YOLO-World

Use YOLO-World open-vocabulary object detection through our Serverless Hosted API

YOLO-World is an open-vocabulary object detection model that detects objects from arbitrary text class names without training. We support YOLO-World inferencing via our Serverless Hosted API.

For more details on running YOLO-World, see the Inference docs.

Code sample

Call the /yolo_world/infer endpoint directly with curl:

curl --location 'https://serverless.roboflow.com/yolo_world/infer' \
  --header 'Content-Type: application/json' \
  --data '{
    "api_key": "YOUR_API_KEY",
    "image": {"type": "url", "value": "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/cars-highway.png"},
    "text": ["car", "truck"],
    "yolo_world_version_id": "v2-s",
    "confidence": 0.05
  }'

The same call through the SDK. Install it and supervision:

pip install inference-sdk supervision

Run YOLO-World with custom class names, then decode and visualize the predictions with supervision. Pass Roboflow's API Key via the API_KEY env variable.

import os
import urllib.request

import cv2
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/cars-highway.png"
image_path = "cars-highway.png"
urllib.request.urlretrieve(image_url, image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)

results = client.infer_from_yolo_world(
    inference_input=image_path,
    class_names=["car", "truck"],
    model_version="v2-s",
    confidence=0.05,
)

detections = sv.Detections.from_inference(results[0])

image = cv2.imread(image_path)
labels = [
    f"{name} {conf:.2f}"
    for name, conf in zip(detections.data["class_name"], detections.confidence)
]
annotated = sv.BoxAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.LabelAnnotator().annotate(scene=annotated, detections=detections, labels=labels)
cv2.imwrite("annotated.png", annotated)

The class_names argument accepts any list of class names. Available model_version values: v2-s, v2-m, v2-l, v2-x, s, m, l, x.

Set api_url to match your deployment target:

• https://serverless.roboflow.com for the Serverless Hosted API.

• http://localhost:9001 for a local Inference server.

• Your Dedicated Deployment URL for a private endpoint.