Hi there, this page will contain all the information you need about my Mirelia lora.

This lora is intended to help in the generation of Mirelia from "the rising of the shield hero" (aka "tate no yuusha no noriagari") and it was trained for 2 main reasons:

• the lack of understanding of the tag "mirelia q melromarc" by illustriousXL

• my intention of having a bunch of loras of the serie that were all at the same level.

This is a character lora, so the following sections will be structured as follows:

• A section containing the technical stuff.

• A section containing the tips and tricks.

• A section containing some tests.

• A brief summary.

Faq: Does this model support nsfw?

Short answer: Yes, and feel free to use this for that.

This model was trained on a dataset of 25 images of the highest quality available. The dataset was not conditioned by any data augmentation tecnique, and the training went on for about 11 epochs with 4 repeats each.

The Lora is intended to have 1 activation keyword, which will have a general feeling of the character and that will stabilize the tags "purple hair, purple eyes, jewelry, earrings, lipstick, crown, makeup," to make them reproduce the likeness of Mirelia.

The activation keyword is:

M1rellia

extra strongly suggested prompt:

purple hair, purple eyes, jewelry, earrings, lipstick, crown, makeup,

This lora is able to reproduce the Official outfit of the character, using the prompt:

dress, puffy sleeves

This lora has a moderate understanding of the anime style, so in some rare cases the tag "anime screenshot" ("anime coloring" could help aswell) might help reproduce the artstyle of the serie.

The model was trained on images that were mostly in the "landscape" resolution category, so it tends to perfomr better on orizontal images, but it has no major issues on vertical ones.

Due to the dataset, it is suggested to use the tag: "close-up" in the negative if it isn't needed.

The lora has no major bias conditions, except when it comes to the clothing.

The lora has a clear understanding of the character and her official attire, but it struggles a bit when it comes to change her clothing.Generally speaking you can lower the lora weight up to 0.6 without having any real character issue, at 0.6 it's very easy to change the outfit, but some "heavy" tags might require you to use a weight a little higher like 0.8 (an example of this is the image in the gallery with the gyaru tag).

if you need help with the general prompt, keeping in mind that i am not really a good prompter, you might try something like:

masterpiece, high quality, best quality, anime screenshot, <lora:m1rellia:1>
1girl, solo, m1rellia, purple hair, purple eyes, jewelry, earrings, lipstick, crown, makeup, {attire tags}, {actions and/or poses}, {indoors || outdoors}, {background description}

It's test times:

The test were all done using WAI-NSFW-illustrious-SDXL with the following settings:

steps: 28~32
cfg: ~6 ~ 6.4

when used adetailer:
model: ultrasharp
steps: 15
denoising: 0.25

• expressions test:

  it seems to support the whole range of emotions without any major tweaking needed.

• Clothing test:

  

  • the 1st image is the official outfit

  • the 2nd image is a random outfit (i've chosen a standard black shirt with a white skirt)

  • the 3rd test is a test to see if the lora reacts well to nsfw stuff (it is censored because this page is setted as a PG-page).

It seems that to change outfit it's needed to lower the weight to 0.6, and if you want to have no choker use the tag "choker" in the negative (or if you want to be even more sure you can use the tag "no_neckwear" in the positive)

So what are my toughts on this?

I am happy with the results, it's pretty flexible, it didn't cost me too much (i am talking about the time and resources needed), and even toh the dataset wasn't big, the result is pretty good.

This lora is part of my character loras collection you can find those in:

my profile -> collections.

faq: Will you train other characters from shield hero?

And at the time of writing i've already trained and tested few more loras from shield hero characters (malty, melty, fitoria), and those will be available pretty soon (maybe i'll publish them along with this one).
But considering that i am not intentioned to train loras for filo and raphtalia i guess i will stop (atleast for now) with those four characters. Maybe i will train glass and the other heroes in the future (but not any time soon).

That said, as always, i thank you for reading all this.

Remember if you like my work you can help me by following this account, publishing your content here, and share your works with your friends.

I hope you will find this helpfull and that i will see you for my next loras.