usyd-community/vitpose-plus-large

2D human pose estimation (ViT-L, 434M). Accepts one image_url or one video_url; no text-only input and no document_url. pose is the only method. Each detected person returns a person label, a normalized bounding box, and 17 normalized COCO keypoints (kpts_xy). On a video_url, the model tracks pose on every frame; the video_fps request parameter sets the detector cadence (default 10).

Output by method

Method	Payload kind	Image `content.object`	Payload
`pose` (default)	json	`vitpose_plus.pose.keypoints`	One region per detected person, with `bbox_xywh`, `label`, and `kpts_xy`

Request

vlmrun gw chat http://images.cocodataset.org/val2017/000000000785.jpg \
  -m usyd-community/vitpose-plus-large --method pose

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="usyd-community/vitpose-plus-large",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "http://images.cocodataset.org/val2017/000000000785.jpg"
                    },
                },
            ],
        }
    ],
    extra_body={"method": "pose"},
)

print(response.choices[0].message.content)

curl https://gateway.vlm.run/v1/openai/chat/completions \
  -X POST \
  -H "Authorization: Bearer $VLMRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "usyd-community/vitpose-plus-large",
    "method": "pose",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "image_url",
            "image_url": {
              "url": "http://images.cocodataset.org/val2017/000000000785.jpg"
            }
          }
        ]
      }
    ]
  }'

Response

Text mode
JSON mode

A single image returns the json block alone, with no wrapper:

{
  "object": "vitpose_plus.pose.keypoints",
  "items": [
    {
      "bbox_xywh": [0.4376, 0.1015, 0.3409, 0.8184],
      "label": "person",
      "kpts_xy": [[0.5749, 0.1886], [0.5859, 0.1722], [0.5652, 0.1737], "..."]
    }
  ]
}

The shared envelope, with one entry per input medium:

{
  "model": "usyd-community/vitpose-plus-large",
  "method": "pose",
  "data": [
    {
      "object": "image",
      "image_hash": "sha256:1433c58c...",
      "image_width": 640,
      "image_height": 425,
      "content": {
        "object": "vitpose_plus.pose.keypoints",
        "items": [
          {
            "bbox_xywh": [0.4376, 0.1015, 0.3409, 0.8184],
            "label": "person",
            "kpts_xy": [[0.5749, 0.1886], [0.5859, 0.1722], [0.5652, 0.1737], "..."]
          }
        ]
      }
    }
  ]
}

kpts_xy lists the 17 COCO keypoints in order (nose, eyes, ears, shoulders, elbows, wrists, hips, knees, ankles), each as a normalized [x, y] pair.

Overview

Guides

API Reference

Misc

usyd-community/vitpose-plus-large

Output by method

Request

Response

​Output by method

​Request

​Response

Output by method

Request

Response