ds-vision-plugin
Run the following command in DeepSeek Harness:
dsh plugin install Sorwcyra/ds-vision-plugin
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, run the command dsh plugin install https://github.com/Sorwcyra/ds-vision-plugin to install the ds-vision-plugin.
About this plugin
In today's AI landscape, image understanding is becoming essential, but many powerful text-only models like DeepSeek lack native image input support, hindering users from directly sharing screenshots or images in conversations. The ds-vision-plugin addresses this gap by enabling image paste or drag-and-drop in the DeepSeek Harness Web composer, automatically converting images to text to provide a natural image-input experience for DeepSeek. Its core capability lies in racing four vision models, including Agnes and GLM series, to ensure swift and reliable conversions while preserving DeepSeek's text-only nature, with transparent failure handling. This plugin is ideal for developers, researchers, or anyone looking to extend DeepSeek's functionality, offering seamless image processing without deep technical involvement, especially suited for applications needing efficient integration of vision features into text models.
Screenshots
Use Cases
- Pasting screenshots into DeepSeek chat
- Automatically converting images to text descriptions
- Racing four vision models for reliable results
Best For
- Developers looking to extend DeepSeek functionality
- Researchers handling multimodal data
- Users needing efficient image processing 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.