LC Person Mask 🧍

Select parts of a person: face, hair, body, clothes, accessories, background. Segformer or MediaPipe, with optional guided filter / VITMatte refine.

By lonecatone23·Created 6 days ago·Updated about 10 hours ago· 0

LC Person Mask 🧍

◄enginesegformer►

◄segformer_model▾►

◄facetrue►

◄hairfalse►

◄bodyfalse►

◄clothesfalse►

◄accessoriesfalse►

◄backgroundfalse►

◄confidence0.40►

◄refinevitmatte►

◄vitmatte_model▾►

◄edge_erode10.0►

◄edge_dilate10.0►

◄black_point0.010►

◄white_point0.990►

◄max_megapixels2.00►

CategoryLC MaskMaker/mask

Inputs (17)

Name	Type	Default	Description
image	IMAGE		Image with a person in it.
engine	COMBO	segformer	segformer: higher resolution. Body = arms and legs only (bare torso and neck read as clothes). mediapipe: body includes torso and neck skin. Needs the mediapipe package.
segformer_model	COMBO		Used by the segformer engine. Entries marked 'Download' are fetched the first time you run.
face	BOOLEAN	true	—
hair	BOOLEAN	false	—
body	BOOLEAN	false	Skin below the face. See engine for what counts.
clothes	BOOLEAN	false	—
accessories	BOOLEAN	false	Hats, glasses, shoes, bags (and whatever else the model calls an accessory).
background	BOOLEAN	false	—
confidence	FLOAT	0.400.05–0.95	How sure the model must be. Lower grows the selection, higher shrinks it.
refine	COMBO	vitmatte	Edge refinement of the raw mask. vitmatte is best for hair, guided_filter is fast, none keeps the raw mask.
vitmatte_model	COMBO		Only used when refine is vitmatte.
edge_erode	FLOAT	10.00–1024	Trimap: how far the sure-foreground is pulled in from the mask edge (pixels).
edge_dilate	FLOAT	10.00–1024	Trimap: how far the unknown band reaches out past the mask edge (pixels).
black_point	FLOAT	0.0100–0.999	Mask values at or below this become 0.
white_point	FLOAT	0.9900.001–1	Mask values at or above this become 1.
max_megapixels	FLOAT	2.000.25–16	vitmatte only. Larger images are matted at this size, then scaled back.