This LoRA series (if I get back to it at all) is experimental. The entire training dataset is generated by me personally using artists tags and LoRAs I've created before. I'll be posting the styles I like here. Perhaps. Maybe.
DISCLAIMER.
These LoRAs are experimental and may have issues. However, they are reasonably workable, so you can give them a try.
More information about each LoRA will be in the ‘About this version’ section.
Have fun <3
Description
NoobAI-XL version. I can't really say anything new, except that this version is a bit more stable and similar to the style that was originally intended. Otherwise it's the same as the wai-illustrious version, so I'll copy the description from there.
For me, it's not a complete style. However, you can use it as such. I have trained it for use with artist tags/other styles.
Therefore, don't expect too much. I trained it as a support-LoRA for my ‘cute’ styles, yep.
Model Information:
In short, this model allows for slightly more rounded facial/eye features, thickened eyelashes, mixed linework, some flat colors.
You can enhance each effect with the tag ‘flat color’, ‘no lineart’ etc.
I recommend it to be used with artists tags.
The weight is adjustable as you wish. I work from 0.35 to 0.85. On average 0.65-0.8. In general, try it yourself.
Trained on the NoobAI-XL EPS version 1.1.
Works best with portraits/upper body.
If you're not happy with "round" eyes, then reduce weight/add "surprised" tag to negative/ add "half-closed eyes, narrowed eyes" to positive prompt.
Overall, I can't recommend it to you for use, but I will definitely use it myself :^)
FAQ
Comments (4)
"Perhaps. Maybe." killed me xD
Is it the style or else the color seems "yellowish".
所以哪怕作者销号跑路了模型文件也不会撤回？
When you delete a profile, they ask you if you want to keep the models. I decided to keep them because some people still use them.
So they give you a choice. I guess :^)