[Models](/models)/[Detection & Recognition](/models?category=detection)/AILab-CVC/YOLO-World-L

PyTorchObject DetectionGPL-3.0

# YOLO-World-L

by AILab-CVC

Real-time open-vocabulary object detection with text prompts

320Kdl/month

~100Mparams

[HuggingFace](https://huggingface.co/wondervictor/YOLO-World)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`AILab-CVC/YOLO-World-L`

## Deploy YOLO-World-L

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

YOLO-World extends the YOLO detector family with open-vocabulary detection via vision-language modeling. Users specify objects to detect with text prompts; the model finds them zero-shot at real-time speeds (52 FPS on V100).

On Mixpeek, YOLO-World enables detecting arbitrary objects in video and images using natural language, without retraining for each new category.

## Architecture

YOLO backbone with Re-parameterizable Vision-Language Path Aggregation Network (RepVL-PAN). Uses region-text contrastive loss and a prompt-then-detect paradigm where vocabulary is embedded as model parameters for fast inference.

## Mixpeek SDK Integration

IngestRetrieve

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so YOLO-World-L runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace\_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns\_your\_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API\_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection\_id: "col\_your\_collection",
      documents: \[
        {
          document\_id: "asset-00412",
          // Boxes, masks, depth maps and anomaly scores are structured
          // results, not vectors. They go in payload and are reachable
          // through pre\_filters on a retriever, not through similarity.
          payload: {
            detections: modelOutput,
            source\_key: "archive/2026/asset-00412",
          },
        },
      \],
    }),
  },
);

// No managed alternative for an open label set. Two extractors do emit a
// bbox, for the one thing each detects: document\_graph\_extractor@v1 per
// layout block, face\_identity\_extractor@v1 per face. Nothing ships that
// returns masks, depth maps or anomaly scores.

## Capabilities

*   Open-vocabulary detection with text prompts
*   52 FPS on V100 (real-time)
*   35.4 AP on LVIS zero-shot
*   Supports image-prompted detection
*   ONNX and TFLite INT8 export

## Use Cases on Mixpeek

Real-time video monitoring for arbitrary object types

Content moderation with dynamically defined categories

Retail inventory tracking with custom product lists

Open-ended visual question answering pipelines

## Benchmarks

Dataset

Metric

Score

Source

LVIS (zero-shot)

AP

35.4

Cheng et al., 2024: Table 1

COCO val2017

AP

45.7

Cheng et al., 2024: Table 2

## Performance

Input Size640×640 px

GPU Latency~8ms / image (A100)

CPU Latency~95ms / image

GPU Throughput~125 images/sec (A100)

GPU Memory~0.9 GB

## Common Pipeline Companions

[

openai/clip-vit-large-patch14

Embed detected regions

](/model/openai/clip-vit-large-patch14)[

microsoft/Florence-2-large

Caption open-vocabulary detections

](/model/microsoft/Florence-2-large)

## Explore on Mixpeek

[

More Detection & Recognition models

Compare alternatives in this category

](/models?category=detection)[

Best Computer Vision APIs

Hand-picked tools & platforms compared

](/curated-lists/best-computer-vision-apis)[

Open-Vocabulary Object Detection

Deep-dive technical guide

](/guides/open-vocabulary-object-detection)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

FrameworkPyTorch

OrganizationAILab-CVC

FeatureObject Detection

Outputbbox + label

Modalitiesvideo, image

RetrieverObject Filter

Parameters~100M

LicenseGPL-3.0

Downloads/mo320K

[

### Research Paper

YOLO-World: Real-Time Open-Vocabulary Object Detection

arxiv.org](https://arxiv.org/abs/2401.17270)

### Build a pipeline with YOLO-World-L

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

### Alternative Models

[

facebook/detr-resnet-50

Object Detection

](/model/facebook/detr-resnet-50)[

hustvl/yolos-tiny

Object Detection

](/model/hustvl/yolos-tiny)[

ultralytics/yolov8n

Object Detection

](/model/ultralytics/yolov8n)[

IDEA-Research/grounding-dino-base

Object Detection

](/model/IDEA-Research/grounding-dino-base)

### Related in Detection & Recognition

[

deepinsight/insightface-retinaface-r50

Face Detection

](/model/deepinsight/insightface-retinaface-r50)[

timesler/facenet-pytorch

Face Detection

](/model/timesler/facenet-pytorch)[

fal/AuraFace-v1

Face Detection

](/model/fal/AuraFace-v1)[

Idiap/EdgeFace-S-GAMMA

Face Detection

](/model/Idiap/EdgeFace-S-GAMMA)