discussion Viability of AI assets and interest in a High Quality AVN using them

[ZDaGoat]

My main rig is a 9800x3d with a 5090 and 64GB of memory, all tuned and overclocked/undervolted. I also have a second computer with a 5900x and a 3090 or 5070ti I could throw in that to do less intensive stuff if I get to that point. I'm a software developer, a pretty hardcore gamer, and I've been building PCs for over 25 years at this point so I've always had pretty high-end hardware.

I grabbed a few screenshots of some of the initial generations I did for the main girls, they are pretty early and this is without the trained LORAs, but here's a sneak peek:

You must be registered to see attachments

You must be registered to see attachments

First, it's great to find at least a few likeminded people who love to entertain the idea to use AI to create games. I think this will have a lot of future, but right now we are still in the pioneering phase. I hope you guys didn't mean my little game when you were talking about the latest AI slop games out there.

The issue is about consistency. I don't know if a Lora necessarily is the best way. I mean it has good performance once you trained it, but it never trains just the character, it always also trains a certain environment, style, clothing, .... unless you put a lot of work into the training.

With tools like Qwen Image Edit 2511 and maybe the upcoming generation of tools that will even top that, you can really create very good consistency just by working from very well done reference images and prompting the rest you want to have.

Also keep in mind the style of the game you want to make: In your reference images, at least the right one was highly realistic.
Dunno if that is what you really want to do. If so, keep going. As long as you don't dive into Sholi territory as I do, that's fine.

But once you decided for a style, you should try to stick with it. My game is lots of fun and has lots of potential, but it is still struggling from style inconsistencies due to changing models over the time i made it, and on top these video models kind of do what they want, in case you want more than just still images. In the future, maybe evolution cycles for such tools will slow down a bit, and you can resist the temptation to always go with the newest models.

DAZ and 3D are great in terms of consistency, but bad at animations and detailed lifely backgrounds. Maybe the best approach is combining both worlds, which Tieneretsu did for his game Girl Scout Island.

 

[NamoCQ]

A big thing for me is how inconsistent the current images I've seen are in ai games. They don't have to be this way. I would generate a good lora for every character first off. Then I'd generate your scenes separately and inpaint the characters or photoshop the 2 images together after generating. Also scenes with multiple characters are often messed up with loras. inpainting also solves this. Just these little steps and a non generic look would put you miles ahead of the competition.

 

[VNThrowaway]

First, it's great to find at least a few likeminded people who love to entertain the idea to use AI to create games. I think this will have a lot of future, but right now we are still in the pioneering phase. I hope you guys didn't mean my little game when you were talking about the latest AI slop games out there.

The issue is about consistency. I don't know if a Lora necessarily is the best way. I mean it has good performance once you trained it, but it never trains just the character, it always also trains a certain environment, style, clothing, .... unless you put a lot of work into the training.

With tools like Qwen Image Edit 2511 and maybe the upcoming generation of tools that will even top that, you can really create very good consistency just by working from very well done reference images and prompting the rest you want to have.

Also keep in mind the style of the game you want to make: In your reference images, at least the right one was highly realistic.
Dunno if that is what you really want to do. If so, keep going. As long as you don't dive into Sholi territory as I do, that's fine.

But once you decided for a style, you should try to stick with it. My game is lots of fun and has lots of potential, but it is still struggling from style inconsistencies due to changing models over the time i made it, and on top these video models kind of do what they want, in case you want more than just still images. In the future, maybe evolution cycles for such tools will slow down a bit, and you can resist the temptation to always go with the newest models.

DAZ and 3D are great in terms of consistency, but bad at animations and detailed lifely backgrounds. Maybe the best approach is combining both worlds, which Tieneretsu did for his game Girl Scout Island.

I completely understand where you're coming from, and I appreciate the opinion. My approach when I started was definitely that I was going to provide a bunch of info about my world/setting and the characters to an LLM for help creating prompts that I could use to generate image sets for each character that would have consistent styles, locations, their default outfits, and a variety of poses/expressions to train a Lora for each character as a baseline that would help me with a good amount of consistency I could then use to generate/edit assets.

