Review
Why we picked it
Pending human review — the facts below come from the source repository.
What it does
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).
Who it’s for
Users who want this capability in DSH; check the source and docs before installing.
Risks & caveats
- No strong risk signals; still worth a source look before installing.
> 上图实拍:粘贴一张 MSN 截图,问「介绍这个页面的布局」。注意中间的