Nodes/ComfyUI-YOLOE26/YOLOE-26 Prompt Segment
ComfyUI Node

YOLOE-26 Prompt Segment

Segment objects matching a comma-separated text prompt and return an annotated preview image plus a merged binary mask at the original image resolution.

By Rinne414·Created 5 months ago·Updated about a month ago· 11
YOLOE-26 Prompt Segment
  • model
  • image
  • annotated_image
  • mask
  • detection_count
promptperson
conf0.10
iou0.70
max_det300
mask_threshold0.50
imgsz640
show_boxestrue
show_labelstrue
show_conftrue
show_maskstrue
CategoryYOLOE26

Inputs (12)

NameTypeDefaultDescription
modelYOLOE_MODEL
imageIMAGE
promptSTRINGpersonText prompt for open-vocabulary segmentation. Separate multiple classes with commas, e.g. 'person, car, dog'.
confoptFLOAT0.100–1Detection confidence threshold.
iouoptFLOAT0.700–1IoU threshold used by Ultralytics inference.
max_detoptINT3001–1000Maximum number of detections returned per image.
mask_thresholdoptFLOAT0.500–1Threshold used to binarize instance masks. Recent Ultralytics releases already return binary masks, in which case values below 1.0 have no additional effect and exactly 1.0 empties every mask.
imgszoptINT64064–2048Inference image size.
show_boxesoptBOOLEANtrue
show_labelsoptBOOLEANtrue
show_confoptBOOLEANtrue
show_masksoptBOOLEANtrue

Outputs (3)

NameTypeDescription
annotated_imageIMAGE
maskMASK
detection_countINT