Those images are my early attempts at generating characters, and I was going for a more photo-realism style that I've pretty much decided against at this point. Now I'm wanting a more stylized semi-realism because I am a little hesitant to make characters that look too much like real people. I've also learned a lot about how prompting works and how much control you have over the scene using JSON script with the models, so I don't think I need to go crazy with fine-tuning Loras as long as I have one with facial features/expressions for each character to help with generation/editing.

I haven't posted more, because at this point I've been learning so much that I've been focused on improving my knowledge about the various tools/models. I started out with image generation/editing, but I've also moved into voice/music/sound generation, animation, and I've even been exploring some pretty radical ideas of what might be possible with AI interaction.

I'm also starting to feel like rather than start out by re-imagining an existing (abandoned) game and sinking a bunch of time into a project that ultimately would never be fully "mine" that it's a better idea for me to just decide the kind of game I want to make and move forward with my own creation. I've had lots of ideas I wanted to pursue over the years, and if this is something I am going to sink a significant amount of my free time into then I'd like it to be something I can call my own.

p.s. I can't say anything about your game since I haven't played it, but I have no intention of venturing into the "plus" category. I will say though, that most of the games I've seen with AI animation have serious issues with consistency, to the point that the character's faces don't stay the same and many of them have issues with blurry motion and pixelation or weird proportions. It's definitely not easy to do well, that's why I'm spending so much time learning right now before I make a decision, and why I asked for opinions.

 

[DrPark]

If the quality is up there, I'm sure plenty of people will play it - AI or not. Also promising that you decided to use Astral Lust as a test-run. I really liked that one! Both the creepy setting and because it felt like an actual game.

In regards to ZDaGoat said about consistency: Yes. This is the main issue.
It's not difficult to make single images with AI that are difficult to distinguish from hand-crafted ones.
With some good workflows with ControlNet, LoRAs, etc. it's even reasonable to do so with decent enough control of the pose, character, setting, and style to generate entire image series that are convincing.
Where it really breaks down is consistency within a single scene. Have several pictures of 2 girls in the same scene but interacting (so some stuff changes) and the nightmare begins. The clothing is slightly different, the food on the dinner table is suddenly different dishes, bleed-through of prompting between multiple characters is always a PITA, size consistency where sometimes both are the same height, but then the next image different. Lighting and materials are a bit off. etc. etc.
This is a fundamental issue with AI image generation, that AFAIK nobody was able to truly solve yet - just mitigate (with significant effort).

Standalone each image is good, but as a consistent series? The differences really stand out.

That being said: Don't let that discourage you! If the game is good and the image are "good enough", most people won't care.

 

[dirtyjack74]

I will never intentionally play a game generated by AI prompts. There's no soul in it. I don't care about the "it's a tool" argument, i think it's a terrible thing for something that is meant to be relaxing in our free time, and it being degraded by an AI is just terrible

 

[darknesu]

My main rig is a 9800x3d with a 5090 and 64GB of memory, all tuned and overclocked/undervolted. I also have a second computer with a 5900x and a 3090 or 5070ti I could throw in that to do less intensive stuff if I get to that point. I'm a software developer, a pretty hardcore gamer, and I've been building PCs for over 25 years at this point so I've always had pretty high-end hardware.

I grabbed a few screenshots of some of the initial generations I did for the main girls, they are pretty early and this is without the trained LORAs, but here's a sneak peek:

You must be registered to see attachments

You must be registered to see attachments

Damn 2 years in LC and this is your first thread?

If you don't want it looking like those ai slop and actually sells just don't use raw generated assets right away

These actually look real enough like what

 

[miike]

I will never intentionally play a game generated by AI prompts. There's no soul in it. I don't care about the "it's a tool" argument, i think it's a terrible thing for something that is meant to be relaxing in our free time, and it being degraded by an AI is just terrible

Agreed 100%. When you remove an artistic barrier of entry for creation, it severely weakens that artform. AI is a cancer for art, in my opinion.

