这个模型使用了超过150张高质量的原始图片进行训练。
这个模型拥有很好的画风模仿效果。训练图片全部来自该画师的原画集。
推荐权重：0.6~1.0
推荐CFG：5~6
推荐模型：Animagine XL V3
--- --- --- --- --- --- --- ---
可以使用以下人物tag：
可怜 Karen,
花穗 Kaho,
卫 Mamoru,
咲耶 Sakuya,
雏子 Hinako,
鞠绘 Marie,
白雪 Shirayuki,
铃凛 Rinrin,
千影 Chikage,
春歌 Haruka,
四叶 Yotsuba,
亚里亚 Aria,
--- --- --- --- --- --- --- ---
This model used more than 150 high-quality original pictures for training.
This model has a good effect of restoring the artist's style. The training pictures are all from the original painting collection of the artist.
Recommendation Weight：0.6~1.0
Recommendation CFG：5~6
Recommendation Model：Animagine XL V3
Description
FAQ
Comments (4)
Your examples don't use names, but seem to be able to duplicate the characters pretty well. Is this trained to use the character names at all, or is that only relying on the heavy influence of the style?
This is an artist-style LORA model, so no specific character name is added for training. You only need to describe the appearance characteristics of the character in detail, and you can get the desired character with a high probability :)
@flyx3 And I checked randomly to find there's a V2 with character names now tagged? You rock.
@OhGodItsBroken Yes, you can use character names to have fun now. ~