dsh-plugin-mm-vision
Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.
通感编码器（Synesthesia Encoder）：调用视觉模型把图片翻译成紧凑的结构化空间文字（画布/元素/百分比坐标），让纯文本 LLM 获得像素级看图能力（`mm_vision` 工具）。
How to install
dsh plugin add dsh-plugin-mm-vision About
dsh-plugin-mm-vision **通感编码器 (Synesthesia Encoder) · DeepSeek Harness 插件** 给任何纯文本 LLM(DeepSeek、GPT-4 base、Claude…)获得**看图能力**:调用视觉模型把图片翻译成紧凑的**结构化空间文字**(画布/元素/百分比坐标/形状/数值/关系),文本模型据此重建空间认知、推理位置关系。 移植自 Elohia/pi-mm-vision(MCP / Pi / Codex / Claude Code 多宿主通感编码器)。核心零依赖,支持任意 OpenAI 兼容视觉模型(qwen-vl / gpt-4o / glm-4v / kimi-vl / MiniMax-VL…)。 ✨ 功能 🖼️ **通感编码**:把图片变成坐标化文字描述——K线图/盘面截图/报告图表/UI 截图/自然照片都适用 📍 **像素级坐标**:所有关键元素带精确 (x%,y%) 百分比坐标(图表转折点/标注/按钮/文字块) 🔢 **可选像素网格**:prompt 含"像素/重建/还原"关键词时,输出 40×30 色块网格(RGB),供原图重建 🔄 **模式自适应**:auto 自动识别图表(坐标优先)vs 自然图(构图主体);也可手动指定 brief/full/coords/pixel 🧠 **缓存**:TTL…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 1
- mo. downloads
- 240
- Last push
- 2026-08-14
- Created
- 2026-08-14
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-web
zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
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.
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.