# dsh-vision-imagen

> DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.

## Metadata

- Author: [@xuxun-oss](https://github.com/xuxun-oss)
- Repo: <https://github.com/xuxun-oss/dsh-vision-imagen>
- GitHub: [xuxun-oss/dsh-vision-imagen](https://github.com/xuxun-oss/dsh-vision-imagen)
- Stars: 2
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Homepage: <https://github.com/xuxun-oss/dsh-vision-imagen>
- Topics: `ai`, `cordis`, `deepseek`, `deepseek-harness`, `dsh`, `dsh-plugin`, `gemini`, `gemini-api`, `generative-ai`, `google-gemini`, `image-editing`, `image-generation`, `image-recognition`, `llm`, `multimodal`, `ocr`, `plugin`, `text-to-image`, `vision`, `vision-language-model`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-20T05:03:10.000Z
- Added: 2026-08-20T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add dsh-vision-imagen
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-vision-imagen](https://deepseek-plugin.org/plugins/xuxun-oss/dsh-gemini-bridge)