dsh-omni-vision
Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.
为纯文本模型装上本地眼睛：eyes_render 在 Web 界面画布上绘制文字/图形/Mermaid，eyes_paste 接收用户粘贴的图片，eyes_ocr 用 Windows 自带 OCR 离线读文字，eyes_analyze 把像素解析成结构化数据，全程无需视觉模型。
How to install
dsh plugin add github:Renji004/dsh-omni-vision About
dsh-omni-vision **本插件全由 DeepSeek v4 Flash（deepseek-v4-flash）编写。** 让 Agent 自己"看见"文字与图形的 DSH 插件，全程本地、不依赖视觉模型： **eyes_render** — 在 Web GUI 对话流里渲染画布（文字、线条、矩形、圆形、椭圆），PNG 落盘到工作区 renders/（读完即焚），并**一式两份**另存永久副本到 pics/。 **eyes_paste** — 让用户把剪贴板图片（截图/照片）直接 Ctrl+V 粘贴或拖进页面：浏览器捕获图片、归一化为 PNG 存到工作区，供本地 OCR/像素分析读取。只写 renders/（读完即焚，**不留** pics/ 永久副本）。**全本地读图路径**（不限流、离线），独立于 DSH 原生发图链路（DSH 输入框本身支持图片粘贴/拖放，但发图需要选择支持图片的模型，见"限制"）。 **eyes_ocr** — 用 Windows 自带 OCR（Windows.Media.Ocr，完全离线）把 PNG 里的文字读回成文本。**这是 Agent "看见文字"的途径**：DeepSeek 是纯文本模型，但识别出的文本可以原样喂回给模型引用。 **eyes_analyze** — 把 PNG 解码成像素数据（N×N 颜色网格、主色占比、内容包围盒）。**这…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-18
- Created
- 2026-08-18
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
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, 100 per machine per day; configurable to your own provider.
picturereader
jing-hy/picturereader
Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.