Turn your low-resolution, low-framerate videos into high-quality, high-FPS videos.
**What’s Interpolation?** A method that adds extra frames between the original ones to make the video look smoother. It basically “fills in the gaps” between frames, so motion appears more fluid and less choppy.
This workflow uses NVIDIA VSR, so it does not add extra detail to the base video. Instead, it preserves the original quality while upscaling without introducing pixelation.
It uses RIFE VFI for interpolation.
Tested with 1-minute-long videos targeting 1440p at 64 FPS on an NVIDIA RTX 4090.
To install ComfyUI_NVIDIA_RTX_Nodes:
1. Update ComfyUI to the latest version.
2. Using ComfyUI Manager, search for the ComfyUI_NVIDIA_RTX_Nodes custom node and install it.
COMFYUI SECURITY ERROR FIX
If you hit a security level error while trying to install the ComfyUI_NVIDIA_RTX_Nodes custom node from ComfyUI manager:
You need to temporarily change the security level in your config.ini file.
If you are using the portable version, the file is located at:
ComfyUI/user/__manager/config.iniChange the value to:
security_level = weak
IMPORTANT:
Do NOT forget to restore it back to its original value. It is safe to temporarily lower the security level for this node since it comes directly from the ComfyUI team, but you should restore it afterward for safety reasons.
Perform a hard restart of ComfyUI (completely stop it, then start it again).
Install the custom node using ComfyUI manager and double-check that it is the official one. The link should point to:
https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUIRestart ComfyUI and check if the node works properly.
If you encounter a dependency error, keep reading...Once everything is working properly, restore your original security level in the config.ini file and restart ComfyUI one final time.
COMFYUI PORTABLE DEPENDENCY ERROR FIX
If you hit a dependency error trying to run the Nvidia VSR node, try this:
Create a backup of your embedded Python directory, in case you break something you can restore your embedded directory later using this backup. Then run the following command:
python -m pip install -U --no-build-isolation nvidia-vfx --index-url https://pypi.nvidia.com
Run the command in your embedded Python directory.
For example: D:\ComfyUI\python_embeded.
This command is designed for CMD. If you're using PowerShell, replace the initial python with .\python.exe.
Detailed use instructions are contained within the workflow it self:
- Yellow nodes are input and settings you can configure to suit your needs.
- Red nodes are instructions and useful notes.
Description
First version release
FAQ
Comments (12)
Every time that RTXVideoSuperResolution shows up in a workflow, it NEVER is able to download the node. I need help where to even get this node to fix this and drop it into my custom nodes folder
1. You need to update ComfyUI to the latest version
2. Using ComfyUI manager, search for the ComfyUI_NVIDIA_RTX_Nodes custom node and install it. If you get the "Security Level" error, you need to temporary change the security level in your ComfyUI config.ini file, if you are using the portable version, this file is located in ComfyUI/user/config.ini. Change the security level to "weak":
security_level = weak
DON'T FORGET TO RESTORE IT BACK TO WHAT IT WAS, it is safe to temporally disable it for this node since it comes directly from the ComfyUI team, but you should restore your security level after you install the node for safety reasons.
3.- Hard restart ComfyUI (stop comfyui completely and then start it again)
4.- Install the custom node, double check it is the oficcial node, the link should point directly to:
https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI
5.- Restart ComfyUI and check if the node works properly. If you hit the dependency error, see the fix steps on this post.
6.- Once the node is working properly, restore your ComfyUI security level in the config.ini file and restart ComfyUI one last time.
@LatentHeart I did everything including update ComfyUI and it STILL not able to download it.... Nothing works
@lanceshocker i have RTXVideoSuperResolution after I updated the KJNodes, not sure if it's available in anything else.
I noticed your video sample has quite some face artifacts in the upscaled version... is that caused by the upscaling itself, or was the original file just too low resolution?
It is the original video, as I explain in the post, Nvidia VSR doesn't do any refinement, only upscales without loosing quality, but everything stays the same. For a light refinement SeedVR2 is better.
@LatentHeart I was gonna ask, i already use SeedVR for upscaling, so i was wondering if this was better than it.. is this at least faster than SeedVR2?
@artificialotaku That's its main advantage yes, it is way faster, like extremely faster. It is the best option if your base video is already good quality (but low resolution), then this baby upscales it in no time.
@LatentHeart awesome, gonna try this then, SeedVR2 is too slow for my taste, so, if you offer speed, i take it, thanks for the wf!
An error occurs stating that the “get image size” node in the subgraph is an unknown node that is not installed.
You can replace that node with any other node that gives you the image size, including the core node.
Won't this workflow throw an out-of-memory error on an RTX 3070 with 64 GB of RAM?