CUGAN

Real-CUGAN is a super-resolution neural network for anime-style arts, based on waifu2x-cunet and trained by bilibili on millions of anime images.

Link:

• (stable) https://github.com/AmusementClub/vs-mlrt/releases/download/model-20211209/cugan_v2.7z

Models

The models support upscaling by 2x/3x/4x and also denoising.

vsmlrt.py wrapper Usage

In order to simplify usage, we provided a Python wrapper module vsmlrt:

from vsmlrt import CUGAN, Backend

src = core.std.BlankClip(format=vs.RGBS)

# backend could be:
#  - CPU Backend.OV_CPU(): the recommended CPU backend; generally faster than ORT-CPU.
#  - CPU Backend.ORT_CPU(num_streams=1, verbosity=2): vs-ort cpu backend.
#  - GPU Backend.ORT_CUDA(device_id=0, cudnn_benchmark=True, num_streams=1, verbosity=2)
#     - use device_id to select device
#     - set cudnn_benchmark=False to reduce script reload latency when debugging, but with slight throughput performance penalty.
#  - GPU Backend.TRT(fp16=True, device_id=0, num_streams=1): TensorRT runtime, the fastest NV GPU runtime.
flt = CUGAN(src, noise=-1, scale=2, backend=Backend.ORT_CUDA())

Notes

Due to issues in TensorRT, Turing/Ampere cards can't use the vs-trt backend. vs-ort cuda is fine.

Benchmarking

Measurements: FPS / Device Memory (GB)

Device memory:

• CPU: private memory including VapourSynth
• GPU: device memory including context