v3.1.0

• Rename fusion parameter to nvfuser.
• Fix inconsistent results between trt and non-trt.
• Bump TensorRT version requirement to 8.5.2.2.

v3.0.0

• Add model paramter to support v4.0~v4.6 models.
• Add ensemble parameter to smooth predictions in areas where the estimation is uncertain.
• Fix corruption with FP16 mode on 4K video.
• Replace multi parameter with factor_num, factor_den, fps_num and fps_den for rational frame rate change.
• Add sc and sc_threshold parameters for scene change detection.
• Add cuda_graphs parameter to use CUDA Graphs.
• Add fusion parameter to enable fusion through nvFuser.
• Remove device_type parameter. No one bothers to run deep learning inference on CPU anyway.
• Add num_streams parameter for parallel execution.
• Remove fp16 parameter and now it's controlled by the format of the clip. RGBH format uses FP16 mode and RGBS format uses FP32 mode.
• Add trt, trt_max_workspace_size, and trt_cache_path parameters for TensorRT support.

With the usage of TensorRT, it should run at least 40~50% faster than previous version or RIFE-ncnn-Vulkan implementation using FP16 mode on GPUs with Tensor Cores. For ease of installation on Windows, you can download the CUDA 7z file 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.

v2.0.0

• Only VS API4 is supported now.
• Update to 4.0 model and remove all old models.
• Remove model_ver parameter.
• Add multi parameter.

model

Update README.md

v1.3.0

• Add 1.8, 2.3 and 2.4 models.

v1.2.0

• Add support for VS API4.

model38

Bump version

model35

Bump version

model31

Bump version

model24

Bump version