Georg Pelz

Any news (regarding ffmpeg integration or pipe support) ?

would be nice if one could not only specify these with ffmpeg but also when using the commandline interface. (so not a ffmpeg issue on it's own)

'scale' is in the original project too, see: https://github.com/hzwer/arXiv2020-RIFE/blob/main/inference_video.py#L64

II downloaded and installed NVIDIA_Nsight_Visual_Studio_Edition_Win64_2021.1.0.21103_29839620 but sadly there is no 'Nsight Monitor'-icon to be seen anywhere like in the screenshots. My guess is you need to install the CUDA SDK...

I increased the TDR (to 60) by creating registry keys (see: https://docs.substance3d.com/spdoc/gpu-drivers-crash-with-long-computations-128745489.html) and rebooting my system and that did help. :) Now the error is gone! :) -> thanks for...

HolyWu ported rife to Vapoursynth, see: https://github.com/HomeOfVapourSynthEvolution/VapourSynth-RIFE-ncnn-Vulkan

@AIisCool: There's also a TemporalDegrain2 port in G41Fun.py (https://github.com/Selur/VapoursynthScriptsInHybrid/blob/master/G41Fun.py) but no clue on which verison ov TemporalDegrain2 it is based.

Okay, thanks for clearing that up. The command line help should be updated to reflect this. Atm. it states '--input-bitdepth : 8-16 [8]'

https://github.com/styler00dollar/VapourSynth-RIFE-ncnn-Vulkan does seem to have already converted the models.

Any news on the Vapoursynth filter? :)