用戶LoRA

DiT.1XLDiT.2
風格

[RE-MAKE] Male manhwa style (V1) | zackshura

[RE-MAKE] Male manhwa style (V1) | zackshura  - AI Model cover image
上傳時間
2026年3月20日 下午6:10
使用數
49.72k
返利
200,000
評論
非常好  (6)
觸發詞

Manhwa men, manhwa style, conventionally attractive, handsome, charming, charismatic, HD eyes, detailed eyes

許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

描述

Kindly, PLEASE READ THE DESCRIPTION BEFORE USING THIS LORA (VERY IMPORTANT ⚠️)


IMPORTANT NOTE ⚠️ : Please note that this LoRA is specifically designed for male characters. It has not been trained to generate female characters, unless combined with other LoRAs that are specifically trained for that purpose.

WARNING⚠️ : NSFW COMPATIBILITY.


Use otome v2 or coco-illustrious-XL V3 & V7 models for the best results with this lora.

make sure to put the weight of this lora between 0.7-1 (if you're using it alone)

If you want to use it as secondary style-loras then put the weight around 03-05

Optional negative prompt : wet skin, ugly, unattractive, unnatural face, oblong face shape, bad teeth, sharp teeth.


Difference between previous version and this remake version (tsubaki and illustrious-V2.0)

PREVIOUS VERSION (DELETED) : -Trained with low quality image and dirty datasets that includes text, watermark, and logo which results in blurry, mosaic, and text artifacts.

-Unbalanced anatomy & angle datasets which results in massive incompatibility.

-basically not compatible with alot of models especially hyper model and model with strong base artstyle like serin.



REMAKE VERSION (NEW)

-Trained with ONLY high quality image and clean datasets that don't include any watermarks, texts, or logo, say goodbye to blurry, mosaic, and texts artifacts (literally)

-balanced anatomy & angle datasets (i hope so)

-hopefully, it will be compatible with a wider range of models.


Sincerely, Thanks for reading the description and enjoy!

評論