# dsh-eyes

> Give text-only DeepSeek models on-demand vision: upload images, DeepSeek answers by calling a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

## Metadata

- Author: [@Leeminjing](https://github.com/Leeminjing)
- Repo: <https://github.com/Leeminjing/dsh-eyes>
- GitHub: [Leeminjing/dsh-eyes](https://github.com/Leeminjing/dsh-eyes)
- Stars: 1
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `dashscope`, `deepseek-harness`, `dsh-plugin`, `multimodal`, `ocr`, `openai-compatible`, `qwen`, `vision`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-16T15:45:18.000Z
- Added: 2026-08-16T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add dsh-eyes
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-eyes](https://deepseek-plugin.org/plugins/Leeminjing/dsh-eyes)