 

[VNThrowaway]

If the quality is up there, I'm sure plenty of people will play it - AI or not. Also promising that you decided to use Astral Lust as a test-run. I really liked that one! Both the creepy setting and because it felt like an actual game.

In regards to ZDaGoat said about consistency: Yes. This is the main issue.
It's not difficult to make single images with AI that are difficult to distinguish from hand-crafted ones.
With some good workflows with ControlNet, LoRAs, etc. it's even reasonable to do so with decent enough control of the pose, character, setting, and style to generate entire image series that are convincing.
Where it really breaks down is consistency within a single scene. Have several pictures of 2 girls in the same scene but interacting (so some stuff changes) and the nightmare begins. The clothing is slightly different, the food on the dinner table is suddenly different dishes, bleed-through of prompting between multiple characters is always a PITA, size consistency where sometimes both are the same height, but then the next image different. Lighting and materials are a bit off. etc. etc.
This is a fundamental issue with AI image generation, that AFAIK nobody was able to truly solve yet - just mitigate (with significant effort).

Standalone each image is good, but as a consistent series? The differences really stand out.

That being said: Don't let that discourage you! If the game is good and the image are "good enough", most people won't care.

That's where the process and approach I'm taking is *VERY* different from anything I've seen anyone else doing. Not only do I have the art and development background, but I'm really digging deep into how AI tools work and building my toolkit up from the ground. What a lot of people don't realize is that scripting is really powerful in image generation and editing both, using JSON as if you're writing a program can allow you to exert fine-control on a scene from the characters to the objects in specific parts of the scene, the camera lens/angle, the mood, etc.

Add in the ability to fine-tune LORAs to aid in consistency of both characters and environments and I think it's already very possible to achieve high degrees of accuracy. The problem as I've mentioned before is that there are huge barriers to entry in creating that level of quality, you need a background like mine, a willingness to spend hundreds of hours tinkering with (and often fixing) tools, learning not just how to use the models but understand how/why they function the way they do, and then you also need a cost prohibitive PC to even begin rendering at a decent enough speed to make it viable.

I've pivoted a bit because I started to find that some of the tools I want are clunky or don't work properly, so I've moved into agentic development and I'm currently working on creating my own tools and processes. It's not exactly what I planned, but I'm still really excited about where things stand with AI and I will definitely be moving forward with a project when I'm ready.

Post automatically merged: Wednesday at 9:23 PM

I will never intentionally play a game generated by AI prompts. There's no soul in it. I don't care about the "it's a tool" argument, i think it's a terrible thing for something that is meant to be relaxing in our free time, and it being degraded by an AI is just terrible

This is nonsense, plain and simple. You can "not care" about the "it's a tool" argument, but that doesn't change anything about the fact it's 100% true. If you look at AI games and feel they have "no soul" then that has nothing to do with the AI use, it is a failure on the part of the developer to create something that sparks a feeling inside you when you play it.

Not to be too harsh, because I know a lot of devs do this purely as a passion project for no real financial gain, but the overwhelming majority of games out there are trash or extremely derivative. Even the ones that *ARE* fun and reasonable quality mostly all look the same, use the same tropes, have no real world-building or character development, they just copy-paste the same arch-type characters into their chosen setting and write a snooze-fest of a story.

There are a rare handful of games that don't fall into that category and actually approach something I'd call an "experience". It's totally valid for you to not like AI or feel conflicted about it. I have an artist background and I definitely feel conflicted about it, because in some ways it invalidates the tens of thousands of hours I've spent drawing when someone can take a piece of reference art and generate something I spent a dozen hours working on in seconds... but at the same time I have dreamed my whole life about being able to craft a game experience that I can share with players to express the feelings and emotions I have felt when playing games.

Maybe I will never finish a game, maybe it won't have the impact I want it to for everyone even if I do, but that doesn't mean that I won't pour my heart and soul into creating something I can be proud of, and if I have to use AI in order to make that possible then no one has any right to tell me that what I've already spend hundreds of hours on just LEARNING and will spend thousands of hours on before it's finished has no soul.

