> This page is for NVIDIA Relighting NIM, version 1.2.0 (Latest) (default).
> For other versions, use one of these documentation indexes:
> - 1.2.0 (Latest) (default): https://docs.nvidia.com/nim/maxine/relighting/1.2.0/llms.txt
> - 1.1.0: https://docs.nvidia.com/nim/maxine/relighting/1.1.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/maxine/llms.txt.

# Support Matrix

## Models

Relighting uses the following models.

| Model Name | Model ID   | Publisher |
| ---------- | ---------- | --------- |
| Relighting | relighting | NVIDIA    |

## Optimized Configurations

Relighting has optimized configurations for the following server GPUs.

| Server GPU                                                                   | Precision |
| ---------------------------------------------------------------------------- | --------- |
| A10G, A40                                                                    | FP16      |
| L4, L40S                                                                     | FP16      |
| RTX PRO 6000 Blackwell Server Edition, RTX PRO 4500 Blackwell Server Edition | FP16      |

## Other Architectures (Consumer and Desktop GPUs)

Relighting also runs on the following consumer and desktop GPUs.

| Consumer GPU                                         | Precision |
| ---------------------------------------------------- | --------- |
| RTX A6000                                            | FP16      |
| RTX 6000 Ada Generation, RTX 4090                    | FP16      |
| RTX PRO 6000 Blackwell Workstation Edition, RTX 5090 | FP16      |

Relighting is compatible with professional, datacenter, and consumer GPUs that have Tensor cores and are based on the NVIDIA Blackwell, Ada, or Ampere architecture. The GPU must have NVENC. The NIM encodes its output on the GPU's video encoder, so a GPU without NVENC, such as the A100, is not supported. The GPU needs more than 17 GB of memory, because the NIM uses about 17 GB after its models are loaded. Refer to [GPU Memory](#gpu-memory) for the figures.

Relighting requires NVENC/NVDEC hardware for video encoding/decoding. For details about supported GPUs and H264 YUV formats, refer to the [Video Encode and Decode Support Matrix](https://developer.nvidia.com/video-encode-and-decode-gpu-support-matrix-new).

### GPU Memory

The NIM uses about 17 GB of GPU memory once its models are loaded and it has served its first request. Each request adds about 0.3 GB for 1080p input and about 0.7 GB for 4K input, the same with eight concurrent requests. On a GPU with 24 GB of memory, two concurrent 4K requests complete with every frame: in NVIDIA internal benchmark runs on the 4K clip of [Performance Results](/nim/maxine/relighting/performance-results), each request ran at 14.7 fps on the A10G and 11.6 fps on the L4. More than two concurrent 4K requests were not benchmarked on these GPUs (refer to [Multiple Concurrent Inputs](/nim/maxine/relighting/advanced-usage#multiple-concurrent-inputs)). 

On the RTX 6000 Ada Generation GPU used for these measurements, eight concurrent requests peaked at about 19.4 GB in total for 1080p input and 22.6 GB for 4K input. The figures come from the sample video (1080p) and a 4K H.264 clip, on a freshly started NIM, as the peak `nvidia-smi` memory use during the requests minus the use with the NIM idle after its first request, sampled every 100 ms, in GB (1 GB = 10^9 bytes). They vary slightly by GPU architecture and by input clip.

### Host Resource Requirements

Approximate figures for planning, measured with one request at a time on a host with an RTX 6000 Ada Generation GPU and 12 CPU threads, as `docker stats` reports the container's memory use (MEM USAGE) and CPU. `docker stats` shows memory in GiB. The following figures are approximate and are for planning (1 GB = 10^9 bytes). Concurrent requests use more host memory and CPU.

