Finegrain Box Segmenter (RMBG) is a ComfyUI node in the 🧪AILab/🧽RMBG category from ComfyUI-RMBG. Inputs: image, bboxes, box_coordinates, margin. Outputs…

A sophisticated ComfyUI custom node engineered for advanced image background removal and precise segmentation of objects, faces, clothing, and fashion elements. This tool leverages a diverse array of models, including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet models, SAM, and GroundingDINO, while also incorporating a new feature for real-time background replacement and enhanced edge detection for improved accuracy.

ComfyUI-RMBG

image

bboxes

box_coordinates

margin

mask_blur

mask_offset

invert_output

unload_model

background

background_color

AILab_FinegrainBoxSegment

IMAGE

MASK

MASK_IMAGE

Finegrain Box Segmenter (RMBG)

Name	Type	Default	Description
image	IMAGE		Input image batch to segment with high definition 1024px quality.
bboxesopt	BBOX		Bounding box(es) from Florence-2 or YOLO detection nodes.
box_coordinatesopt	STRING		Manual bounding box as 'x1, y1, x2, y2' in pixel or normalized [0..1] coordinates.
marginopt	FLOAT	0.150–0.5	Safety padding margin around bounding boxes.
mask_bluropt	INT	00–64	Blur mask edges (0 to disable).
mask_offsetopt	INT	0-64–64	Expand (positive) or shrink (negative) mask edges in pixels.
invert_outputopt	BOOLEAN	false	Invert the output mask.
unload_modelopt	BOOLEAN	false	Unload model from VRAM immediately after execution.
backgroundopt	COMBO	Alpha	Background type: Alpha (transparent) or Color (custom solid background).
background_coloropt	COLORCODE	#222222	Hex color code for background when Color mode is selected.

Finegrain Box Segmenter (RMBG)

Inputs (10)

Outputs (3)