dsh-llm-deepseek-vision
Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.
视觉增强的 DeepSeek 适配器：由视觉模型把图片描述成文字，纯文本 DeepSeek 模型再基于描述推理。
How to install
dsh plugin add github:NagasakiSoyo-ui/dsh-llm-deepseek-vision About
dsh-llm-deepseek-vision 给 DeepSeek Harness 的纯文本模型装上"眼睛"的视觉插件。 Vision-augmented adapter plugin for DeepSeek Harness. 它让**纯文本**模型能够"看"图片：每个附加的图片先交给另一个**视觉模型**描述成文字，再由纯文本模型基于描述进行推理。推理模型永远不需要直接处理图片字节——另一个模型是它的眼睛。默认文本推理与图片描述都跑在 OpenCode Zen Go（opencode-go）。 工作原理 / How it works 注册一个额外的 provider 路由：**DeepSeek (Vision)**（deepseek-vision），对外广告与 DeepSeek 目录相同的模型 id（deepseek-v4-flash / deepseek-v4-pro），但声明 [text, image] 输入。 **不带图片的请求**：零开销，直接透传给文本推理路由（默认 opencode-go）。 **带图片的请求**：配置的视觉模型把每张图描述成文字（[Image #N description: …]），图片块被描述替换，纯文本模型再作答。 快速开始 / Quick start 1. 安装插件 **推荐（一键安装）**——插件已发布到 npm，声明了 dsh.bund…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-08-14
- Created
- 2026-08-14
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
- deepseek-harness, dsh-plugin, llm, plugin, vision
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.