thank you mr astromahdi from gpu.garden

Please support the original artist: GumiaoAndPeace

All preview images were genned with V2. I feel like the lora is definitely not accurate enough, it didnt really capture the full texture and scratchyness feel of the style, but I dont think I could push Anima to learn further without harming stuffs so oh well. Hope Anima full version style convergence will be even better.

Please support the original artist:

V1: Trained on a bigger dataset, but I didn't found it to be as accurate, but it could be more stable and less rigid.

V2: Narrowed dataset down to 25 image and abuse repeat (OP strat), seems a lil more accurate, but may be less stable.

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.