Almost all super resolution and interpolation models in a colab-notebook

PatchWorKs · 13th November 2022, 10:18

We just found this very interesting repo (and relative colab):

Quote:

Repository to use super resolution models and video frame interpolation models and also trying to speed them up with TensorRT. This repository contains the fastest inference code that you can find, at least I am trying to archive that. Not all codes can use TensorRT due to various reasons, but I try to add that if it works. Further model architectures are planned to be added later on.

Currently working networks:

ESRGAN with rlaphoenix/VSGAN and HolyWu/vs-realesrgan
RealESRGAN / RealESERGANVideo with xinntao/Real-ESRGAN and rlaphoenix/VSGAN
RealESRGAN ncnn with styler00dollar/realsr-ncnn-vulkan-python and media2x/realsr-ncnn-vulkan-python
Rife4 with HolyWu/vs-rife
RIFE ncnn with styler00dollar/VapourSynth-RIFE-ncnn-Vulkan and HomeOfVapourSynthEvolution/VapourSynth-RIFE-ncnn-Vulkan
SwinIR with HolyWu/vs-swinir
Sepconv (enhanced) with sniklaus/revisiting-sepconv
EGVSR with Thmen/EGVSR and HolyWu/vs-basicvsrpp
BasicVSR++ with HolyWu/vs-basicvsrpp
RealBasicVSR with ckkelvinchan/RealBasicVSR
RealCUGAN with bilibili/ailab
FILM with google-research/frame-interpolation
PAN with zhaohengyuan1/PAN
IFRNet with ltkong218/IFRNet
M2M with feinanshan/M2M_VFI
IFUNet with 98mxr/IFUNet
eisai with ShuhongChen/eisai-anime-interpolator
SCUNet with cszn/SCUNet
GMFupSS with 98mxr/GMFupSS
ST-MFNet with danielism97/ST-MFNet
VapSR with zhoumumu/VapSR

Also used:

TensorRT C++ inference with AmusementClub/vs-mlrt
ddfi with Mr-Z-2697/ddfi-rife (auto dedup-duplication, not an arch)
nix with lucasew/nix-on-colab
custom ffmpeg with markus-perl/ffmpeg-build-script

VSGAN-tensorrt-docker

PLEASE DON'T ABUSE (and, if you're able to, establish some kind of collaboration to optimize / evolve the project).

Enjoy and share results !

SaurusX · 15th November 2022, 22:22

I've been using this for a few months now. It is the fastest way to use that suite of AI networks by far. TensorRT makes a hugemongous difference.

Selur · 16th November 2022, 04:26

Would be nice to see a small comparison of all the methods. (Got no card with Tensor RT atm.

)

16th November 2022, 04:26	#3 \| Link
Selur . Join Date: Oct 2001 Location: Germany Posts: 7,859	Would be nice to see a small comparison of all the methods. (Got no card with Tensor RT atm. ) __________________ Hybrid here in the forum, homepage, its own forum

Thread Tools	Search this Thread
Show Printable Version Email this Page	Search this Thread: Advanced Search
Display Modes
Linear Mode Switch to Hybrid Mode Switch to Threaded Mode

15th November 2022, 22:22	#2 \| Link
SaurusX Registered User Join Date: Feb 2017 Posts: 149	I've been using this for a few months now. It is the fastest way to use that suite of AI networks by far. TensorRT makes a hugemongous difference.