ComfyUI Node: Qwen2.5-VL Object Detection
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Qwen2.5-VL
Inputs
qwen_model QWEN_MODEL
image IMAGE
target STRING
bbox_selection STRING
score_threshold FLOAT
merge_boxes BOOLEAN
Outputs
JSON
BBOX
Extension: ComfyUI Qwen2.5-VL Object Detection Node
This repository provides a custom ComfyUI node for running object detection with the a/Qwen 2.5 VL model. The node downloads the selected model on demand, runs a detection prompt and outputs bounding boxes that can be used with segmentation nodes such as a/SAM2.
Authored by TTPlanetPig
Looking for a different node?
More nodes in ComfyUI Qwen2.5-VL Object Detection Node
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.