VapourSynth GAN Implementation using RRDBNet, based on ESRGAN's implementation
Project description
VSGAN
VapourSynth GAN Implementation, based on ESRGAN's implementation
Installation
pip3 install vsgan
PyTorch and CUDA needs to be installed seperately.
Usage
import vsgan as VSGAN
(...)
result = VSGAN.Start(clip=clip, model=[string: path to .pth], scale=[int: model's scale], old_arch=[bool: only set to true for models not working with the current arch])
result.set_output()
The resulting video will be the same color space format as your input clip, BUT, it's currently assuming its matrix is 709, if your inputs matrix is different, please change it at this line of code. :(
Enjoy! Thanks to:
- xinntao For RRDBNet_arch
- VideoHelp.com For helping me
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vsgan-1.0.0.post1.tar.gz
(6.3 kB
view hashes)
Built Distribution
Close
Hashes for vsgan-1.0.0.post1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 19533002805e9bb51d8cb89e8f7f289c8c2b21bc544068b3fdd65e57282ee38d |
|
MD5 | b2684f719a5d6c161917fe0c43fddf78 |
|
BLAKE2b-256 | df6c895c0606a9f9506167d2fe578aae09fa88c7876e73380b51cf23d03b9e6c |