qwen2-vl 开源项目推荐（117 个）

roboflow /maestro

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

2U1 /Qwen-VL-Series-Finetune

阿里云对Qwen-BL系列进行微调的开源实现。

PaddlePaddle /PaddleMIX

Paddle 多模态集成与探索，支持主流多模态任务，包括端到端大规模多模态预列模型和扩散模型工具箱。配备高性能和灵活性。

worldbench /DriveBench

[ICCV 2025] Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

col14m /cadrille

cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

NetEase-Media /grps_trtllm

比 vLLM 服务更高性能的 OpenAI LLM 服务：纯 C++ 高性能 OpenAI LLM 服务，采用 GPRS+TensorRT-LLM+Tokenizers.cpp实现，支持聊天和函数调用、AI 代理、分布式多 GPU 推理、多模态能力和 Gradio 聊天界面。

arcstep /illufly

✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体

soulteary /dify-with-qwen-vl

视频理解：千问视频多模态模型 & Dify

WalkerWorldPeace /MLLMerging

[ICLR 2026] OptMerge: data-free merging of multimodal LLM experts (VQA, Geometry, Chart, OCR, Grounding) and modalities, plus SWUDI / ASWUDI closed-form spectral merging for CLIP-ViT, Flan-T5, Llama-3.2 and MLLMs.

fireicewolf /wd-llm-caption-cli

A Python base cli tool for caption images with WD series, Joy-caption-pre-alpha,meta Llama 3.2 Vision Instruct and Qwen2 VL Instruct models.

Younis-Ahmed /qwen-ai-provider

Community-built Qwen AI Provider for Vercel AI SDK - Integrate Alibaba Cloud's Qwen models with Vercel's AI application framework

see2023 /autoXHS

基于多模态大模型的智能搜索助手，通过AI技术实现小红书平台的智能化信息检索和知识整合|An intelligent search assistant based on multimodal large models, enabling smart information retrieval and knowledge integration on the Xiaohongshu platform.

shaadclt /Qwen2-VL-OCR-VQA

This project demonstrates how to use the Qwen2-VL model from Hugging Face for Optical Character Recognition (OCR) and Visual Question Answering (VQA). The model combines vision and language capabilities, enabling users to analyze images and generate context-based responses.

KhadgaA /Amazon-ML-Challenge

This repo contains the winning code for Amazon ML Challenge 2024. The challenge was to develop a Machine Learning model to extract product entity details directly from the product images.

aws-samples /sample-for-multi-modal-document-to-json-with-sagemaker-ai

This open-source project delivers a complete pipeline for converting multi-page documents (PDFs/images) into structured JSON using Vision LLMs on Amazon SageMaker. The solution leverages the SWIFT Framework to fine-tune models specifically for document understanding tasks.

BUAADreamer /Qwen2-VL-History

Qwen2-VL在文旅领域的LLaMA-Factory微调案例 The case for fine-tuning Qwen2-VL in the field of historical literature and museums

zhangguanghao523 /CMMCoT

[AAAI'26] Official implementation of CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation

ZachcZhang /Qwen2-VL-inference

An open-source server implementation for inference Qwen2-VL series model using fastapi.

aurintex /pai-os

Open-source AI wearable companion. Local-first multimodal perception (VLM & Audio) on Edge NPU. Built with Rust & Flutter.

RahulSChand /chess_vlm

Repo to test and finetune VLMs on chess tasks