyes with a given level of esteem. That penmanship is all but dead now. Few people can even read cursive, much less write it. What about our very language losing its "soul?" And what contribution to it disappearing has your complacency amounted to?

This is an email world. Text messaging. Phone. Breakthrough internet communications device. And wide screen iPod. Or I guess I could like.. find some paper and a pen that works. Do I have an envelope and stamps? No? Ughhhh I guess I have to go to the store to get a fifty pack of each when I just need ONE.

It all comes down to:
aint nobody got time for that GIF


Decades from now our robot overlords people will look at the cro-magnon coding methods of writing and debugging code by hand that we employ today and balk.
I bet all the coders and art designers at big companies are shitty bricks AI will take their jobs leaving the truly valuable people left.

But all the indie devs who already have low overhead and tiny budgets where a small number of people handle the entire game are probably loving AI. Who knows how good AI will go. But if it can help churn out some higher quality stuff they'd never be able to do that a fully stocked AAA game studio can do, they are loving the prospects.

No different than giant media corporations going down the tubes when the internet came about with free info, and the past 10-15 years with internet personalities on shoestring budgets can get more viewers time than media companies with billion dollar budgets in a skyscraper head office. They hate they are losing their grip to the avg joe or small scale company who got access to better tools.

If this was before the internet, you'd have all these big news corps being extremely profitable on TV, and every other house would subscribe to a newspaper delivery. Wow did all that change the past 20+ years.
 
Last edited:
I bet all the coders and art designers at big companies are shitty bricks AI will take their jobs leaving the truly valuable people left.

But all the indie devs who already have low overhead and tiny budgets where a small number of people handle the entire game are probably loving AI. Who knows how good AI will go. But if it can help churn out some higher quality stuff they'd never be able to do that a fully stocked AAA game studio can do, they are loving the prospects.
I'm thinking that China devs will embrace AI, or already is, and it could lead to more seemingly big budget releases.

The problem with AI is that it can't come up with unique ideas. It's all based on what is already out there.

On the other hand, most games now are an iteration of something already made.
 
I'm thinking that China devs will embrace AI, or already is, and it could lead to more seemingly big budget releases.

The problem with AI is that it can't come up with unique ideas. It's all based on what is already out there.

On the other hand, most games now are an iteration of something already made.
I wonder if we'll ever get to a point someone can just type in layman's terms lets say 30 bullet points of what they want..... WWII, bloody, realistic, FPS, TDM, 8 maps, bot mode, online mode etc.... And if I want to adjust some stuff, I just retype some stuff and the AI is smart enough to only change those variables. And it generates a game.

I saw that video of someone doing an AI game and it was a crude as NES game. I'm talking something with some half decent production values and gameplay.

And the AI tool will spit out a decent game. Not expecting perfection which would come from pro gaming employees. But no different than someone dabbling at home painting, I can dabble making my own game easy without needing to worry about real coding or making or finding free assets to manually add to the game.

And then I can upload this game and other people can try it too.
 
Last edited:
I wonder if we'll ever get to a point someone can just type in layman's terms lets say 30 bullet points of what they want..... WWII, bloody, realistic, FPS, TDM, 8 maps, bot mode, online mode etc.... And if I want to adjust some stuff, I just retype some stuff and the AI is smart enough to only change those variables. And it generates a game.

I saw that video of someone doing an AI game and it was a crude as NES game. I'm talking something with some half decent production values and gameplay.

And the AI tool will spit out a decent game. Not expecting perfection which would come from pro gaming employees. But no different than someone dabbling at home painting, I can dabble making my own game easy without needing to worry about real coding or making or finding free assets to manually add to the game.

And then I can upload this game and other people can try it too.
I definitely think we'll get there.

Through something like Unity you can already fairly easily make a platformer by using a 2D platformer template and then insert your own art. I'm doing exactly that. Crude and extremely basic but fun if you're a creative person.
Though you still need to code in C# for behaviors and tweak animations etc. But I can see AI doing that, you can add AI in Visual Studio for coding help. Not sure it can help out in detailed tasks but I haven't tried, could be possible.
 
