Type | |
Stats | 103 59 17 |
Reviews | (20) |
Published | Aug 22, 2024 |
Base Model | |
Training | Steps: 4,005 Epochs: 15 |
Usage Tips | Clip Skip: 2 |
Trigger Words | kasumidoa5lr |
Hash | AutoV2 43AC510274 |
This is SDXL version.
Pony XL version:
【Pony XL】Kasumi 霞 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。
Kasumi is one of my favorite character.
I hope everyone will like it. I'd like to share it with you here.
But It's hard to present Kasumi's beautiful appearance with DOA5LR style.
I'll try my best to show the best of Kasumi's appearance with DOA5LR style.
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)(new version 1.5)
1. Description:
This LoRA can images Kasumi (Ver DOA5LR) images.
2.My way to use prompt:
Trigger Words :kasumidoa5lr
This LoRA can paint three hairstyles for this character.
prompt (for example):
(1) ponytail
kasumidoa5lr, 1girl, solo, long hair, ponytail...... <lora:kasumidoa5lrXL:0.5>(0.5~0.7, Decide by yourself.)......
(2) long hair, loose hair (more stable)
kasumidoa5lr, 1girl, solo, long hair, loose hair...... <lora:kasumidoa5lrXL:0.5>(0.5~0.7, Decide by yourself.)......
(3) side ponytail
kasumidoa5lr, 1girl, long hair, side ponytail...... <lora:kasumidoa5lrXL:0.5>(0.5~0.7, Decide by yourself.)......
Negative prompt:
In principle, none. Decide by yourself.
Personal preference prompts:
masterpiece, best quality, Full-HD, HD, 8K, HDR, highres, highly detailed, RAW photo
3.LoRA權重 (LoRA Weight)(new version 1.5)
LoRA Weight:0.5~0.7 more ideal.
0.5 is good.Deside by yourself.
4.使用ADetailer (Use ADetailer)(new version 1.5)
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:kasumidoa5lr:0.5> (recommend 0.4~0.7, I use 0.5, 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 XL. This checkpoint is 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. :)
6.Tips
You can use Hires. fix to upscale pictures you create.
Make pictures more clarity and more like DOA5LR style.
Setting:
Upscaler:4x-UltraSharp
Denoising strength:0.35
Have fun.~~
7. Version comparison
kasumidoa5lrXL V1.0 is more mature.
kasumidoa5lrXL V1.5 is more cute.
Both fo them are good. you can try to use.