π Update News
- 2026-03-05: Official release of KORMo-Diffusion.
- 2026-03-02: Official release of KORMo-VL.
- 2025-10-13: Official release of KORMo-10B-sft.
π‘ About KORMo-VL-Diffusion
KORMo-VL is a vision-language model developed from scratch by the KAIST MLP Lab (https://sites.google.com/view/aailab), built on top of KORMo-10B. The system consists of two components:
- Vision-Language Model (VLM)
- Image Generation Model
The KORMo-VL-Diffusion model, designed for image generation, was trained from scratch with a high proportion of images reflecting Korean daily environments and culture. Unfortunately, due to limited GPU resources during the research process, we are sharing the intermediate results of the model at this stage.
KORMo-VLμ KAIST MLP μ°κ΅¬μ€μμ from scratchλ‘ κ°λ°ν μκ°-μΈμ΄ λͺ¨λΈλ‘, KORMo-10Bλ₯Ό κΈ°λ°μΌλ‘ (1) μκ°-μΈμ΄ λͺ¨λΈκ³Ό (2) μ΄λ―Έμ§ μμ± λͺ¨λΈλ‘ ꡬμ±λμ΄ μμ΅λλ€.
μ΄ μ€ μ΄λ―Έμ§ μμ±μ μν KORMo-VL-Diffusion λͺ¨λΈμ νκ΅μ μν νκ²½κ³Ό λ¬Ένλ₯Ό λ°μνκΈ° μν΄ κ΅λ΄ νκ²½ μ΄λ―Έμ§λ₯Ό κ°λ₯ν λμ λΉμ¨λ‘ μ¬μ©νμ¬ from scratchλΆν° νμ΅λ λͺ¨λΈμ λλ€. λ€λ§ μ°κ΅¬ μ§ν μ€ GPU μμμ μΆκ°λ‘ ν보νμ§ λͺ»ν΄ νμ¬λ μ€κ° κ²°κ³Όλ¬Όμ 곡μ νκ² λμμ΅λλ€.
- LLM: KORMo-VL
- Model Structure: Qwen-Imageλ₯Ό ꡬ쑰λ₯Ό μ°Έμ‘°ν΄ μ¬κ°λ°ν¨ (20B μ λμ DiffusionλΆλΆμ λ³νν΄ scratchλΆν° νμ΅)
- Languages: Korean / English
- Training Data: Synthetic data + public datasets (e.g., AI Hub, details to be released)
ν₯ν ν΄λΉ λͺ¨λΈμ μΆ©λΆν νμ΅ν μ μλ νκ²½μ΄ λ§λ ¨λλ€λ©΄ μμ±λ λͺ¨λΈλ‘ λ°μ μν€λ κ²μ λͺ©νλ‘ νκ³ μμ΅λλ€. μ€κ° κ²°κ³Όλ¬Ό μμμ μΆκ° νλμ΄λ μ°κ΅¬λ₯Ό μ§ννκ³ μΆμ λΆλ€μ μμ λ‘κ² νμ©ν΄ 보μκΈ° λ°λλλ€.
π T2I Performance
English Prompt
| Prompt | Generated Image |
|---|---|
| Prompt: Dense forest | ![]() |
| Prompt: Black pattern mug | ![]() |
Korean Prompt
| Prompt | Generated Image |
|---|---|
| Prompt: μΈμ°½ν μ² | ![]() |
| Prompt: κ²μ 무λ¬μ λ¨Έκ·Έμ»΅ | ![]() |
KORMo-VL-Diffusion Demo
prompt: μλ¦λ€μ΄ μ μμ κ½λ€
π¦ Installation
uv pip install transformers==4.57.1 pillow torchvision diffusers
π Inference Example
github repo νμ© μμ
Contact
- KyungTae Lim, Professor at KAIST.
ktlim@kaist.ac.kr
Contributor (https://sites.google.com/view/aailab)
- Junghun Yuk
- INho won
- HANGYEOL YOO
- Junmyeong Lee
- KyungTae Lim
Citation
@misc{KORMo,
author = {Minjun Kim, Hyeonseok Lim, Hangyeol Yoo, Inho Won, Seungwoo Song, Minkyung Cho, Junghun Yuk, Changsu Choi, Dongjae Shin, Huije Lee, Hoyun Song, Alice Oh, and KyungTae Lim},
title = {KORMo: Korean Open Reasoning Model for Everyone},
year = {2025},
publisher = {GitHub},
journal = {Technical Report},
paperLink = {\url{https://arxiv.org/abs/2510.09426}},
},
}
- Downloads last month
- 5


