video-test版本：尝试使用静态图片练的视频lora，似乎过拟合了，使用其他的描述词效果不佳，后面试试视频炼制的效果。

使用的训练脚本来自青龙圣者大佬：https://civarchive.com/articles/10640/ez-hunyuanvideo-training-for-windows100-optimizerlycoris

强度建议0.7左右，到达1后很难出现动态效果

--
v1.2版本，测试了一下flux，推荐强度1，没有添加wlop，后续版本加上试试

--

v1.1版本推荐使用 DPM++ 2M Karras | Euler a

在原有模型的基础上，新增了200+的图片，wlop的图片占多数，所以风格会偏向wlop

推荐强度：0.7

--

推荐采样方法：DPM++ 2M Karras | DPM++ 2M SDE Exponential

放大算法：DAT x2

数据集基于 宽 x 高：1024 * 768 进行的训练，所以这个效果应该是最好的

描述就参考我上传的图片即可

VIDEO-TEST VERSION: Tried to use the video lora practiced with static images, seems to be overfitting, using other descriptors doesn't work well, try video refining later.

The training script used is from bdsqlsz: https://civarchive.com/articles/10640/ez-hunyuanvideo-training-for-windows100-optimizerlycoris

Intensity is recommended to be around 0.7, it's hard to get dynamic effects after reaching 1

--

v1.2 version, tested flux, recommended strength 1, did not add the wlop picture, the subsequent version plus try

--

v1.1 recommended DPM++ 2M Karras | Euler a

On the basis of the original model, 200+ new images have been added, and wlop images account for the majority, so the style will be biased towards wlop

Recommended strength: 0.7

--

Recommended Sampling Method: DPM++ 2M Karras | DPM++ 2M SDE Exponential

Enlargement Algorithm: DAT x2

The dataset is trained on width x height: 1024 * 768, so this should be the best.

Just refer to the image I uploaded for the description