That's just disrespectful, and I look forward to proving people like you wrong.

 

[dirtyjack74]

That's where the process and approach I'm taking is *VERY* different from anything I've seen anyone else doing. Not only do I have the art and development background, but I'm really digging deep into how AI tools work and building my toolkit up from the ground. What a lot of people don't realize is that scripting is really powerful in image generation and editing both, using JSON as if you're writing a program can allow you to exert fine-control on a scene from the characters to the objects in specific parts of the scene, the camera lens/angle, the mood, etc.

Add in the ability to fine-tune LORAs to aid in consistency of both characters and environments and I think it's already very possible to achieve high degrees of accuracy. The problem as I've mentioned before is that there are huge barriers to entry in creating that level of quality, you need a background like mine, a willingness to spend hundreds of hours tinkering with (and often fixing) tools, learning not just how to use the models but understand how/why they function the way they do, and then you also need a cost prohibitive PC to even begin rendering at a decent enough speed to make it viable.

I've pivoted a bit because I started to find that some of the tools I want are clunky or don't work properly, so I've moved into agentic development and I'm currently working on creating my own tools and processes. It's not exactly what I planned, but I'm still really excited about where things stand with AI and I will definitely be moving forward with a project when I'm ready.

Post automatically merged: Wednesday at 9:23 PM

This is nonsense, plain and simple. You can "not care" about the "it's a tool" argument, but that doesn't change anything about the fact it's 100% true. If you look at AI games and feel they have "no soul" then that has nothing to do with the AI use, it is a failure on the part of the developer to create something that sparks a feeling inside you when you play it.

Not to be too harsh, because I know a lot of devs do this purely as a passion project for no real financial gain, but the overwhelming majority of games out there are trash or extremely derivative. Even the ones that *ARE* fun and reasonable quality mostly all look the same, use the same tropes, have no real world-building or character development, they just copy-paste the same arch-type characters into their chosen setting and write a snooze-fest of a story.

There are a rare handful of games that don't fall into that category and actually approach something I'd call an "experience". It's totally valid for you to not like AI or feel conflicted about it. I have an artist background and I definitely feel conflicted about it, because in some ways it invalidates the tens of thousands of hours I've spent drawing when someone can take a piece of reference art and generate something I spent a dozen hours working on in seconds... but at the same time I have dreamed my whole life about being able to craft a game experience that I can share with players to express the feelings and emotions I have felt when playing games.

Maybe I will never finish a game, maybe it won't have the impact I want it to for everyone even if I do, but that doesn't mean that I won't pour my heart and soul into creating something I can be proud of, and if I have to use AI in order to make that possible then no one has any right to tell me that what I've already spend hundreds of hours on just LEARNING and will spend thousands of hours on before it's finished has no soul.

That's just disrespectful, and I look forward to proving people like you wrong.

The fact that you are defending using it for games, shows you have no real passion for what games are supposed to be. AI is a tool, to support development yes, but to use it as a primary way to develop a game, and using prompts to generate something that could've and should be done by hand is disgusting. I won't support it, or support idiots like you that want to try and defend the use of it for making slop.

 

[VNThrowaway]

The fact that you are defending using it for games, shows you have no real passion for what games are supposed to be. AI is a tool, to support development yes, but to use it as a primary way to develop a game, and using prompts to generate something that could've and should be done by hand is disgusting. I won't support it, or support idiots like you that want to try and defend the use of it for making slop.

Could and should have been done by hand? Your ignorance is showing, it's pretty clear you have no concept whatsoever of what it takes to develop a game or the number of hours it requires or the breadth of different skills.

Also, if I had to wager I bet you don't have the same level of "outrage" against games made with Honey Select, or generic DAZ models do you? Because if you don't then that's extremely hypocritical, since obviously anything that isn't 100% hand-drawn/rendered and animated has "no soul" right? Give me a break. Visual novels as a whole are 95% derivative, lazy trash.

If you honestly believe the effort, care and passion I'm approaching this with is "slop" then feel free to leave my thread and not come back, I could not care less about what you think.

