Nodes/comfyui-dsocr-bbox/GLM Vision BBox Extractor
ComfyUI Node

GLM Vision BBox Extractor

Calls a configurable GLM vision chat-completions API for one image and returns clean desc/class/bbox JSON while preserving bbox values and coordinate order.

By maomaozi·Created about a month ago·Updated about a month ago· 0
GLM Vision BBox Extractor
  • image
  • bbox_json
prompt输出图中所有banner,logo,品牌,平台,活动,质保,店铺相关描述的区域bbox,输出为json list,格式如下,不要输出任何其他内容/格式: [ { "desc": "官方旗舰店", "class": "店铺", "bbox": [x1,y1,x2,y2] } ]
endpointhttps://open.bigmodel.cn/api/paas/v4/chat/completions
modelglm-4.6v-flash
api_key
Categorydsocr_bbox/GLM Vision BBox

Inputs (5)

NameTypeDefaultDescription
imageIMAGE
promptSTRING输出图中所有banner,logo,品牌,平台,活动,质保,店铺相关描述的区域bbox,输出为json list,格式如下,不要输出任何其他内容/格式: [ { "desc": "官方旗舰店", "class": "店铺", "bbox": [x1,y1,x2,y2] } ]
endpointSTRINGhttps://open.bigmodel.cn/api/paas/v4/chat/completions
modelSTRINGglm-4.6v-flash
api_keySTRING

Outputs (1)

NameTypeDescription
bbox_jsonSTRING