YOLO-World Model

Class: YoloWorldModelBlockV1

Source: inference.core.workflows.core_steps.models.foundation.yolo_world.v1.YoloWorldModelBlockV1

Run YOLO-World, a zero-shot object detection model, on an image.

YOLO-World accepts one or more text classes you want to identify in an image. The model returns the location of objects that meet the specified class, if YOLO-World is able to identify objects of that class.

We recommend experimenting with YOLO-World to evaluate the model on your use case before using this block in production. For example on how to effectively prompt YOLO-World, refer to the Roboflow YOLO-World prompting guide.

Type identifier

Use the following identifier in step "type" field: roboflow_core/yolo_world_model@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
class_names	List[str]	One or more classes that you want YOLO-World to detect. The model accepts any string as an input, though does best with short descriptions of common objects..	✅
version	str	Variant of YoloWorld model.	✅
confidence	float	Confidence threshold for detections.	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to YOLO-World Model in version v1.

• inputs: Roboflow Dataset Upload, Google Vision OCR, Single-Label Classification Model, SIFT, Model Comparison Visualization, Google Gemini, Identify Changes, Polygon Visualization, Dimension Collapse, Dynamic Zone, EasyOCR, Image Slicer, Dynamic Crop, Image Threshold, Local File Sink, Icon Visualization, Reference Path Visualization, OpenAI, Circle Visualization, Trace Visualization, Email Notification, Pixelate Visualization, Twilio SMS/MMS Notification, Line Counter Visualization, Camera Calibration, Webhook Sink, Halo Visualization, Blur Visualization, Relative Static Crop, QR Code Generator, OpenAI, Ellipse Visualization, Crop Visualization, Polygon Zone Visualization, Buffer, Identify Outliers, OpenAI, Grid Visualization, Stability AI Inpainting, Image Slicer, Classification Label Visualization, Size Measurement, Florence-2 Model, Stitch OCR Detections, Roboflow Custom Metadata, Camera Focus, Model Monitoring Inference Aggregator, Image Blur, Corner Visualization, Anthropic Claude, LMM For Classification, OCR Model, Email Notification, Mask Visualization, Stability AI Outpainting, Anthropic Claude, Contrast Equalization, Absolute Static Crop, Clip Comparison, Detections List Roll-Up, VLM as Detector, Background Subtraction, Instance Segmentation Model, Depth Estimation, Google Gemini, Keypoint Detection Model, Stitch Images, Stability AI Image Generation, Florence-2 Model, Triangle Visualization, Label Visualization, LMM, Detections Consensus, Camera Focus, SIFT Comparison, Text Display, Clip Comparison, CSV Formatter, Twilio SMS Notification, Keypoint Visualization, Dot Visualization, CogVLM, Perspective Correction, Image Convert Grayscale, VLM as Classifier, Color Visualization, Background Color Visualization, Slack Notification, Image Contours, Motion Detection, Image Preprocessing, Object Detection Model, Anthropic Claude, Roboflow Dataset Upload, Bounding Box Visualization, Google Gemini, Morphological Transformation, OpenAI, Llama 3.2 Vision, Multi-Label Classification Model
• outputs: Roboflow Dataset Upload, Byte Tracker, Velocity, Model Comparison Visualization, Time in Zone, Time in Zone, PTZ Tracking (ONVIF).md), Detections List Roll-Up, Dynamic Crop, Detections Stitch, Icon Visualization, Byte Tracker, Byte Tracker, Circle Visualization, Segment Anything 2 Model, Trace Visualization, Path Deviation, Florence-2 Model, Line Counter, Pixelate Visualization, Triangle Visualization, Label Visualization, Detection Event Log, Detections Consensus, Time in Zone, Detections Filter, Detection Offset, Blur Visualization, Ellipse Visualization, Dot Visualization, Crop Visualization, Perspective Correction, Detections Combine, Detections Stabilizer, Distance Measurement, Color Visualization, Corner Visualization, Overlap Filter, Detections Transformation, Background Color Visualization, Path Deviation, Roboflow Dataset Upload, Size Measurement, Florence-2 Model, Bounding Box Visualization, Roboflow Custom Metadata, Stitch OCR Detections, Line Counter, Camera Focus, Detections Classes Replacement, Model Monitoring Inference Aggregator, Detections Merge

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds YOLO-World Model in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • class_names (list_of_values): One or more classes that you want YOLO-World to detect. The model accepts any string as an input, though does best with short descriptions of common objects..
  • version (string): Variant of YoloWorld model.
  • confidence (float_zero_to_one): Confidence threshold for detections.

• output

  • predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.

Example JSON definition of step YOLO-World Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/yolo_world_model@v1",
    "images": "$inputs.image",
    "class_names": [
        "person",
        "car",
        "license plate"
    ],
    "version": "v2-s",
    "confidence": 0.005
}