Description

This LoRA is trained for -17 and similar Illustrious XL checkpoints. It is intended to recall the character identity and the Youran Lingzhu outfit while keeping enough flexibility for portrait, full-body, seated, and elegant showcase prompts. Cross-model behavior on Pony, realistic XL, or non-Illustrious checkpoints is not guaranteed.

Recommended Usage

Basic Prompt

<lora:popukar_youran_lingzhu_recommended_e000005:0.7>, popukar_youran_lingzhu, popukar (arknights), 1girl, solo, no text, looking at viewer, upper body, pale pink hair, purple eyes, side ponytail, bamboo basket hat, flowers on hat, wide sleeves, simple background

Full Body Prompt

<lora:popukar_youran_lingzhu_recommended_e000005:0.7>, popukar_youran_lingzhu, popukar (arknights), 1girl, solo, no text, full body, elegant pose, purple kimono, black outer robe, wide sleeves, fur-trimmed obi, thick rope belt, long flowing ribbons, dark patterned thighhighs, black platform geta sandals, soft lighting

Negative Prompt

low quality, worst quality, lowres, bad , bad hands, bad fingers, extra fingers, missing fingers, extra limbs, disfigured, deformed, blurry, jpeg artifacts, text, watermark, logo, signature, arknights logo, chinese text, english text, caption, artist name, bad face, bad eyes, multiple girls, 2girls, cropped head, out of frame, wrong hair color, black hair, blonde hair, orange hair, red hair, short hair, wrong eye color, blue eyes, red eyes, green eyes, missing pale pink hair, missing purple eyes, missing side ponytail, missing bamboo basket hat, missing flowers on hat, wrong outfit

Practical Notes

• Start from 0.7.

• Use 0.5 if a pose needs more prompt freedom.

• Use higher weights only when identity or outfit recall is too weak.

• Avoid 0.9 as the default if it makes the bamboo basket hat, ribbons, wide sleeves, or outfit details too rigid.

• Keeping popukar_youran_lingzhu, popukar (arknights), 1girl improves identity stability.

Training Summary

• Base checkpoint: WAI--Illustrious-17.safetensors

• Recommended epoch: 5

• Training images: 100

• Caption files: 100

• SFW / samples: 100 / 0

• Training setup: SDXL LoRA, UNet-only, rank 32, alpha 16, dropout 0.05, AdamW8bit, bf16, 10 epochs.

• Final average loss: 0.0949