search

danier97 / LDMVFI

[AAAI'2024] "LDMVFI: Video Frame Interpolation with Latent Diffusion Models", Duolikun Danier, Fan Zhang, David Bull
MIT License
138 stars 15 forks source link

use our own video for inference #20

Open miumiuc opened 3 months ago

miumiuc commented 3 months ago

How to use our own video for inference, mp4 format instead of yuv format

andreYoo commented 3 months ago

Change your mp4 video format using the comment 'ffmpeg -i sample.mp4 out.yuv' and do the inference.

danier97 commented 3 months ago

Change your mp4 video format using the comment 'ffmpeg -i sample.mp4 out.yuv' and do the inference.

Thanks for your answer here. Another option would be to change the video reading and frame parsing part of the ‘interpolate_yuv’ script to directly read from mp4 format.