ComfyUI Node
GLM Vision BBox Dual Extractor
Processes two image/prompt pairs concurrently with separate endpoints and API keys, preserving each response's bbox values and coordinate order.
GLM Vision BBox Dual Extractor
- image_1
- image_2
- bbox_json_1
- bbox_json_2
◄prompt_1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]
}
]►
◄prompt_2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]
}
]►
◄endpoint_1https://open.bigmodel.cn/api/paas/v4/chat/completions►
◄modelglm-4.6v-flash►
◄api_key_1►
◄endpoint_2https://open.bigmodel.cn/api/paas/v4/chat/completions►
◄api_key_2►
Categorydsocr_bbox/GLM Vision BBox
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| image_1 | IMAGE | — | |
| prompt_1 | STRING | 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] } ] | — |
| image_2 | IMAGE | — | |
| prompt_2 | STRING | 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] } ] | — |
| endpoint_1 | STRING | https://open.bigmodel.cn/api/paas/v4/chat/completions | — |
| model | STRING | glm-4.6v-flash | — |
| api_key_1 | STRING | — | |
| endpoint_2 | STRING | https://open.bigmodel.cn/api/paas/v4/chat/completions | — |
| api_key_2 | STRING | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| bbox_json_1 | STRING | — |
| bbox_json_2 | STRING | — |