search

ashawkey / RAD-NeRF

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
MIT License
878 stars 153 forks source link

请问如果我的训练视频不是25fps，哪些地方需要修改呢？？ #24

Open muyoucun opened 1 year ago

muyoucun commented 1 year ago

数据预处理？以及渲染生成视频的部分？谢谢

aishoot commented 1 year ago

You need to use ffmpeg to process the original video to 25fps, 512x512.

RuojiWang commented 8 months ago

You need to use ffmpeg to process the original video to 25fps, 512x512.

i want to train model about 256x256，how can i do?

thanks in advance