This was trained with high quality in game images only. No fanart, renders or other non luminous engine depictions were used.
This LORA will not produce usable images with models not based on Pony XL.
In particular, I have found my preferences of models to use as the following:
Autism Confetti - For general images, stays more true then the other autism mix
Pony Realism or Piano mix- For realism images
PD for Anime - For flat 2D style
Not entirely sure what the best parameters are, I haven't had any issues generating with just my basic settings: Clip Skip - 2
CFG - 7
Steps - 60
Sampler - Dpmpp_3m_sde_gpu
Scheduler - Karras
I'm a modder for Final Fantasy XV, and an enthusiast for AI art. I will try to get the rest of the cast soon.
Support me on:
https://www.curseforge.com/members/rinual/
This model is very trained, and my first time training without captions surprisingly. You will not need to prompt parts of her outfit, it should default to it unless you specify something else. But stable diffusion will assume she is wearing her outfits by default. With that said, these are tags that should aid in generating parts of her outfit.
Weight: 1.0
Trigger words: irisamicitia
Appearance:
irisamicitia, 1girl, short hair, brown hair, swept bangs, red eyes
Outfit:
black choker, pendant, jewelry, sleeveless, bare shoulders, sleeveless hoodie, hood down, bracelet, pleated skirt, belt, chain, knee boots, black footwear
I generally will only ever use the prompt:
irisamicitia, 1girl, black choker