⚡ Update: the recommended weight is now pre-baked into the file — just drop it in and use it at weight 1.0 (no need to set 0.8). Lower only if stacking many LoRAs.

Phoebe (Wuthering Waves) LoRA

Trigger word: pho

Trained base: waiIllustriousSDXL_v170 (Illustrious XL family)

Network: dim=32, alpha=16

Optimizer: Prodigy (lr=1.0)

Recommended settings

• Weight: 0.8 (identity metrics measured at 1.0; human quality calibration caps the recommendation at 0.8).

• - Hi-res fix: recommended (~1.8x, denoise ~0.45) for clean lines.

Usage

1girl, solo, pho, blonde hair, purple eyes, long hair, x hair ornament, white hat,
black collar, white shirt, white skirt, black gloves, white pantyhose,
<pose here>, <background here>,
masterpiece, best quality, amazing quality, absurdres, newest
```

Recommended weight **0.8**. Trigger `pho`.

**-- Identity (baked into the trigger) --**
blonde long hair, purple eyes, and the blue **X-shaped hair ornament**. Keep those tags in for full likeness.

**-- Trademark details (add for the canonical look) --**
white wide-brim **hat**, **black collar**, white shirt + white skirt, **black gloves**, striped/black bows, white pantyhose. If the outfit drifts to a plain coat, add `black collar, white shirt, white skirt` explicitly.

**-- Style note (IMPORTANT) --**
For clean anime shading (not 3D / semi-real skin), put anti-realistic terms in the NEGATIVE prompt: `realistic, 3d, photorealistic, shiny skin, oiled body, semi-realistic, render`. The negatives alone are enough.

## Tested checkpoints

- ✅ `waiIllustriousSDXL_v170` (trained base)
- 🔍 Other Illustrious XL fine-tunes (untested; start weight 0.6-0.8)
- ❌ Pony / SDXL base (architecture mismatch, untested)

## Caveats

- On checkpoints other than the training base, the recommended weight shifts (try 0.7-1.2).
- The default outfit reproduces best; add the trademark clothing tags if it drifts.