谢谢 我的确被警告了

@RobertsShen555  请问你说的 比较难调整 角度 是指 人物的面向角度吗？ 还是说人物的姿态动作姿势。

@RobertsShen555 我重新提交了我的数据集的预览视频， 在zip中 如果感兴趣可以 重新下载zip 看看

I apologize for the delayed response due to the holiday break.

Yes, these are the high and low models for wan2.2. However, one of the models was included in the ZIP file during the previous upload because I was unfamiliar with Civitai's upload process at the time.

I have now submitted my original training dataset. You can download it if needed.

Additionally, I've recently been attempting to train a character LORA model using 3000 images and encountered the following issues:

1. Some images in the dataset feature high-resolution bodies and heads, but hands exhibit motion blur. I'm unsure whether this motion blur might interfere with the model and cause negative effects.

2. Certain images depict physical interactions between characters (e.g., handshakes, head touches). I'm concerned these extraneous limbs might interfere with the model's learning of the main character's appearance.

I would greatly appreciate any insights or assistance on these points.

————————————————————————————————————————

很抱歉，因为假期的原因，过了很久才回复您。

是的，这是wan2.2 的高、低两个模型 不过其中一个模型在之前上传时 放入了zip 中 ，因为当时我还不了解 civitai如何上传。

我现在提交了我的训练原数据集,如果你需要你可以下载它。

另外我最近在尝试 使用3000张图片训练人物lora，

遇到问题：

1、数据集中部分图片的身体和头部是高清的，但是手部有运动模糊，我不知道这种运动模糊是否会干扰模型 带来负面影响。

2、人物和另一个人物有肢体交互 如(握手、摸头)，我担心这种外来肢体 会干扰模型学习主角的外观。

如果有人能帮忙解答，我将十分感谢。