叶夜靥

Results 4 comments of 叶夜靥

> > Without data preprocessing, a random picture is used as ref_image and the provided motion_6 for inference. The result is as follow. The consistency of the character's movements is...

> > > > Without data preprocessing, a random picture is used as ref_image and the provided motion_6 for inference. The result is as follow. The consistency of the character's...

> Could this be the reason for the flickering? > > Some weights of the model checkpoint were not used when initializing UNet2DConditionModel: ['conv_norm_out.weight, conv_norm_out.bias, conv_out.weight, conv_out.bias'] Encountered the same...

> 同样的问题 > > ``` > webui | 2024-10-14 05:06:33 | ERROR | "./app/services/material.py:330": clip_videos - 视频裁剪失败: "00:50-00:53" => t_start (50.00) should be smaller than the clip's duration (41.01). >...