v4: better results than v2, especially in terms of following the prompt(version 3 doesn't exist, only an internal test). v2 and v1 sometimes change the "style" of the image, especially the faces, this problem has been fixed in v4
v2: better results than v1, and woman usually more "mature"
v1: first version
Useful when you type woman(or women) in the prompt but the anime checkpoint shows girls/loli instead.
Recommended clip skip 2
No trigger words need it, if you write woman or women in your prompt you will have better results.
Recommended checkpoint:
-base_anime_style
-true_anime_style
-AbyssOrangeMix(any versions)
-Anything(any versions)
-Defmix-v2.0
-animefull
-similar anime-focus models
Weight :1 recommended
(Trained on animefull model)
---
If you want to support me, check out my Patreon: https://www.patreon.com/Shiroppo
Follow me on civitai(!!!): https://civitai.com/user/shiroppo
Follow Me on Twitter/X: https://x.com/ShiroppoTwit
Deviantart: https://www.deviantart.com/shiroppoart
Pixiv: https://www.pixiv.net/users/96490888
---
描述:
Better results, with more "mature" women
训练词语:
名称: matWomen_v2.safetensors
大小 (KB): 9327
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
