This LoRA was trained on a small dataset of her appearance in season 4 and after.
Try experimenting within the 3–10 range until you find the output that best fits your preference.
Recommended Model:
Recommended workflow:
For best results, use Text-to-image Hi-res fix (denoise around: 0.3) to enhance details and overall quality.”
Recommended Use Settings:
- Lora Weight: 1 , CFG Scale: 3-10 , Sampler: Euler a , Steps: 30 and higher
- ADetailer for Face Fix is highly recommended.
- image-to-image Hi-res fix, (Also perfect for face fix)
- Img2img Upscale ( Remacri )
Trigger Prompt:
Mikasa_4, red scarf, 1girl, black eyes, black hair, short hair, hair between eyes, white background, simple background, looking at viewer, breasts,
Mikasa_4, 1girl, breasts, nipples, solo, black hair, underwear, panties, censored, short hair, topless, black eyes, navel, panty pull, medium breasts, undressing, skirt, mosaic censoring, looking at viewer, pussy, tummy,