If you’re into my LoRAs, feel free to like, comment, or share. More coming soon—stay tuned and let me know what you think!
Checkpoint: waiNSFWIllustrious_v140
Lora: Noob Hyper Dmd strength: 0.45 (Optional)
Lora: Simple/Transparent Background - Background (Optional)
Sampler name: euler | Scheduler: normal | Cfg: 1~1.3 | Steps: 5~8 (If you're not using Noob Hyper Dmd, please use a general metrics for generation)
HighRes-Fix: RealESRGAN_x4plus_anime_6B (upscale by 1.35, hires steps: 8, denoise: 0.56) (Optional)
Trained Tags:
katoakira5, hair bun, double bun,
*I only used monochrome images in the dataset, but if you want color, "black hair, grey eyes" is a good combination for me.
*Actually I feel generating without HighRes could present a more manga vibe, not too sharp, however, you can try the highres setting above if you want or for complicated images.
DISCLAIMER:
THIS LORA MODEL IS CREATED SOLELY FOR ACADEMIC RESEARCH AND PERSONAL USE. IT IS STRICTLY PROHIBITED TO USE IT FOR COMMERCIAL PURPOSES OR PROFIT. ADDITIONALLY, IT MUST NOT BE USED TO GENERATE NSFW CONTENT. ANY CONSEQUENCES ARISING FROM VIOLATIONS OF THESE TERMS SHALL BE THE SOLE RESPONSIBILITY OF THE USER.