NOTICE: Some version may have trigger words while others may not.
I treat this as a first testing ground on training different base models (Illust,NoobAI,EQvae variant,NetaLumina,ect,....)
That being said, I am a novice and this is my first LoCon ever trained, it will not be optimally made, that unfortunately only come with experience. But I'm confident that it work well even on base Noob.
Please do comment on the LoRA quality and potential issues, outside feedback is instrumental for me to know if I had fucked up lol.
Suggested Tags:
j^ckn1fe, long hair, long sleeves, full body, hair between eyes, gloves, jewelry, yellow eyes
Disclaimer
I respect the artists who honed their crafts for years to achieve these styles among all else, if any artists whom LoRA i've made from shown displeasure/objection to their arts being used as AI training material or if they request a takedown notice on Danbooru , I'll delete the LoRA with no further notice.
Description
All images are genned using NetaYume Lumina (Neta Lumina/Lumina Image 2.0) - v3.5 (pretrained) | Lumina Checkpoint | Civitai .
I may be one of the first to train NetaLumina using Colab/Kaggle free gpus, so there's that.
There's this new kaggle notebook for it if you're interested:tpulumina | Kaggle
Training setup was a pain in the ass to figure stuffs out.
This came out alot better than I thought though, hopefully some of you give Neta a chance (even if it's slow as hell).