ComfyUI Node
Grounding Detector
A ComfyUI node in grounding with 14 inputs and 4 outputs.
Grounding Detector
- model
- image
- bboxes
- annotated_image
- labels
- masks
◄promptperson . car . dog .►
◄confidence_threshold0.30►
◄single_box_modefalse►
◄single_box_per_prompt_modefalse►
◄bbox_output_formatlist_only►
◄seed42►
◄text_threshold0.25►
◄florence2_max_tokens1024►
◄florence2_num_beams3►
◄yolo_iou0.45►
◄yolo_agnostic_nmsfalse►
◄yolo_max_det300►
Categorygrounding
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| model | GROUNDING_MODEL | — | |
| image | IMAGE | — | |
| prompt | STRING | person . car . dog . | Period-separated (.) = multiple objects: 'banana. orange' finds bananas AND oranges. Comma or no separator = single object: 'banana, orange' finds items labeled 'banana, orange' |
| confidence_threshold | FLOAT | 0.300–1 | Confidence threshold for detections. Typical: 0.2-0.35 (permissive), 0.35-0.5 (balanced), 0.5+ (strict) |
| single_box_modeopt | BOOLEAN | false | Return only the highest-scoring detection. Use for referring expressions (e.g., 'the red car on the left') |
| single_box_per_prompt_modeopt | BOOLEAN | false | Return highest-scoring detection for each prompt/label (e.g., 'banana. orange' returns best banana and best orange). Ignored if single_box_mode is True |
| bbox_output_formatopt | COMBO | list_only | list_only: SAM2-compatible | dict_with_data: includes labels/scores |
| seedopt | INT | 420–4294967295 | Fixed seed for reproducible results (affects mask visualization colors and model randomness) |
| text_thresholdopt | FLOAT | 0.250–1 | GroundingDINO ONLY! Text confidence threshold |
| florence2_max_tokensopt | INT | 10241–4096 | 🌸 Florence-2 ONLY! Max tokens for generation |
| florence2_num_beamsopt | INT | 31–10 | 🌸 Florence-2 ONLY! Beam search width |
| yolo_iouopt | FLOAT | 0.450–1 | 🌍 YOLO-World ONLY! IoU threshold for NMS. Typical: 0.3-0.4 (keep more overlapping boxes), 0.45 (balanced/default), 0.5-0.7 (aggressive filtering) |
| yolo_agnostic_nmsopt | BOOLEAN | false | 🌍 YOLO-World ONLY! Class-agnostic NMS. Enable when detecting overlapping objects of different classes (e.g., person holding bottle) |
| yolo_max_detopt | INT | 3001–1000 | 🌍 YOLO-World ONLY! Max detections per image. Typical: 100 (sparse), 300 (balanced/default), 500-1000 (dense/crowded scenes) |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| bboxes | BBOX | — |
| annotated_image | IMAGE | — |
| labels | STRING | — |
| masks | MASK | — |