The underlying depth estimation model. “Fast” and “Accurate” are deprecated options and need to be manually installed. Accurate 2023 is the current state-of-the-art and Accurate Large 2023 might give some improvements for indoor scenes and might need some readjustment with a level node.
The image resolution on which the depth map is computed.
Includes the depth from neighbouring frames to calculate a smoother depth map.
Runs an additional pass of depth estimation at a higher resolution.
Extra Details Multiplier
The resolution of the extra details pass.
Extra Details Samples
More samples mean more accuracy in the high pass.
Extra Details Alternative Algorithm
Sometimes the Extra Details options produces artifacts. This option tries to remove those.
Enhances edge details. The higher the setting the stronger the filter. A high value may give inaccurate results.
Will reduce flickering between frames at the cost of edge sharpness.
Define, how the computed depth will be mapped to the 0-1 range for displaying.
This is the raw depth prediction. Use this for consistent results between frames.
Scale the computed depth to the 0-1 range. This can introduce flickering on image sequences / videos.
Set (and keyframe) the two points Near Guide Point and Far Guide Point as well the Near and Far values to define which parts of the image correspond to which depth.
Choose between “Depth Map” and “Slicing”. “Depth map” outputs the pure depth, whilst slicing lets you select parts of the images based on depth. Attention: The former “Heatmap” mode is deprecated. Please use Colorama effect with preset “Old Glory” as a replacement.
Minimum (only if “Slicing”)
The near plane to cut.
Maximum (only if “Slicing”)
The far plane to cut.
Soft Border (only if “Slicing”)
Blur amount of the cutting planes.
Backend & Performance
Hardware Acceleration (on GPU version of the plugin only)
Run calculations on the GPU. This will give massive speedups compared to CPU mode.
Compute with reduced precision if possible. This can save up to half of the memory and give you some speedups.
Optimize for low VRAM
If you have not that much graphics card memory enabling this will try to optimize memory consumption.
Samples (not available for all settings)
The number of ai samples to calculate. This will improve the models accuracy.
Computation Tiles (not available for all settings)
Split the computation into several tiles. This can help if you run out of memory.