modelle/MGE Monster Girls - V5.2 - Illustrious

MGE Monster Girls - V5.2 - Illustrious

|
8/12/2025
|
4:08:03 AM
| Discussion

Empfohlene Prompts

1girl, best quality, masterpiece, absurdres

Empfohlene Negative Prompts

lowres, worst quality, low quality, bad anatomy, signature, watermark, Steps: 45, Seed: 518842312, Model: ntrMIXIllustriousXL_xiii, Model hash: 1207404b17, App: SD.Next, Version: c4ecee3, Backend: Diffusers, Pipeline: StableDiffusionXLPipeline, Parser: native, Operations: txt2img, LoRA networks: MGE_V5_2_IL

Empfohlene Parameter

samplers

DPM++ 2M, Euler

steps

28 - 100

cfg

5.8 - 6.5

resolution

832x1096, 832x1216, 896x1152

vae

sdxl_vae_fp16_fix.safetensors

other models

b3fecc91-fdbd-4876-beb5-732b20217480 (bd8754eea6df), MGE_V5.2_IL (bd8754ee), ntrMIXIllustriousXL_xiii (1207404b17)

Empfohlene Hires (Hochauflösungs-) Parameter

upscaler

R-ESRGAN 4x+ Anime6B

upscale

2

steps

35

denoising strength

0.35

Tipps

Refer to the detailed MGE monster girls taglist for more customization options.

Good results may require experimentation with different features and prompt combinations.

Respect original authors and avoid unauthorized commercial use of generated images.

Versions-Highlights

All of the changes from the Pony version of V5.2 apply, plus a few more minor changes. (I didn't want to spend an extra 4000-ish buzz on a retrain for the other version, but future versions should be identical.)

Differences from V5.2 Pony:

General Illustrious vs Pony observations:

  • Generally much more consistent, but in my experience requires more specific details to look good. I normally have to specify things like eye colour, facial expressions, arm positions and similar things with Illustrious to get a decent image, whereas Pony generally gives you decent ones with or without specification. With them though, the end result is almost always better with Illustrious.

  • Some styles work better with one, some with the other, although performance will vary with the specific model used regardless. Below is a list of all the styles that worked for each model. For Illustrious I used "NTR mix XIII" for testing, and for Pony I used "WAI-ANI-NSFW V12". (Mostly repeats, sorry. I can't change the colour of text in model updates, which is what I would've done to show version compatibility)

Illustrious:

  • MGE artstyle

  • CG artstyle

  • Merunyaa artstyle

  • Monorus artstyle

  • Barbariank artstyle

  • Sketch

  • Lineart

  • Pixel art

Pony:

  • MGE artstyle

  • CG artstyle

  • Merunyaa artstyle

  • Barbariank artstyle

  • Pixel art

Dataset changes (from V5.2 Pony):

  • Lilim horns aren't (as) broken this time, I removed too many images from the other version's dataset.

  • The "extremely long tongue" the karakasa-obake has been changed to "one tentacle" instead, and uses things like "loose tentacle hug" where appropriate. It still doesn't work to the extent I'd like, but the core features at-least appear now.

  • Separated a few species' ears using "floppy animal ears", where before things like "dog ears", "pig ears" and so on only used "animal ears".

  • Added "thick hair" to many of the slime girls, to give a bit more control over the hair design.

Last updated - 06/03/2025

Model description:

This is an attempt at an all-in-one lora for generating the monster girls of MGE, with a focus on customisability and being able to select the features you want individually. Refer to the taglist for more details, there's a lot of them. Not everything works perfectly, so good results may require a bit of experimentation at times.

Background info:

"MGE" Refers to the monster girl encyclopedia book series by Kenkou Cross. For more information, see the MGE wiki here.

"Non-entertainment" usage:

I've had my first question regarding legalities and commercial use, so: I am in no way affiliated with the creator, nor anyone involved in anything regarding MGE. This is a solo project, created solely for fun, which I've uploaded here because I assume other people will also enjoy using it. I haven't, nor do I intend to make any money with this beyond the buzz on this site, and I don't condone anyone else doing so*. I don't feel that strongly about it, and I appreciate being asked, just be aware that if you try I'm not getting involved in any disputes.

*So it turns out you can now exchange Buzz for real money... This section was written in the context of external projects like pay-walled Patreon content, or using generated images in larger "commercial projects", both due to a lack of legal knowledge, and feeling like it oversteps a boundary with my personal ethics. I don't intend to change my stance on this, as I think the negative online perception around generative AI stems from the immediate rush to monetise it, and I think most "ethical concerns" would have taken years to be brought up, if ever, if things like ChatGPT remained as niche research projects.

Actual artists:

If any artists dislike the idea of their stuff being used for this (and you've drawn things from MGE), let me know and I'll avoid your work. I understand that AI is a very divisive topic, and I didn't make this with the intention of pissing people off. As I don't intend to make money using my model, thid is more-so a thing for artstyles, because obviously impersonators will become harder to distinguish the better AI gets.

Reuploads:

I've decided to prevent unrequested reuploads of this (and my other stuff) on other sites as I've found the claiming process to be quite tedious, and there's little to no reason to allow it. I'll take direct requests for uploads, as if there's a reason to put it somewhere (say, for instance, a new startup has really good servers/features), then there’s a valid reason for doing so. I'm just not comfortable with stuff I've spent a significant amount of time making being spread to places I'm not aware of, nor people that did nothing to help benefitting from it. If you want to spread it elsewhere through links or something, go ahead, just don't reupload it to get yourself some free credits.

Zurück
Incase + gothic style mix | Illustrious - Illustrious
Weiter
Machigami Yoh | Shiiro's Styles - v1.0

Modell-Details

Modelltyp

LORA

Basismodell

Illustrious

Modellversion

V5.2 - Illustrious

Modell-Hash

2190655e7c

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.