NVIDIA AI for Media Relighting

Getting Started

NVIDIA AI for Media Relighting NIM uses gRPC APIs for inferencing requests. Following instructions demonstrate the usage of AI for Media Relighting NIM model using Python client.

Prerequisites

You will need a system with git and Python 3.10+ installed.

Download the NVIDIA AI for Media Relighting Python client

Download code by cloning the NVIDIA AI for Media NIM Clients Repository:

git clone https://github.com/NVIDIA-Maxine/nim-clients.git
cd nim-clients/relighting

Install the dependencies for the NVIDIA AI for Media Relighting Python client:

sudo apt-get install python3-pip
pip install -r requirements.txt

Run Python Client

Navigate to the scripts directory

cd scripts

Send gRPC request

python relighting.py --preview-mode \
--target grpc.nvcf.nvidia.com:443 \
--function-id 253bc77f-2d6c-4b9d-86c6-c6fb0f9e239c \
--api-key $NVIDIA_API_KEY \
--video-input <input_file_path> \
--output <output_file_path>

Note the requirements for input file:

• The supported file type is mp4 with H.264 codec.
• The size limit for input file is 50 MB.
• HDRI environment maps in Radiance .hdr format are supported for custom lighting.

Refer the documentation for more information.