qwen-vl 开源项目推荐（148 个）

aiptimizer /TurboOCR

TurboOCR，在 OmnidocBench 上 >200 img/s。TensorRT FP16、PP-OCRv6、HTTP + gRPC

1038lab /ComfyUI-QwenVL

ComfyUI-QwenBL自定义节点：集成了Qwen-BL系列（包括Qwen 2.5-BL和最新的Qwen 3-BL），并支持GGUF在文本生成、图像理解和视频分析方面的高级多模式人工智能。

zli12321 /Vision-Language-Models-Overview

一个最前端的视觉语言模型论文集和模型汇总，GitHub 仓库。持续更新。

zjysteven /lmms-finetune

一个用于微调大型多模态模型的最小代码库，支持 llava-1.5/1.6、llava-interleave、llava-next-video、llava-onevision、llama-3.2-vision、qwen-vl、qwen2-vl、phi3-v 等。

zli12321 /Vision-SR1

基于自视觉感知奖励的视觉语言模型强化学习

TIGER-AI-Lab /RewardHarness

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

Shaohan-He /deepseek-eyes

给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL

reidbarber /webmarker

Mark web pages for use with vision-language models

sunxin-ai /dsh-design-qa

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected defects, and every raw model transcript. Retires itself when DeepSeek ships vision.

dolphin-creator /VideoContext-Engine

Local Video RAG Engine. A FastAPI microservice for video understanding: Scene Detection + Whisper ASR + Qwen3-VL. Optimized for Apple Silicon (MLX) & Windows/Linux (Llama.cpp).

zsxm1998 /awesome-perception-aware-rlvr

Unified reproductions, benchmarking & evaluation for perception-aware RLVR and OPD in VLMs, plus multi-turn agentic RL with HTTP, OpenEnv and OpenReward environments. 19 methods · 30+ benchmarks · Official code of CGPO (ACM MM 2026 Oral).

Codeeaner /Computer-Use-Agent

An AI Agent that is able to control your screen to complste any task

bruhosdotai /bruhOS

The skill OS that stands next to the robot. Runs like your bruhhh.

mimika9937-glitch /VisionMCP

Visual bridge for text-only models and visual enhancement toolkit for multimodal AI agents — OCR, zoom, PDF/Office rendering, web vision and interaction.

odebo /CC-Vision

Give non-multimodal Claude Code main models the ability to see pasted screenshots — a ~200-line UserPromptSubmit hook.

janelu9 /EasyLLM

Running Large Language Model easily.

Apageoflove /VLM-Driving-Scene-Understanding

基于Qwen2.5-VL-3B + QLoRA的智能驾驶场景结构化理解系统

nanofatdog /video-to-prompt

🎬 Extract AI prompts from video using Vision LLM (llama.cpp API) — Gradio WebUI + CLI

Ygria /poster-grid-inspector

Model-agnostic AI poster grid inspector: detect a poster's layout grid system with a vision model, view it overlaid, and export SVG guides / CSS Grid / Tailwind code. Ships as an installable agent skill.

ziyouzhiyi666888 /PE_SmartFixer

🚀 PE-SmartFixer：国内首款基于 AI 视觉大模型（Qwen-VL）的 Windows PE 离线系统修复与蓝屏诊断智能工具。纯 Go 语言编写，支持脱机维护与注册表挂载。