 

[dirtyjack74]

Could and should have been done by hand? Your ignorance is showing, it's pretty clear you have no concept whatsoever of what it takes to develop a game or the number of hours it requires or the breadth of different skills.

Also, if I had to wager I bet you don't have the same level of "outrage" against games made with Honey Select, or generic DAZ models do you? Because if you don't then that's extremely hypocritical, since obviously anything that isn't 100% hand-drawn/rendered and animated has "no soul" right? Give me a break. Visual novels as a whole are 95% derivative, lazy trash.

If you honestly believe the effort, care and passion I'm approaching this with is "slop" then feel free to leave my thread and not come back, I could not care less about what you think.

You go on a public forum and talk about AI and are shocked when people don't like AI.

Grow up.

 

[DrPark]

That's where the process and approach I'm taking is *VERY* different from anything I've seen anyone else doing. Not only do I have the art and development background, but I'm really digging deep into how AI tools work and building my toolkit up from the ground. What a lot of people don't realize is that scripting is really powerful in image generation and editing both, using JSON as if you're writing a program can allow you to exert fine-control on a scene from the characters to the objects in specific parts of the scene, the camera lens/angle, the mood, etc.

Add in the ability to fine-tune LORAs to aid in consistency of both characters and environments and I think it's already very possible to achieve high degrees of accuracy. The problem as I've mentioned before is that there are huge barriers to entry in creating that level of quality, you need a background like mine, a willingness to spend hundreds of hours tinkering with (and often fixing) tools, learning not just how to use the models but understand how/why they function the way they do, and then you also need a cost prohibitive PC to even begin rendering at a decent enough speed to make it viable.

I think you miss my point about consistency here, which is inherent to the way AI / image gens work under the hood.
Yes, you can build a complex workflow in Comfy with refinement steps and all the jazz to create good output.
Yes, you can address this workflow via api to automate the settings and prompts with consistency.
Yes, you can pin the seeds of an image you like and then fuzz certain keywords with templates (wiggle weight a bit around, using similar but not identical wording) to get a bunch of variations and then pick something that really strikes your vision.
All of that *with* character LoRAs to support consistency.

But at the end of it: You have one image. That image may be great, but it's still only one.
The issue arises when you want to generate the next image in the same scene! New image depicting the same character (or worse: characters - plural), but from a different angle and pose.
Now you modify your base prompt so the main subject of the image goes from e.g. "neutral pose, curious expression" to "arms crossed, suspicious expression" or something along those lines.
You redo all the steps above and again get an image that is great on its own!

But once you compare both images, the inconsistencies will show: Maybe the buttons on her shirt are black in img1 but red in img2. The pattern of the skirt is slightly different. The glasses are rimmed in one while sleeker in the other. In the background the potted plant changed and other details are just... different. This gets worst if you have angle changes, you cant easily mask a small area to change but keep everything else static.

At that point you will need to let go of the perfectionist ambition to have it indistinguishable from a photo/render/whatever or you'll get nowhere.
Each image on it's own may reach that quality - but in a series the inconsistencies make it obvious.
That's just how AI image generation works under the hood.

I've pivoted a bit because I started to find that some of the tools I want are clunky or don't work properly, so I've moved into agentic development and I'm currently working on creating my own tools and processes. It's not exactly what I planned, but I'm still really excited about where things stand with AI and I will definitely be moving forward with a project when I'm ready.

Cool! If you find (or make) some neat harnesses to control the base-tools / workflows in a easy to use way (once setup) to really get productive churning out images, it'd be awesome if you share.
I'm mostly messing around with this topic out of interest in the tech w/o actually doing anything productive with it but I'm always curious to see different approaches.

 

[Oakbender]

I mean based on the examples you've shown the stills look great. The main challenge will be the consistency and keeping the artifacting in check especially if you decide to do animated scenes. Going for a realistic look like the examples you showed is going to trigger some real uncanny valley vibes if things move and warp weirdly.

But honestly if you manage to pull it off I'd be pretty impressed would generally be open to the idea.