PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

User LoRA

XL
Style

Korean NAI Soft Artstyle LoRA

Create

  • AI Image Generator
  • AI Animation Generator
  • AI Tools
  • Thematic generators
  • Train LoRA
  • Mio.2 Agent
  • Studio

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
Korean NAI Soft Artstyle LoRA - AI Model cover image
Uploaded at
Apr 3, 2026, 7:46 AM
Uses
141
Reviews
No reviews
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

witch - AI Model cover image

User LoRA

witch
0
thighs - AI Model cover image

User LoRA

thighs
52
Mao Asakura (Futabu - Anime) IL - AI Model cover image

User LoRA

Mao Asakura (Futabu - Anime) IL
5
DIC on face before eyes covered eyes (noonai 1.0) - AI Model cover image

User LoRA

DIC on face before eyes covered eyes (noonai 1.0)
125

Description

This is a style LoRA trained on images that reflect the commonly used art styles by Korean users of NAI (NovelAI).It is based on multiple artists such as toma, 92m, ikeuchi tanuma, and healthyman, and is characterized by soft skin rendering, voluptuous body shapes, and clean facial expressions.It has been confirmed to work well with WAI-based models, and adding artist tags according to your preference may yield results that better match your taste.Since I use this LoRA via node connection in ComfyUI, there is no specific trigger word required.If you are using a tool other than ComfyUI, you can call it using the lora:~ syntax.The training was done using the ILXL1.1 base model, and the recommended LoRA weight setting is between 0.8 and 1.0.이 Lora는 한국에서 NAI(Novel AI)를 사용하는 유저들이 보편적으로 사용하는 그림체들로 만들어진 이미지들을 학습하여 만든 스타일 Lora입니다.toma, 92m, ikeuchi tanuma, healthyman 작가 등을 베이스로 여러 작가가 학습되었으며, 부드럽운 피부 표현과 풍만한 육체, 깔끔한 얼굴 표현이 특징인 스타일입니다. WAI 계열 모델에서 잘 작용하는 것을 확인하였으며, 사용자의 취향대로 작가태그를 추가하여 사용하면 더욱 취향에 맞는 결과물을 얻을 수 있을 것입니다. 저는 comfyUI에서 노드로 연결하여 Lora를 호출하여 사용하기에 트리거워드는 따로 없습니다. 만약 comfyUI가 아닌 다른 툴에서 사용 시에는 lora:~ 하는 문법으로 호출하시면 사용 가능할 겁니다! 학습은 ILXL1.1 베이스모델을 사용하였으며 추천하는 설정 값은 Lora weight 0.8 ~ 1.0 입니다.

Comments