Models
QwenVL vs. LLaVA

QwenVL vs. LLaVA

Both QwenVL and LLaVA-1.5 are commonly used in computer vision projects. Below, we compare and contrast QwenVL and LLaVA-1.5.

Models

icon-model

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.
icon-model

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.
Model Type
Multimodal Model
--
Object Detection
--
Model Features
Item 1 Info
Item 2 Info
Architecture
--
--
Frameworks
--
--
Annotation Format
Instance Segmentation
Instance Segmentation
GitHub Stars
3.3k+
--
16,000
--
License
Tongyi Qianwen
--
Apache-2.0
--
Training Notebook
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.

Read more of our analysis.

Download the raw image results from our analysis.

Compare QwenVL vs. LLaVA

Provide your own image below to test YOLOv8 and YOLOv9 model checkpoints trained on the Microsoft COCO dataset.

COCO can detect 80 common objects, including cats, cell phones, and cars.