Anionex/dsh-vision-toolkit

★ 825 · UI & Appearance

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service,

Install command
dsh plugin --profile web add @anionex/dsh-vision-toolkit

View on GitHubBrowse similar plugins

About this plugin

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service,

How to install

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

中文说明：Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service,（安装方式请参考 GitHub 仓库说明。）

More plugins like this