dseyesopen
Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.
视觉桥：纯文本 DeepSeek 也能收图（单独发、图文混发均可），快速小识图模型后台描述，对话框里图还在、模型只见文字；纯插件，卸载即复原。
How to install
dsh plugin add github:balue8246-maker/dseyesopen About
dseyesopen **无感、自动、快速、真插件——仿佛 DeepSeek 真能看图了。** 挂 DeepSeek（无识图能力）照样发图：单独发、图文混发都行 图片自动交给快速小识图模型（glm-4.6v-flashx，识一张约 0.001 元）后台描述 描述不进对话框：对话框里你发的图原样还在，后台 DeepSeek 处理的是转成的文字描述 真插件：拔掉即恢复原样，不留痕迹 --- 安装 bash dsh plugin --profile web add file:/path/to/dseyesopen 重启 dsh web。 配置 API Key（3 步，2 分钟） 1. 打开 open.bigmodel.cn，手机号/微信注册 2. 控制台 → **API 密钥** → 创建新密钥 → 复制 3. dsh → **模型设置页** → Zhipu GLM Vision → 粘贴密钥 glm-4.6v-flashx 是极低价付费档，账号里充几块钱就够用很久（如遇高峰限流，免费档 glm-4.6v-flash 可作备选）。密钥也可以放进环境变量 ZHIPU_API_KEY。 粘贴截图：Cmd+V 直接成图 dsh 原生 composer 本身支持图片粘贴成**真附件**（无需 modlens / 无需 patch 配置）。 与 **dsDragPasteALL** 同时安装时，需…
Recommendation signals
Meta
- License
- –
- Language
- JavaScript
- GitHub stars
- 2
- mo. downloads
- –
- Last push
- 2026-08-21
- Created
- 2026-08-18
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令；无 license
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-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.