ComfyUI Node
Qwen2.5-VL Object Detection
A ComfyUI node in Qwen2.5-VL with 6 inputs and 2 outputs.
Qwen2.5-VL Object Detection
- qwen_model
- image
- text
- bboxes
◄targetobject►
◄bbox_selectionall►
◄score_threshold0.00►
◄merge_boxesfalse►
CategoryQwen2.5-VL
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| qwen_model | QWEN_MODEL | — | |
| image | IMAGE | — | |
| target | STRING | object | — |
| bbox_selection | STRING | all | — |
| score_threshold | FLOAT | 0.000–1 | — |
| merge_boxes | BOOLEAN | false | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | JSON | — |
| bboxes | BBOX | — |