So you're ok with play testing which requires requires a significant of amount of grind to get it right but you also don't like grinding because it's trash, so which is it?
Let me get this straight in my brain housing group. Your argument is that grinding to play test a game that you prompt to get it where you want it to be is the same as grinding what a developer purposely puts in a game to push you to buy their no value goods?

I'm not sure we live in the same world at this point. So to answer your questions, it's neither?
 
Last edited:
Stuff like this is going to decimate jobs in game development. It's going to be brutal. I wonder when we will see the first game completely generated by A.I.
Agreed, but it is also going to let single individuals and small teams to create games that they otherwise wouldn't have been able to before. It may lead to a renaissance in the indie market, but I expect the AAA market to just squander the advantages offered by better tools and churn out more large empty open worlds with checklist gameplay.
 
Last edited:
Stretched jpegs with no depth and no proper 3D models. Still a long way to go.

Before we generate satisfactory 3D environments, let's try generating satisfactory videos. There is already a lot of improvements to be done on this part.
 
Last edited:
Its not going anywhere and will speed things up exponentially.
I agree it's not going anywhere. We don't need things to speed up though. There's to many games coming out as is. Now we need them to come out faster which will just lead to even more games coming out. I play games all the time and I can't keep up.
 
These kinds of ideas come and go. Someday I hope it gets to a good quality and being faster than UE5 atleast.

Wasn't there somebody creating a south park world for unlimited tv shows, whatever happened to that?
 
Seems like natural progression. All of these will ultimately be tools to accelerate game development and give indies a massive boost to make games of much bigger scope. Not seeing the dystopia that people are so afraid about. If your 5 year development comes back down to 2, why is that so scary? Let's not get stupid thinking this will replace the need for humans altogether for good games. For making mindless slop, may be. Those humans needed to be replaced anyway.
 
Seems like natural progression. All of these will ultimately be tools to accelerate game development and give indies a massive boost to make games of much bigger scope. Not seeing the dystopia that people are so afraid about. If your 5 year development comes back down to 2, why is that so scary? Let's not get stupid thinking this will replace the need for humans altogether for good games. For making mindless slop, may be. Those humans needed to be replaced anyway.
Biggest scares come from people on the firing line. And big studios and corporations with tons of budget, resources, people, mocap rooms etc.... all getting squeezed because now some small studios or game made by 5 indie guys can use AI tools and perhaps make something bigger than they could realistically do without AI.

The biggest different to me between AAA games and indie games are production values, cost to make, and price to gamers. Not gameplay and definitely not fresh ideas. You'll never get a big company bothering making a Balatro, REPO, Terreria or a Minecraft back in the day.

If small budget games with often pixel shitty production values can amp up to something that looks and sounds better, IMO they got a lot more to gain than a AAA studio using AI to boost themselves up too.
 
Last edited:
Biggest scares come from people on the firing line. And big studios and corporations with tons of budget, resources, people, mocap rooms etc.... all getting squeezed because now some small studios or game made by 5 indie guys can use AI tools and perhaps make something bigger than they could realistically do without AI.

The biggest different to me between AAA games and indie games are production values, cost to make, and price to gamers. Not gameplay and definitely not fresh ideas. You'll never get a big company bothering making a Balatro, REPO, Terreria or a Minecraft back in the day.

If small budget games with often pixel shitty production values can amp up to something that looks and sounds better, IMO they got a lot more to gain than a AAA studio using AI to boost themselves up too.
Agreed. It will certainly level the playing field for Indie vs AAA in terms of scope and fidelity. For AAA, the benefit would simply be faster turnarounds, tighter budgets and fewer people needed to do the same job. Will that result in a dramatic reduction in workforce in the long term? I'm not too sure yet. In the short term, probably. But I think studios would realize that they could just multiply their output instead and re-hire. More games means more profit!

Having said that, there are some specific departments that will have an existential crisis, like voice acting, mocap, outsourced asset creation etc. Will have to see how that plays out.
 
Last edited:
One is that this will just feel "soulless" and devoid of any human creation and feeling.

As I said, prime time Ubisoft development.

I'm pretty sure that this will be used a lot for prof of concepts, to fast tracking projects, etc. but the final product will be "handmade" tailored.

Imagine a 3D Final Fantasy designed entirely from Yoshitaka Amano's art. You know... The one that Square never had the guts to do it.
 
Last edited:
Top Bottom