If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊
This model was trained using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai
Checkpoint used in examples:
model.ckpt · a1079602570/animefull-final-pruned at main (huggingface.co)
I am once again open for suggestions for other styles, SFW and NSFW.
You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated. No guarantees but if it interests me I'll give it a go.
About the artist:
Newgrounds: introspurt (newgrounds.com)
Hentai Foundry: introspurt's Profile - Hentai Foundry (hentai-foundry.com)
Introspurt is mostly known for creating the Crimson Keep game, an ongoing turn based hentai rpg with 7 chapters to date.
There is an abundance of monster girls and nudity with a cartoony artstyle.
Weights & Prompts
Update:
I've added another version trained on anyLoRA. With the same training parameters it turned out considerably worse than the animefull variant. I'd recommend sticking to that unless you are only using anyLoRA.
The activation prompt is:
introspurtThe dataset is almost exclusively nsfw content which in turn means that a lot of nsfw prompts work better than with the base model. Skin color is also a lot more flexible due to the different monster girls. Male characters are severely underrepresented so expect lower quality when they are the focus.
Use a weight of 0.7-1.2, adjust to taste and depending on your checkpoint. Many checkpoints only work at a lower weight than the 1.0 I used.
As usual I have included an XYZ plot for reference.
Please leave a review if you enjoyed this model or have problems with it. This helps me with improving future models and finetuning them in general. Give it a try and throw some images down below! 👇
Description
FAQ
Comments (7)
Hello there, i hereby come with another suggestion:
I'd like to see an artstyle from KadaburaDraws, she's an awesome artist that does really cool surreal art and stuff.
i'd be more interested if you did her 2.5D style she tends to do.
- https://www.kadaburadraws.com/3d-art
if you want to check out other art though, she also does pixel art and line art.
- https://twitter.com/KadaburaDraws/media
That actually looks pretty damn cool.
I kinda doubt that this would work particularly well with the checkpoints I normally use and there aren't a lot of images at a glance, but I'll definitely give it a try.
It's always surprising how versatile the supposed anime checkpoint is for sd1.5
As I expected, the incredibly small sample size didn't help. So don't expect too much. Still gonna do the 2D model though. Really like the vibe of the minimalist inhuman creatures.
Although those images also have the problem that they are segmented and each part is lower res than 512x512
Hello, i have five suggestions they are mainly doujin artists, but the last one is mainly a animation artist but he still does arts.
1- Ydoujin/Yamamoto
https://e-hentai.org/tag/artist:yamamoto
2- Naruho Doujin
https://twitter.com/naruhodo0130
https://e-hentai.org/tag/group:naruho-dou
3- Rikka Kai
https://e-hentai.org/tag/rikka+kai
4- Mark Gavatino
https://twitter.com/MarkGavatino
5- Cartoonsaur
https://rule34.xxx/index.php?page=post&s=list&tags=cartoonsaur+
https://twitter.com/cartoonsaur
Maybe one of them will be of interest to you.
At best I'll give Mark Gavatino a try. The others are pretty ugly in my opinion 😅
But thanks for adding links to these.
Hi, I have some suggestions of some artists that are either not on this page or outdated
Zyugoya:https://nozomi.la/search.html?q=zyugoya#1
Ray-kbys:https://nozomi.la/search.html?q=ray-kbys#1
Ryokucha michi:https://nozomi.la/search.html?q=ryokucha_michi
Zyugoya looks fun. Reminds me a bit of Karasu-chan.



















