Making LoRA's is a thing I do for fun. So if you like what I do? You can help me out by just using the LoRA and leaving a review!

📷 This LoRA has been mostly trained on in-game screencaps, but also some artwork from booru sites.

This LoRA does not have a character trigger word, this will provide you with more flexibility. Take a look at the trigger words at the panel to the right, or the images I've provived how to prompt this LoRA. You're free to remove keywords from the provided trigger words, that just gives you flexibility in how you want to promt the LoRA, in e.g. what she wears. I've provided the given trigger words as a base set. E.g. if you want to have her wear a different outfit, remove her base outfit keywords.

👉 From my testing she's really flexible to prompt. When you ommit parts of her outfit from her trigger words, that will allow you to replace it with some other outfit of your choosing, or rather not have her wear it. But because of this flexibility you must also be specific in your prompting. Meaning e.g. don't prompt for her black thighhighs, if you want to only see her upper body. Another example is don't prompt for her eyes if you're prompting for from behind and don't actually want to see her eyes. Because this LoRA is trained so much on all aspects of her, these are things to take into consideration. TL;DR don't be contradicting in your prompting.

All WAI-NSFW-illustrious-SDXL sample images used the following setting:

• Hires. fix,

  • Upscaler: R-ESRGAN 4x+ Anime6B

  • Steps: 15

  • Denoising: 0.3/0.4

  • Scale factor: 1.5

All NoobAI-XL (v-prediction model) sample images used the following setting:

• Also use the following LoRA's

  • Add detail XL: https://civarchive.com/models/122359/detail-tweaker-xl?modelVersionId=135867

  • NAI vpred fix: https://civarchive.com/models/99619/control-lora-collection?modelVersionId=1965505

• Hires. fix,

  • Upscaler: R-ESRGAN 4x+ Anime6B

  • Steps: 16

  • Denoising: 0.4

  • Scale factor: 1.5