Neural Enhancement Suite

Parameters

Task

Choose the task.

Task Settings (depend on the choosen task)

Guided Colorize

This will only give consistent results on still images. However, if you want to colorize a video, you can create a few reference stills from the video and colorize it with the “Example Colorize” task.

Mode

“Colorize BW” colorizes a black and white image, and “Keep Color” will apply color modifications to an already colored image.

Add Hint

Adds a hint. Distribute hints on the image to guide to colorizing process. Each hint has a position, a color and an influence.

Overlay Hints

Draw the hints on top of the image.

Hint Size

Size of the drawn hints.

Example Colorize

Choose up to two layers to colorize the frame.

Example Layer(1|2)

Define the layers you want to take the colors from.

Influence(1|2)

The influence of the respective layers.

Low Light Enhancement

Use this task to restore image information lost due to low exposure or high contrast.

Mode

“Overall Exposure” will lift the brightness of an overall (underexposed) frame, while “HDR Recover” will bring up details only in darker areas.

Amount

The influence of the filter.

Superresolution

Increases the frames resolution by A.I. guided supersampling.

Mode

“Overall Exposure” will lift the brightness of an overall (underexposed) frame, while “HDR Recover” will bring up details only in darker areas.

Amount

The influence of the filter.

Backend & Performance
Hardware Acceleration (on Silicon Macs and CUDA machines only)

Run calculations on the GPU. This will give massive speedups compared to CPU mode.

Lower Precision

Compute with reduced precision if possible. This can save up to half of the memory and give you some speedups at the cost of sometimes slightly reduced quality.

CUDA Memory Sharing (on CUDA machines only)

Try to keep frames data on the GPU for rendering. This is faster, especially on larger resolutions like 4k. Might not work on some NVIDIA driver versions (e.g. 476.x) so keep your drivers updated.

Model Offloading

Enabling this will make sure only the AI model parts which are needed for computation are kept on the GPU. This might lower VRAM usage under some settings at the cost of moving AI models in and out of GPU memory. Options are:

  • No offloading: Keep all models on the GPUs VRAM.

  • CPU: Move unneeded models to the RAM and back if needed. This will occupy RAM.

  • Full Unload: Completely unload models if not needed. This saves both VRAM and RAM but might be much slower, as the models have to be loaded again for every request.

Samples (not available for all settings)

The number of ai samples to calculate. This will improve the models accuracy.

Parallel (only available if Samples > 2)

This will render all samples at the same time (faster), if disabled computation might be slower but require less VRAM.

Computation Tiles (not available for all settings)

Split the computation into several tiles. This can help if you run out of memory.