This is pretty promising, just a few touch-ups and I'd be down with having it in-game.
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.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.
), so if people think the style is wrong / bad - please say so.
This is definitely cool of course there is no limit to perfection I like that the sporty style has not been lost after all, initially all the heroines had a sporty and drawn figure with a press, the main thing I want is if a game based on the kingdom of deception really appears, so fuck the orcs and their village with smelly tentsOkay I attempted to train my own "Momo 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..
- 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.
View attachment 3068253
I would say Neve doesn't look fierce enough. Sabia as well, but I feel like with her it's less of a problem but Neve was already highly confident and competent, and much more take-charge and domineering.Okay I attempted to train my own "Momo 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..
- 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.
You can also use the gallerys on e-hentai.org for the training of the Lora, you can pretty much find the entire KoD gallery there.Okay I attempted to train my own "Momo 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..
- 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.
View attachment 3068253
Hands aside i think this looks great, though fairly, Nomo is not good at drawing hands either. It feels like lot of progress is being made here, i look forward to where we get.
.
yo....This is not img2img.
I used the left one to generate a openpose rig - then used that rig to generate the right side images..
For those who don't use SD, the left image itself is not used at all to make the right one(s), I only used the left image to generate a skeleton rig which is basically a JSON file of lines that represent bones / fingers that can be used to pose characters, the pixels / original image is then thrown away, it's just a way to copy the pose, not the actual aesthetic.
Noxian Nights sequel?
There are small fixes / clean ups that could be done on the below images..
I was rushing a little because I'm trying to test how well the LORA works..
The goal should be:
- very consistent poses / facial expressions without relying on a crutch like img2img, because ideally you want to create multiple clothing types
- have very deterministic outcomes when you prompt or pose something, you don't want "randomness" coming through your LORA / Model otherwise it makes it very difficult to create assets.
View attachment 3069262 .
Sir, im gonna need you to post that LORA pls.This is not img2img.
I used the left one to generate a openpose rig - then used that rig to generate the right side images..
For those who don't use SD, the left image itself is not used at all to make the right one(s), I only used the left image to generate a skeleton rig which is basically a JSON file of lines that represent bones / fingers that can be used to pose characters, the pixels / original image is then thrown away, it's just a way to copy the pose, not the actual aesthetic.
Noxian Nights sequel?
There are small fixes / clean ups that could be done on the below images..
I was rushing a little because I'm trying to test how well the LORA works..
The goal should be:
- very consistent poses / facial expressions without relying on a crutch like img2img, because ideally you want to create multiple clothing types
- have very deterministic outcomes when you prompt or pose something, you don't want "randomness" coming through your LORA / Model otherwise it makes it very difficult to create assets.
View attachment 3069262 .
