liustack/modlens

★ 3,664 · UI & Appearance

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

💬 Paste an image, get vision analysis from text-only models. Fills a real gap.
贴图就能让纯文本模型看图，补上了真空白。

Install command

dsh plugin --profile web add @liustack/modlens@3.25.0

About this plugin

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Run the install command above inside your DeepSeek Harness environment. Requires DSH 0.1.x+.

中文说明：Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).（安装方式请参考 GitHub 仓库说明。）