Type | |
Stats | 430 168 |
Reviews | (74) |
Published | Nov 24, 2023 |
Base Model | |
Training | Steps: 216 Epochs: 6 |
Usage Tips | Clip Skip: 2 Strength: 0.7 |
Trigger Words | succubus,1girl,ponytail,black hair, 1girl,ponytail,black hair,red eyes, black headwear, mouth mask, leather shirts,long_sleeves, frilled_skirt, fingerless gloves, pantyhose, thigh boots, |
Training Images | Download |
Hash | AutoV2 DF78DA0CA1 |
test LORA
*********************************************
provider:Buddy17
"succubus from Vindictus + testfield"
https://civitai.com/models/205727/succubus-from-vindictus-testfield
*********************************************
好きなポーズや、背景、衣装などを追加して下さい。
Add your favorite poses, backgrounds, costumes, etc.
*********************************************
weight 0.5 ~ 0.7、ADetailerを使用しface_yolov8nで顔修正を行っています。
高解像度補助:R-ESRGAN 4x+ Anime6B,倍率2倍
Weight 0.5 to 0.7 ADetailer is used and face_yolov8n is used for face correction.
Hires.fix:R-ESRGAN 4x+ Anime6B,2x magnification
*********************************************
Impressions
元データに、AI出力画像を2枚加えて学習。
顔や体のデータは十分だと思います。
衣装の再現が少し曖昧なので、あと、2～3枚あってもいいかも。
大鎌は、学習困難なので、もっと教師画像が必要だと思います。
手の形成が非常に困難なので、手のデータはもっと必要だと思います。
Learn by adding two AI output images to the original data.
I think the data on the face and body is sufficient.
The reproduction of the costume is a little vague, so it might be nice to have two or three more.
Scythe is difficult to learn, so I think more teacher images are needed.
I think we need more data on the hand because it is very difficult to form the hand.