AnimeSR

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.

Dependencies

• PyTorch 2.5.0.dev or later
• VapourSynth R66 or later

trt requires additional Python packages:

• TensorRT 10.0.1
• Torch-TensorRT 2.5.0.dev

To install TensorRT, run pip install tensorrt==10.0.1 tensorrt-cu12_bindings==10.0.1 tensorrt-cu12_libs==10.0.1 --extra-index-url https://pypi.nvidia.com

To install Torch-TensorRT, run pip install --pre torch_tensorrt --index-url https://download.pytorch.org/whl/nightly/cu124

Installation

pip install -U vsanimesr

Usage

from vsanimesr import animesr

ret = animesr(clip)

See __init__.py for the description of the parameters.