| Resource | Requirement |
| -------- | ----------- |
| Container image | About 5.8 GB to download, 9.3 GB on disk |
| Model artifacts | About 0.1 GB, downloaded on first start into the cache directory. Mount a persistent cache to avoid downloading them on every launch; refer to [Model Caching](/nim/maxine/relighting/advanced-usage#model-caching). |
| Host memory | About 1.1 to 1.3 GB after the NIM starts. It grows during the first requests and levels off within about 40 requests, at about 1.9 to 2.0 GB with the NIM idle and up to about 2.1 GB during a 1080p or 4K request. |
| CPU | About 1.3 CPU cores during a request |
| Disk | Space for the image, the model cache, and your input and output media |
| Shared memory | `--shm-size=8GB`, as in every launch command |

## Input Media

Relighting accepts the following input media.

| | |
| --- | --- |
| Container | MP4. The NIM also accepts WebM; the sample client sends only `.mp4` files. |
| Video codec | H.264, H.265 (HEVC), VP9 |
| Resolution | At least 512 pixels wide and 288 pixels high, the minimum of the AI Green Screen segmentation that Relighting uses, and within the range that the GPU's video decoder (NVDEC) supports for the codec. A smaller video is rejected with `INVALID_ARGUMENT`. A video outside the NVDEC range is also rejected with `INVALID_ARGUMENT`, and the message gives the supported minimum and maximum. If the resolution changes during the video, the output keeps the resolution of the first frame: later frames are scaled to it, and stretched if their aspect ratio differs. Re-encode such a video at one resolution to avoid this. |
| Pixel format | YUV 4:2:0, 8-bit or 10-bit, as NVDEC supports for the codec. The output is 8-bit YUV 4:2:0. A chroma format or bit depth that NVDEC does not decode, such as H.264 4:4:4, is rejected with `INVALID_ARGUMENT`. |
| Frame rate | Constant or variable. The output keeps the frame timestamps of the input, so each frame must be later than the one before. A video whose timestamps repeat or go backwards, such as two files joined with `ffmpeg -c copy`, is rejected with `INVALID_ARGUMENT`. |
| Tracks | One video track and at most one audio track. Other tracks, such as metadata or subtitles, are ignored. To keep only the first video track and the first audio track of an input, use for example `ffmpeg -i input.mp4 -map 0:v:0 -map '0:a:0?' -c copy output.mp4`. |
| Audio | Copied to the output without re-encoding. |
| File size | No maximum. A streamable video is processed as it arrives. A video that is not streamable is stored in full in the container before processing starts, and so is its output: the container needs free disk space for both (refer to [Input Modes](/nim/maxine/relighting/basic-inference#input-modes)). |

## Software

The Relighting NIM requires the following host software, NVIDIA platform components, and disk and memory resources.

### NVIDIA Driver and Prerequisites

NVIDIA driver requirements and other prerequisites for Relighting. The NIM runs on Linux x86-64 (amd64) hosts.

| Prerequisite                     | Version | Download and install steps                                                                                                                                                                                                                        |
| -------------------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| NVIDIA Graphic Drivers for Linux | 570.26+ | [https://www.nvidia.com/en-us/drivers/unix/](https://www.nvidia.com/en-us/drivers/unix/)                                                                                                                                                          |
| Docker                           | latest  | Ubuntu, CentOS, and Debian: [https://docs.docker.com/engine/install/](https://docs.docker.com/engine/install/); Rocky Linux: [https://docs.rockylinux.org/gemstones/containers/docker/](https://docs.rockylinux.org/gemstones/containers/docker/) |
| NVIDIA Container Toolkit         | latest  | Installation and configuration instructions: [https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)           |
| `acl` package, provides `setfacl` (SSL and mTLS only) | Any | Your distribution's package manager, for example `sudo apt install acl`. Needed only by the [SSL Enablement](/nim/maxine/relighting/advanced-usage#ssl-enablement) recipe. |

Relighting uses the following NVIDIA software platforms:

| Components              | Version   |
| ----------------------- | --------- |
| CUDA                    | 12.8.1    |
| cuDNN                   | 9.8.0.87  |
| TRT                     | 10.9.0.34 |
| Triton Inference Server | v2.56.0   |
| DeepStream              | 8.0       |