# seigan — serene classical beauty LoRA
seigan(清顔) gives photorealistic female portraits a serene, classically
sculpted beauty: narrow almond eyes with a meditative, half-closed gaze (半眼),
a calm expressionless mouth, and finely balanced features.
- Base model: beretMixReal_v110 (Illustrious) — other realistic Illustrious/SDXL merges may work but are untested
- Trigger word: seigan
- Training data: a small curated set of freely-licensed images
## Recommended recipe
- **Weight 0.6** for portraits / upper body. **Raise to 0.8 for face close-ups**
(the effect fades in extreme close-ups at 0.6)
- The booster (narrow eyes:1.3), tsurime, single eyelid, black eyes is part of
the recipe — the LoRA is trained light so skin stays photographic
- Euler a, 28 steps, CFG 6. Hires 2x (denoise 0.5–0.6) for quality
- **Face close-ups: use a square canvas** (1024×1024 → hires 1.6x, denoise 0.5).
Tall canvases can duplicate facial features at high resolution
## Negative prompt — important!
**Do not put statue, sculpture, figurine, doll in the negative prompt** —
these words cancel this LoRA's effect entirely. Use texture words only:
Optional extras:
- Perfectly smooth skin: add wrinkles, aged skin, nasolabial folds, eye bags to NEG
- Meditative half-closed eyes (半眼): add expressionless, serene expression to POS
and smile, grin, open mouth, teeth to NEG
---
seigan(清顔)は、切れ長の半眼と端正な造形を実写ポートレートに与える LoRA です。
トリガー seigan、推奨重み 0.6(顔アップは 0.8)+上記ブースター。
NEG に statue / sculpture 等を入れると効果が消えます(質感語のみ使用)。
学習素材はすべてフリーライセンス(CC0 / CC BY / CC BY-SA、全件ライセンス・作者記録済み)で、
実在人物の画像は使用していません。