QwenVL vs. LLaVA: Compared and Contrasted

Models

QwenVL

Qwen-VL is an LMM developed by Alibaba Cloud. Qwen-VL accepts images, text, and bounding boxes as inputs. The model can output text and bounding boxes. Qwen-VL naturally supports English, Chinese, and multilingual conversation.

Learn more about QwenVL

LLaVA-1.5

LLaVA is an open source multimodal language model that you can use for visual question answering and has limited support for object detection.

Learn more about LLaVA-1.5

Model Type

Multimodal Model

Object Detection

Model Features

Item 1 Info

Item 2 Info

Architecture

Frameworks

Annotation Format

Instance Segmentation

GitHub

View Repo

GitHub Stars

3.3k+

16,000

License

Tongyi Qianwen

Apache-2.0

Paper

View Paper

Training Notebook

Train on Colab

Deploy Model

Deploy with Roboflow

Compare Alternatives

Compare QwenVL and LLaVA-1.5 with Autodistill

We ran seven tests across five state-of-the-art Large Multimodal Models (LMMs) on November 23rd, 2023. QwenVL passed at five of seven tests and LLaVA passed at one of seven tests. Here are the results:

Based on our tests, QwenVL performs better across different multimodal tasks than LLaVA.