Communityv0.1.0

Ms Qwen Vl

调用魔搭社区（ModelScope）Qwen3-VL 多模态 API 进行视觉解析。使用 OpenAI SDK 兼容方式调用，支持图片内容描述、OCR 文字提取、视觉问答、对象检测等功能。用户提到"魔搭"、"ModelScope"、"Qwen-VL"、"多模态视觉"、"解析图片"等关键词时应触发。

1.7kdownloads4active installscrocketc
View on ClawHubBack to Skills

Skill Details

Slug
ms-qwen-vl
Latest Version
0.1.0
Author
crocketc
Published
Feb 2, 2026
Updated
Apr 28, 2026
Total Versions
1

How to Install

  1. 1 on OpenClawdBots (takes under 60 seconds).
  2. 2Open your bot dashboard and go to the Skills tab.
  3. 3Switch to the ClawHub tab and search for “Ms Qwen Vl”.
  4. 4Click Install and the skill is deployed to your bot automatically.

Changelog — v0.1.0

- Initial release of ms-qwen-vl skill for multi-modal visual analysis via ModelScope Qwen3-VL API. - Supports image description, OCR text extraction, visual question answering, object detection, and chart analysis. - Compatible with OpenAI SDK, with sample Python and CLI usage provided. - Handles both local images (auto-converted to base64) and online image URLs. - Offers two model modes: fast (30B) and precise (235B). - Detailed task options and usage instructions included in the documentation.