ComfyPilotComfyPilot
文档 / 节点说明 / RT-DETR 检测

RT-DETR 检测

RT-DETR Detect 节点使用 RT-DETR 模型对输入图像执行目标检测。

节点说明 RTDETR_detect 更新于 2026-11-12

查看官方原文

RT-DETR 检测 - ComfyUI Built-in Node Documentation

RT-DETR Detect 节点使用 RT-DETR 模型对输入图像执行目标检测。

RT-DETR Detect 节点使用 RT-DETR 模型对输入图像执行目标检测。该节点可识别物体，返回物体周围的边界框，并根据 COCO 数据集类别为其标注。你可以按置信度分数、物体类别筛选结果，并限制检测总数。

输入

参数描述数据类型必填范围
模型用于目标检测的 RT-DETR 模型。MODEL是N/A
图像要在其中检测物体的输入图像。节点最多可批量处理 32 张图像。IMAGE是N/A
阈值检测结果必须达到的最低置信度分数，满足条件才会被包含在结果中（默认：0.5）。FLOAT是N/A
类别名称按类别筛选检测结果。设置为 'all' 可禁用筛选（默认："all"）。COMBO是"all" "person" "bicycle" "car" "motorcycle" "airplane" "bus" "train" "truck" "boat" "traffic light" "fire hydrant" "stop sign" "parking meter" "bench" "bird" "cat" "dog" "horse" "sheep" "cow" "elephant" "bear" "zebra" "giraffe" "backpack" "umbrella" "handbag" "tie" "suitcase" "frisbee" "skis" "snowboard" "sports ball" "kite" "baseball bat" "baseball glove" "skateboard" "surfboard" "tennis racket" "bottle" "wine glass" "cup" "fork" "knife" "spoon" "bowl" "banana" "apple" "sandwich" "orange" "broccoli" "carrot" "hot dog" "pizza" "donut" "cake" "chair" "couch" "potted plant" "bed" "dining table" "toilet" "tv" "laptop" "mouse" "remote" "keyboard" "cell phone" "microwave" "oven" "toaster" "sink" "refrigerator" "book" "clock" "vase" "scissors" "teddy bear" "hair drier" "toothbrush"
最大检测数每个图像最多返回的检测结果数量。按置信度分数从高到低排列（默认：100）。INT是N/A

输出

输出名称描述数据类型
边界框每个输入图像的边界框列表。每个框包含坐标 (x, y, width, height)、类别标签和置信度分数。BOUNDINGBOX
本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ 在 GitHub 上编辑

Source fingerprint (SHA-256): 658a47cae788da207a52edc6bf8a428c9f3d8cf415e5f20f71d6125ad6d49734