Now with Tsubaki DiT version
Recommended weight : 1 , also facefix is recommended for consistency.
Caution
- Delicate stylized style with saturated color mean this style can get easily override by realistic tag and certain strong character tag, adjust weight and settings accordingly
-Due to Pixai auto trainer causing likely overfitting, this LoRAs have on average bad hands,use at your own caution.
- Using Accelerators like DMD2 / LCMTurboMix / Hyper SDXL may reduce style effectiveness, it still generally work good though
Optimal Settings
- Was tested and found to be stable on 15 step /euler a/ cfg 5 or DMD2 8 step/euler a / cfg 1.5 , please do test more settings and explore at your own discretion.
*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.