VN Ren'Py Kingdom of Deception [v0.14.2.2] [Hreinn Games]

[DreamingAway]

it isn't tho. with a few keywords it generates Sabia's exact hairstyle and body shape. I played with it for a while and I realized without ControlNet, the pics almost always need refining. it's especially bad at creating eyes. as you said, it's not that much focused one the style and more on the character.

They fully tagged the datasets. It doesn't understand other characters but you can make it do non-sabia prompts.

Some things seem undertagged like if you use her hair style the LORA wants to make it purple, you can change it in your prompt though.

 

[Retromancer]

Enjoy Hreinn hiring Lithuanian hitmen to hunt you down.

I had no idea Lithuanian hitmen were the terror of the continent. Live and learn, I guess. Your idea about making a little KoD minigame is intriguing. If I were an unemployed coder from Macedonia I might think about it.

 

[psycohunter96]

guys new "update" dropped if anyone can share i am in need of a good laught

 

[Jinsoyun]

guys new "update" dropped if anyone can share i am in need of a good laught

I can't read it, but at the start they mention the human brothel and the orc shopkeeper. Aren't those the content that were cut from 0.11 and 0.12 and never got made in the end? Did they finally got around to create them?

 

[CourierNPC]

AI is the hidden blessing out of all this

 

[DM933940]

It seams to me that people on this thread are making more content for the game than actual creators.

 

[zorin0815]

Second Attempt at trying to get Nomo's style.

That loks great.
Can you share your prompts and your SD-Setup Info?
I added the Lora and Checkpoints to my SD-setup, but the T2I generated images aren't very good.
thanks.

 

[Enigmanic]

It just goes to show.. if NDS and Monsinne were really interested in doing a good job on this game they could have at least explored the possibility of using AI while Nomo's sick.

..or they could actually learn how to write and code.

 

[Grozar]

Second Attempt at trying to get Nomo's style.

(Identical Control Net Pose, just seeding in different LORA combinations and swapping models)

View attachment 3063166

Amazing, Neve pls

 

[DreamingAway]

Who wants to make the Nomo Dataset?

 

[xhyde]

Does anyone have a link to the new update they finally put out? i know its not much but still like to see the used asset scenes they put out

 

[TERES]

 

[Bruh?OhmyGodgivemeauserna]

Second Attempt at trying to get Nomo's style.

(Identical Control Net Pose, just seeding in different LORA combinations and swapping models)

View attachment 3063166

prefer this to the original tbh, eyes might a bit too big, and her head might be too round making her look really young, but other than that, looks so good

 

[Bruh?OhmyGodgivemeauserna]

View attachment 3067421 View attachment 3067422

titties look a little too big, maybe making her more streamlined/naturally curvy?

 

[scheriel]

View attachment 3067421 View attachment 3067422

Oh just noticed that those were AI. Hands in the first picture are deformed

 

[BigBiggieBig]

View attachment 3067421 View attachment 3067422

This is pretty promising, just a few touch-ups and I'd be down with having it in-game.

Nomo can be replaced by robots.
The writer can be replaced by anyone who passed 3rd grade English.
And the coder can be replaced by a monkey paid for with two bananas a day.

I wonder if a surge in AI generated content of Sabia would make Hreinn worry enough to actually work on their game.

 

[scheriel]

I wonder if a surge in AI generated content of Sabia would make Hreinn worry enough to actually work on their game.

Hell no! They got some die hard fans still.

 

[DreamingAway]

If ~someone~ trained a "Nomo Art Style" and sent it to them, do you think they would use it or be offended?

Based on this thread, it seems their community is very ban happy.. is Nomo cold / callous to fans approaching them with new ideas / suggestions?

Looking through NN and KoD - it *seems* they don't really leverage "modular design" in their artwork very much, they will make swappable heads / clothes for important NPC's but it's very limited. Redrawing things from scratch is a progress killer and very laborious.

I feel like they would appreciate this technology more than anyone.. They could still exert creative control over everything but AI would do a lot of the repetitive tasks for them and probably help their motivation levels.

View attachment 3067421 View attachment 3067422

The hands need a little clean up. Even on the second image, her finger nails are trying to escape her body.

 

[Skarfaze]

If ~someone~ trained a "Nomo Art Style" and sent it to them, do you think they would use it or be offended?

Based on this thread, it seems their community is very ban happy.. is Nomo cold / callous to fans approaching them with new ideas / suggestions?

Looking through NN and KoD - it *seems* they don't really leverage "modular design" in their artwork very much, they will make swappable heads / clothes for important NPC's but it's very limited. Redrawing things from scratch is a progress killer and very laborious.

I feel like they would appreciate this technology more than anyone.. They could still exert creative control over everything but AI would do a lot of the repetitive tasks for them and probably help their motivation levels.




The hands need a little clean up. Even on the second image, her finger nails are trying to escape her body.

The entire discord server is very anti AI i believe , including the devs so i dont think they would take kindly to any such approach. No matter how foolish that seems it would only result in a swift ban i think.

 

[DreamingAway]

Okay I attempted to train my own "Nomo Style" LORA. (Using KOD / NN / Rule34)

It does not have any concepts of characters..
So there is no such thing as "Sabia" or "Neve" in the tagging, if you want those characters you have to describe them.

I did a few quick tests .. with the following rules:
- No Controlnets (meaning the poses are purely prompt based, each image may look slightly different)
- No image touchups or fixups or seed cherry picking
- No Segmenting (each image will have small variations, like clothing changes or background changes)

Known Issues So Far:
I can already see a problem with my tagging, I completely trashed "ponytail" with "folded ponytail" training. I will need to pick a single word tag that doesn't do that.


The image prompts left to right are:

[Describing Sabia as best I can]
[Describing Neve but with short hair and elf ears]
[Describing Neve but with short hair and cat ears]

The background is just "Sunny Day, Village, Huts, Grass"


Feedback appreciated - is the art style over cooked or under cooked?

I will likely need to do another run (or 10.. ), so if people think the style is wrong / bad - please say so.

- Focus criticism / feedbacl on the art style (both background & characters), the color palette, line work, shading style, etc.
- Ignore inconsistencies in height / clothing / pose. Those are fixed in a different way.