-
Notifications
You must be signed in to change notification settings - Fork 19
New issue
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
scripts/vsmlrt.py: add support for esrgan janai models #42
Conversation
there will be more and more waifu2x/esrgan/cugan-like models in the future, and it's impractical to maintaining an up-to-date support of all such models in the python wrapper, at least not in a timely manner. so my questions are:
|
Agreed, actually this is a draft. I prefer to only keep two or three models of janai (one for speed and one for quality). Comparing the previous esrgan's official model. janai could preserve anime's original art style rather than totally rebuilding(/breaking?) it. Of course, from the perspective of serious encoding, there is still a gap in its level. This is what I think is lacking in the current ESRGAN model. |
After extensive discussions, we propose the following policy regarding contributing models into vs-mlrt:
What do you think about this proposed policy? Thanks. |
I agree with this policy. |
It would be out of tuple's range. |
b0118ae
to
4bfb152
Compare
This comment was marked as resolved.
This comment was marked as resolved.
The only solution I could work out is leave away from |
That's a better solution. LGTM. Please also attach your name. |
|
Continue from #41 (comment)
edit:
models - 1.zip