We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
It seems like I cannot reduce the scale from 4 to 2 with realesrgan-plus Model. It is locked at 4.
I can only reduce it to 2 under realesr-animevideov3.
I'm looking to upscale a real-life video, therefore my preference is to use realesrgan-plus instead of realesr-animevideov3.
It takes a bit too long to do 4x upscaling and then downscale to 2x.
Unless realesr-animevideov3 performs just as well for real-life videos, I would prefer to use realesrgan-plus for this upscale job.
Any help or clarification would be greatly appreciated!
The text was updated successfully, but these errors were encountered:
It is not possible since realesrgan-plus only has a 4x model trained. Take a look under https://github.com/k4yt3x/video2x/tree/master/models/realesrgan.
Unless someone from upstream trains a 2x model, 4x is what we're stuck with, unfortunately.
Sorry, something went wrong.
I've reopened this issue since the model added wasn't working and was producing black frames.
No branches or pull requests
It seems like I cannot reduce the scale from 4 to 2 with realesrgan-plus Model. It is locked at 4.
I can only reduce it to 2 under realesr-animevideov3.
I'm looking to upscale a real-life video, therefore my preference is to use realesrgan-plus instead of realesr-animevideov3.
It takes a bit too long to do 4x upscaling and then downscale to 2x.
Unless realesr-animevideov3 performs just as well for real-life videos, I would prefer to use realesrgan-plus for this upscale job.
Any help or clarification would be greatly appreciated!
The text was updated successfully, but these errors were encountered: