XL_V2.0模型使用了超过1000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。
使用提示词“Old Version”可以获得漆原智志早期风格效果。
不添加额外提示词,可以获得漆原智志中后期风格效果。
Flux 版本:https://civarchive.com/models/732879
illustriousXL 版本:https://civarchive.com/models/885911
Animagine XL V3版本:https://civarchive.com/models/269934
SD1.5版本:https://civarchive.com/models/49599
--- --- --- --- --- --- --- ---
XL_V2.0 version used more than 1000 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.
Use the prompt word "Old Version" to get early style effects for that artist.
Without adding additional prompt words, to get recent style effects for that artist.
Flux version:https://civarchive.com/models/732879
illustriousXL version:https://civarchive.com/models/885911
Animagine XL V3 version:https://civarchive.com/models/269934
SD1.5 version:https://civarchive.com/models/49599
Description
FAQ
Comments (8)
I will use the LoRA of the work.
您好,
有個疑問,我用跟您一樣的設定參數,
但是出來的結果卻跟您的一點都不樣,
請問您hire.ex是如何設定的呢?
如果你想得到和例图一样的效果,可以下载例图,然后将图片拖到webui的图片信息里,点击发送到文生图,就可以获得图片的所有原始生成信息。
同时,也可以查看例图右下角的“i”标记,里面显示了所有图片信息。
最后,例图Negative prompt使用了negativeXL_D,请自行下载
@flyx3 了解,謝謝,這麼完還打擾您休息.orz
a3和pony应该差不多吧
都能用,
稳定性还原度来说,肯定A3比较好
对于不可描述的那些内容,Pony的传统强项
后面试试pony
Thanks for this LoRA ! You did a nice work !
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















