Downloads · 30 days
0
Minhwa-LoRA-v1
gguk2/Minhwa-LoRA-v1
Minhwa-LoRA-v1 is a text-to-image model from gguk2. Use it when you need an image from a text prompt. The card lists the license as creativeml-openrail-m.
Living Minhwa는 한국 전통 민화(Minhwa), 특히 '까치호랑이'와 '화조도'의 화풍을 학습한 Stable Diffusion LoRA 모델입니다. 단순한 스타일 모방을 넘어, Aspect Ratio Bucketing 기술을 통해 족자(Scroll)와 병풍(Screen)의 구도까지 학습했습니다.
Access
Public
Updated Dec 18, 2025
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 54%
At a glance
- Task
- Text-to-Image
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Dec 18, 2025
- Updated
- Dec 18, 2025
- SHA
- acfec70b
Base models
Model card
From the Hugging Face model README
🐯 Living Minhwa: Korean Folk Art LoRA
Living Minhwa는 한국 전통 민화(Minhwa), 특히 '까치호랑이'와 '화조도'의 화풍을 학습한 Stable Diffusion LoRA 모델입니다.
단순한 스타일 모방을 넘어, Aspect Ratio Bucketing 기술을 통해 족자(Scroll)와 병풍(Screen)의 구도까지 학습했습니다.
💡 Model Details
- Model Type: SD 1.5 LoRA
- Rank/Alpha: 32 / 16 (Optimized for fidelity)
- Trigger Word:
minhwa style - Training Data: 70 High-quality images from National Museum of Korea (e-Museum)
🎨 How to Use (Prompt Engineering)
이 모델은 "Minhwa Cheat Code" (특수 프롬프트)를 사용할 때 가장 성능이 좋습니다.
Recommended Settings
- LoRA Weight: 0.8 ~ 1.0
- Sampler: DPM++ 2M Karras or Euler a
- CFG Scale: 7.0
✨ The "Cheat Code" Prompt
Use this suffix to enforce texture and flat perspective:
, minhwa style, (masterpiece, best quality:1.4), (traditional korean ink painting:1.3), (hanji paper texture:1.3), rough brush strokes, flat perspective, vivid colors
- Task
- Text-to-Image
- License
- creativeml-openrail-m
- Created
- Dec 18, 2025
- Updated
- Dec 18, 2025