xby-head-person-detection
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-head-person-detection
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install xby-skill/xby-head-person-detection; the full source is available at https://github.com/xby-skill/xby-head-person-detection
About this plugin
In image analysis and content understanding pipelines, locating human heads and bodies is the most fundamental step. xby-head-person-detection wraps this capability into a single, straightforward call: feed it an image and get back bounding boxes, confidence scores, and labels for every detected target, without the overhead of standing up your own inference service.
The plugin accepts images in three flexible formats — URL, BASE64-encoded string, or local file path — making it easy to slot into online services, local scripts, or offline batch jobs alike. API key configuration is persistent, so you set it once and it survives restarts, eliminating repetitive setup.
It is well suited for developers and teams who need to integrate head and person detection quickly: whether your use case is smart album sorting, pose analysis, or target localization in interactive applications, a single call returns structured detection results ready for downstream processing.
Use Cases
- Automatically detecting and labeling people in smart album applications
- Quickly locating all head and body targets in content moderation pipelines
- Detecting human body targets in interactive apps to drive downstream pose analysis
Best For
- Independent developers who need quick head and person detection integration
- AI engineering teams building visual analysis pipelines
- Software engineers embedding structured detection into existing applications
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
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.