Sign In

丰子恺FONG TSE KA

42
140
51
5
Updated: Dec 28, 2023
style
Verified:
SafeTensor
Type
LoRA
Stats
140
51
Reviews
Published
Dec 28, 2023
Base Model
SDXL 1.0
Training
Steps: 4,320
Epochs: 8
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
fen9zik4i
Hash
AutoV2
C92CB246E1
default creator card background decoration
Yiyan32's Avatar
Yiyan32

测试了主流的几个XL大模型,泛化性还可以,古今中外各种类型基本也都可以跑出来。

采样器我用的dpm++2m karras,步数25就可以跑出不错的效果,权重根据大模型及绘画主体不同可自由调节,可以先从1逐渐累加到1.5。

不过参数没有那么死板,还请大家自由发挥~

I tested several mainstream XL models, and the generalization was okay.All kinds of paintings are worth trying.

I used the dpm++2m karras sampler, and 25 steps could produce good results. The weights could be adjusted freely according to the different models and drawing subjects. You can start from 1 and gradually increase to 1.5.

But the parameters are not so rigid, please feel free to play around~