Real-ESRGAN function for VapourSynth
Project description
Real-ESRGAN
Training Real-World Blind Super-Resolution with Pure Synthetic Data, based on https://github.com/xinntao/Real-ESRGAN.
Dependencies
- NumPy
- ONNX Runtime. CUDA and TensorRT require
onnxruntime-gpu
, while DirectML requiresonnxruntime-directml
. Note that only one ofonnxruntime
,onnxruntime-gpu
andonnxruntime-directml
should be installed at a time in any one environment. - VapourSynth R55 or newer.
- (Optional) CUDA Toolkit
- (Optional) cuDNN
- (Optional) TensorRT
Installation
pip install --upgrade vsrealesrgan
python -m vsrealesrgan
Usage
from vsrealesrgan import RealESRGAN
ret = RealESRGAN(clip)
See __init__.py
for the description of the parameters.
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 Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Close
Hashes for vsrealesrgan-3.0.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6cb048efa56c7a6ba7ad1fa947ce7063fb70ec02d96f0cbdeb21732f27ebfcb6 |
|
MD5 | fee5bd4ea9c6b074c80cae00f88787b1 |
|
BLAKE2b-256 | 29e5e1ecf04ffb0cb3c4bb2f140af0a1b43c90b01da2f7c9fcf7fe9de7dd7072 |