Tencent AI Lab Vision Models

Compare the one Tencent AI Lab vision model we track, all of them open-weight. Try them on your own images, free in the Roboflow Playground.

1 model · 1 open-weight · 1 free to try · Updated Feb 2024

About Tencent AI Lab Vision Models

Every Tencent AI Lab vision model in our catalog is open-weight. The one model we track publishes downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on GPL v3 terms. The most recent release is YOLO World (Feb 2024).

The Tencent AI Lab models we list cover object detection (1 model), open vocabulary object detection (1), and phrase grounding (1).

On the open-weight tier, YOLO World runs at 13M parameters.

The one Tencent AI Lab vision model we track runs live in the Roboflow Playground, so you can test it on your own image before committing to it.

Which Tencent AI Lab Model Should You Use?

The one Tencent AI Lab vision model in our catalog and what it is built for.

YOLO World: Best for: Open Vocabulary Object Detection and Object Detection. Open weights: GPL v3 license, 13M parameters. Self-host it or run it here. Small enough for on-device and edge deployment. Runnable in the Playground.

Open-Source Tencent AI Lab Models

1 model with downloadable weights you can self-host under their licenses (GPL v3). All run live in the Playground through hosted APIs, so self-hosting is optional.

YOLO World

YOLO-World v2 Small (YOLO-World-S-v2) is the smallest variant of Tencent AI Lab’s YOLO-World v2 family, released around February 2024 under GPL-v3. With ~13 million parameters, it adopts a prompt-then-detect paradigm using offline vocabularies and is pretrained on large-scale datasets such as Objects365 and GoldG. The model processes image inputs at 640×640 or 1280×1280 resolutions and supports zero-shot open-vocabulary object detection, enabling recognition of novel categories from text prompts without retraining.Evaluations show competitive results across benchmarks like LVIS and COCO, while maintaining real-time efficiency. On an NVIDIA V100, the small variant reaches ~74 FPS at standard resolutions. Together with larger YOLO-World v2 models, it provides a scalable framework for efficient, open-vocabulary detection across diverse deployment settings.

Frequently Asked Questions About Tencent AI Lab Vision Models

Which Tencent AI Lab models can do object detection?

1 of the 1 Tencent AI Lab vision models we track handles object detection: YOLO World. Each model page lists its full task coverage, license, and specs.

Which Tencent AI Lab models can do open vocabulary object detection?

1 of the 1 Tencent AI Lab vision models we track handles open vocabulary object detection: YOLO World. Each model page lists its full task coverage, license, and specs.

Are Tencent AI Lab vision models open source?

Yes. The one Tencent AI Lab vision model we track publishes downloadable weights you can self-host under its license (GPL v3).

How many Tencent AI Lab vision models are on Roboflow Playground?

We track 1 live Tencent AI Lab vision model. The most recent addition is YOLO World, released Feb 2024.

Can I try Tencent AI Lab vision models for free?

Yes. The one Tencent AI Lab models run live in the Roboflow Playground. Upload your own image, run several models on it at once, and compare the outputs side by side. No setup and no account required.

This page lists the one Tencent AI Lab vision model in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover object detection, open vocabulary object detection, and phrase grounding, among other tasks. All of them run live in the Roboflow Playground on your own images. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.