TNTwise

Are you using the flatpak version? If not, and it's an issue with 1.2.0, I would try the alpha version currently being worked on. https://github.com/TNTwise/REAL-Video-Enhancer/releases/tag/prerelease_2.0

closing due to inactivity

If you recompile ncnn with the memory data parameter set as yes, you can use these models converted by styler00dollar: https://github.com/styler00dollar/VapourSynth-RIFE-ncnn-Vulkan/tree/master/models If you want a tutorial, the best luck you...

> > If you recompile ncnn with the memory data parameter set as yes, you can use these models converted by styler00dollar: https://github.com/styler00dollar/VapourSynth-RIFE-ncnn-Vulkan/tree/master/models > > > > If you want...

> > If you recompile ncnn with the memory data parameter set as yes, you can use these models converted by styler00dollar: https://github.com/styler00dollar/VapourSynth-RIFE-ncnn-Vulkan/tree/master/models > > > > If you want...

> > > > If you recompile ncnn with the memory data parameter set as yes, you can use these models converted by styler00dollar: https://github.com/styler00dollar/VapourSynth-RIFE-ncnn-Vulkan/tree/master/models > > > > If...

Ncnn and onnx are different things. My repo only contains ncnn versions of the models. If you are looking for a .onnx model, they can be found here: https://github.com/styler00dollar/VSGAN-tensorrt-docker/releases/tag/models

Fp16 clamp sim is usually the best. I don't have any experience with svp.

Ensemblefalse is the default, ensembletrue merges 2 different flows together, it takes longer but can produce a better result.

MacOS is really broken, I have been considering removing support for it to focus on Linux and Windows.