Home Creators Posts Import Register Favorites Logout

Content

At this point I think we all agree that AI is here to stay. As many of you guys know, I am an actual developer and have been for many years. Initially I think a lot of people in my field were really scared about LLM's "taking away our jorbs" because they are pretty good at transpiling spoken (well, written actually) English rulesets and specs into code that sort of works.

To be honest, they've only gotten better during the last year or so, although they've sort of plateaued - which is fine I guess, everything has diminishing returns so why should LLM's be any different?

Anyway, this post isn't about using generative AI to make code, or even using it to play the game with you or write dynamic scenes (although that might be fun hey?) It's about using a much older technology - StableDiffusion, to generate image content dynamically.

Now, this isn't to say that QoS is all of a sudden going to be riddled with AI images. Actually, the free and exclusive versions will remain 2D and based (at this point, somewhat loosely) on DAD - the Dynamic Avatar Drawer by PerplexedPeach. As you'll see from my latest release, I'm putting a LOT of effort into increasing that 2D experience and making it better.

HOWEVER... This:

Anyone who has played recent versions of FreeCitie's "PregMod" version will probably recognize some of the above screenshot. I'm basically putting StableDiffusion integration into the game - starting with ComfyUI. I'm going to be putting A LOT of work (and hilariously, burning a lot of AI credits) to create a smooth and easy to use surface here for people to try to use these tools to create their own visualizations for characters and scenes.

That's right, I'm not going to be adding shitty AI images to the game, YOU ARE.

Basically what I'm hoping to do is provide a really cool playground for people to experiment and enjoy themselves, maybe one handed. Wink wink.

Here's just some samples that the game made on the fly recently in different modes. This is VERY early days, but it shows the adapter is reading the game data and trying to generate the correct tokens to the models.

"Drawn" style, starting clothes on ship.

Same scene but with more masculine stats.

A "sissy" in the tavern.

On the ship, but more "bimbo" body stats.

Reprocessing the same scene but with body sliders jacked up

An early attempt to do the cooking scene.

I tried photorealistic but to be honest, unless I can find a LoRA for clothing or costumes, this just looks weird to me lol.

Anyway, as you can see. There's alot going on here. I wish the image gen was faster, but I'm going to be doing my best once I get this working to implement a system that is constantly processing thing smartly behind the scenes and trying to deliver images when you need them.

Files

Comments

Ronin

Whelp, I wanted to support because you didn’t use Ai, but now I’m gone. Too many of these games where the image generation is just bad.

Malhavok

I'm a big believer in personal freedom and personal choice. That's why I'm happy to give people the option to integrate 3rd party AI tools into the game if they choose to. I'm not personally going to ship any or generate any images myself and add them to the game, but I'm not going to tell someone to stop having fun the way that they want to. If you can't deal with it bro, keep your five bucks. Peace.

Ronin

Brother you have a good concept here, but Ai doesn't help your game, if anything it divides your attention from the game itself to an "upgrade" that people can do themselves for a system that has no creativity or value to the game itself. I remember I played this game 7 years ago, liked it and it definitely needs improvements. But you come back, update, and immediately switch into "Ai is the answer"??? Your biggest concerns should be increasing the quality of writing/scenes, improving the existing systems, and expanding from there. All this tells me is that there is a big red flag of a bunch of updates dedicated to 3rd party Ai software that doesn't actually address the game whatsoever, and in fact waters down it's concept and creativity into some data-center slop.

tenthsneeze

You need to chill out man having a optional extra thing that is "AI" on top of the game isn't that bad. this is going to be a optional way of engaging with the game you can just not choose to engage with it. Its weird when the dev gave a milquetoast opinion on it they clarified that the game is still overwhelmingly going to be using DAD. Personally for me stable diffusion isn't for me the uncanny valley makes me feel uncomfortable but as long as I don't have to engage with it I don't care.

Ronin

I’m not angry, I’m offering you constructive criticism, if you take that as an attack then I can’t help how you feel. But I’ve seen enough games to know the patterns now, trying to warn you this isn’t something worth investing in. At least not now. But if this is how you take it, then yeah, cya.

kielbasa

It does seem that this might only be used by the subset of people who have relatively modern mid tier and above GPUs.

Malhavok

I agree, it's definitely more nerd core, but I also expect that in the future it will get better/faster for people. I'm writing everything with an adapter, so hopefully as new locally run servers become available I just have to point Claude at the adapter and say, "make a new one like this for XX" I got really interested in this when I was playing FreeCities PregMod like last year and I thought it would be pretty easy to implement (I mean, if they can do it...) so I did it too.