Learning Real-World Super-Resolution Models for Animation Videos, based on https://github.com/TencentARC/AnimeSR.
Note that the SR result and hidden state of the current frame will propagate to the next frame. Hence you may not get the same result if you jump to random frames in the editor/previewer instead of rendering linearly.
- NumPy
- PyTorch 1.13
- VapourSynth R55+
trt
requires additional runtime libraries:
- CUDA Toolkit 11.7
- cuDNN 8.6
- TensorRT 8.5.2.2
For ease of installation on Windows, you can download the 7z file on Releases which contains required runtime libraries and Python wheel file. Either add the unzipped directory to your system PATH
or copy the DLL files to a directory which is already in your system PATH
. Finally pip install the Python wheel file.
pip install -U vsanimesr
from vsanimesr import animesr
ret = animesr(clip)
See __init__.py
for the description of the parameters.