This is Pony XL version.
NoobAI-XL version:
【NoobAI-XL】Mai Shiranui 不知火舞 DOA5LR LoRA ◤Louiswolf_style◢
Illustrious version:
【Illustrious】Mai Shiranui 不知火舞 DOA5LR LoRA ◤Louiswolf_style◢
SDXL version:
【SDXL】Mai Shiranui 不知火舞 DOA5LR LoRA ◤Louiswolf_style◢
SD1.5 version:
Mai Shiranui 不知火舞 doa5lr LoRA ◤Louiswolf_style◢
我很喜歡這個角色,希望大家會喜歡,在這邊分享與各位交流。
I like this character very much.
I hope everyone will like it.
I would like to share it with you here.
If there are images using this LoRA you create, I hope you can post images and comment with everyone, thank you.
一.我使用的設定 (My setting)
Sampling method:DPM++ 2M (Automatic)
Sampling steps:20
CFG Scale:7
二.關於LoRA (About LoRA)
1. Description:
This LoRA can generate Mai Shiranui (Ver DOA5LR) images.
2.My way to use prompt:
Trigger Words :maishiranuidoa5lr
This LoRA can paint three hairstyles for this character.
Trigger Words: maioutfit . You generate Mai's classic outfit by using this trigger word.
Full body Trigger Words: maioutfit, fingerless gloves, pelvic curtain, tabi, tassel You can generate Mai's full body classic outfit by using these trigger words.
prompt (for example):
(1) ponytail
maishiranuidoa5lr, 1girl, solo, long hair, ponytail, high ponytail, hair ribbon...... <lora:maishiranuidoa5lrPONYXL:0.7>(0.7, Decide by yourself.)......
(2) long hair, loose hair
maishiranuidoa5lr, 1girl, solo, long hair, loose hair...... <lora:maishiranuidoa5lrPONYXL:0.7>(0.7, Decide by yourself.)......
(3) short hair
maishiranuidoa5lr, 1girl, solo, short hair...... <lora:maishiranuidoa5lrPONYXL:0.7>(0.7, Decide by yourself.)......
(4) Mai's classic outfit
maishiranuidoa5lr, maioutfit, breasts, huge breasts, sideboob, cleavage, 1girl, solo, long hair, high ponytail, looking at viewer...... <lora:maishiranuidoa5lrPONYXL:0.7>
Negative prompt:
In principle, none. Decide by yourself.
3.LoRA權重 (LoRA Weight)
LoRA Weight:0.5~0.7 more ideal.
4.使用ADetailer (Use Adetailer)
It is highly recommended to use ADetailer to inpaint the face to achieve the ideal effect.
ADetailer model:face_yolov8n.pt
ADetailer prompt:detailed face, beautiful face, perfect face <lora:maishiranuidoa5lrPONYXL:0.7>(I use 0.7, decide by yourself)
ADetailer Inpaint denoising strength:0.4
5.個人使用的Stable Diffusion checkpoint (The Stable Diffusion checkpoint I use)
Some checkpoints are not highly suitable for this LoRA.
I personally recommend using it with
AniVerse - Pony XL(I often used)
Ponymature SDXL (I often used)
WAI-ANI-HENTAI-PONYXL (I often used)
Sym-Pony World (I often used)
These checkpoint are suitable for this LoRA and it can generate the ideal face and hairstyle.
You can also try other checkpoint to paint the style you want.
Happy painting and don’t hesitate to share. Thank you. :)
Have fun.~~
Description
(1)Adjustment images to train new version LoRA.
(2)Let Mai's face style more natural and like DOA5LR style.
FAQ
Comments (6)
比上个版本确实好多了,不过AI脸还是有点明显
是指表情樣貌單調嗎?這方面還在努力調整中。
不是,是指脸部建模本身看起来就是AI脸,而不是不知火舞的脸
@Ryudo12345 原來如此,我把訓練圖片篩選後,重新設定學習率訓練,這次版本的出圖會較接近不知火舞DOA5LR的樣貌,之後會繼續更新版本來減少AI臉。
@Louiswolf 哦好的,只是提个意见
@Ryudo12345 不客氣,也希望您能繼續提出意見參考,感謝您。
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.







