# dsh-vision

> DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥

## Metadata

- Author: [@reimu-create](https://github.com/reimu-create)
- Repo: <https://github.com/reimu-create/dsh-vision>
- GitHub: [reimu-create/dsh-vision](https://github.com/reimu-create/dsh-vision)
- Stars: 3
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh-plugin`, `multimodal`, `vision`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-16T09:20:28.000Z
- Added: 2026-08-16T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:reimu-create/dsh-vision
```

---

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