dsh-vision
Run the following command in DeepSeek Harness:
dsh plugin install xiaoshihou514/dsh-vision
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install this plugin with the command dsh plugin install xiaoshihou514/dsh-vision, and the full source address is https://github.com/xiaoshihou514/dsh-vision.
About this plugin
In AI model inference, vision capabilities are increasingly vital, yet traditional integration often involves complex setups or costs. The dsh-vision plugin offers a minimal, native solution to add vision enhancement for DeepSeek Harness users. It supports seamless access to the free Zhipu API and local Qwen-VL 2B model for inference, requiring no complicated configuration, and is ideal for rapid development and lightweight applications. This plugin is perfect for developers, researchers, and AI enthusiasts already using DeepSeek Harness, enabling them to quickly infuse vision intelligence without diving into setup complexities.
Screenshots
Use Cases
- Quickly add vision processing to AI applications.
- Use local models for privacy-safe image analysis.
- Reduce vision model integration costs via free APIs.
Best For
- Developers using DeepSeek Harness.
- AI researchers needing vision capabilities.
- Enthusiasts seeking lightweight vision solutions.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.