DSH-dseyes
Native image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.
为纯文本 DeepSeek 提供原生图片上传体验：在 Web GUI 粘贴/拖入图片即以缩略图附件进入会话，发送前由 host 用免费智谱 GLM-4V-Flash 视觉 API（glm-4v-flash 降级链）读取并替换为文字描述，DeepSeek 据此回答，原图保留在聊天历史中。
How to install
dsh plugin add dsh-dseyes About
DSH-dseyes 给 DeepSeek Harness 装上「眼睛」 **中文** | English **DSH-dseyes** 让 DeepSeek Harness 的纯文本模型（DeepSeek）拥有**原生图片上传体验**： 在 Web GUI 聊天框里**粘贴或拖入一张图片**，可以像正常 AI 聊天那样： 1. 图片作为**附件**显示缩略图（聊天历史里保留原图，可点击放大）； 2. 发送后，host 端自动用**智谱 GLM 免费视觉模型**（glm-4v-flash → glm-4.6v-flash → glm-4.1v-thinking-flash 自动降级链）识别图片内容； 3. DeepSeek 收到的是图片的文字描述——它会基于图片内容直接回答你。 不需要任何额外命令、不需要手动转文字、不需要改模型。 **原理**：DSH 原本在 session.prompt 的图片准入检查里会拒绝带图消息（DeepSeek 适配器声明 inputModalities: ["text"]，报 MODEL_DOES_NOT_SUPPORT_IMAGES）。DSH-dseyes 在 host 端做两件事： 1. **放行准入**——让图片以附件形式真正进入会话（所以缩略图、历史、点击放大全都正常）； 2. **LLM 调用前自动替换**——在消息发给 DeepSeek 之…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 2
- mo. downloads
- –
- Last push
- 2026-08-19
- Created
- 2026-08-18
Basic safety check
- Findings
- None
- 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.