usyd-community/vitpose-plus-large

The full model card is on the website: 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	`img.pose.kpts`	One region per detected person, with `bbox_xywh`, `label`, and `kpts_xy`

Request

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)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.vlm.run/v1/openai",
  apiKey: process.env.VLMRUN_API_KEY,
});

const response = await 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",
          },
        },
      ],
    },
  ],
  method: "pose",
});

console.log(response.choices[0].message.content);

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

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
Video

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

{
  "object": "img.pose.kpts",
  "items": [
    {
      "bbox_xywh": [0.4387, 0.1035, 0.3395, 0.8176],
      "label": "person",
      "kpts_xy": [[0.573, 0.1872], [0.584, 0.1706], [0.5639, 0.1738], "..."],
      "kpts_score": [0.9638, 0.9702, 0.9541, "..."]
    }
  ],
  "kpts_labels": ["nose", "left_eye", "right_eye", "..."]
}

The flat reply, with the image’s details beside the payload:

{
  "model": "usyd-community/vitpose-plus-large",
  "method": "pose",
  "image_hash": "sha256:1433c58c...",
  "image_width": 640,
  "image_height": 425,
  "content": {
    "object": "img.pose.kpts",
    "items": [
      {
        "bbox_xywh": [0.4387, 0.1035, 0.3395, 0.8176],
        "label": "person",
        "kpts_xy": [[0.573, 0.1872], [0.584, 0.1706], "..."],
        "kpts_score": [0.9638, 0.9702, "..."]
      }
    ],
    "kpts_labels": ["nose", "left_eye", "right_eye", "..."]
  }
}

A video_url returns the vid counterpart. Items gain frame_id and track_id, and the container gains a frames table:

{
  "model": "usyd-community/vitpose-plus-large",
  "method": "pose",
  "video_hash": "sha256:5c9e5eb1...",
  "video_width": 1280,
  "video_height": 720,
  "video_fps": 23.976,
  "video_nframes": 6059,
  "video_duration": 252.711,
  "content": {
    "object": "vid.pose.kpts",
    "items": [
      {
        "bbox_xywh": [0.2278, 0.2611, 0.2148, 0.7389],
        "label": "person",
        "kpts_xy": [[0.4587, 0.3242], "..."],
        "kpts_score": [0.9924, "..."],
        "frame_id": 168,
        "track_id": 1
      }
    ],
    "frames": [{ "frame_id": 0, "frame_ts": 0.0 }, "..."],
    "kpts_labels": ["nose", "left_eye", "right_eye", "..."]
  }
}

kpts_xy lists the 17 COCO keypoints in order, and kpts_labels on the container names them once for every item: nose, the eyes, the ears, the shoulders, elbows, wrists, hips, knees and ankles. Each [x, y] pair is normalized against the frame, and a joint may fall outside 0-1 when the model places it past the edge. kpts_score is the model’s raw per-joint confidence, in the same order. On a video_url, video_fps at the top level of the request sets the detector cadence (default 10). frames lists every sampled frame, including frames with nobody in them, so a gap in items is distinguishable from a frame that was never read.

Get Started

OpenAI-Compatible API

TypeSafe-Compatible API

Guides

API Reference

Tools

Platform

usyd-community/vitpose-plus-large

Output by method

Request

Response

​Output by method

​Request

​Response

Output by method

Request

Response