dsh-draw-router
Run the following command in DeepSeek Harness:
dsh plugin install xiaozhe7772222/dsh-draw-router
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command 'dsh plugin install xiaozhe7772222/dsh-draw-router'; the source code is available at https://github.com/xiaozhe7772222/dsh-draw-router.
About this plugin
DeepSeek Harness (DSH) is a powerful LLM agent framework, but it lacks built-in image generation capabilities, preventing users from creating images directly through conversation. The dsh-draw-router plugin addresses this by acting as a universal image generation router, adding draw_image and draw_list_sources tools to DSH. This enables agents to generate images naturally within chat, just like executing commands.
The plugin's core strengths lie in its intelligent model detection and broad compatibility. Users only need to provide any OpenAI-compatible base URL and API key; the plugin then automatically probes and identifies supported drawing models without manual specification. It supports dozens of image generation providers, including SenseNova, StepFun, DashScope, Hunyuan, GPT Image, Flux, and more, handling API quirks automatically. Additionally, via REST API, users can manage draw sources at runtime, add models manually, and persist configurations to survive restarts.
dsh-draw-router is a practical extension for teams or individuals using DeepSeek Harness for AI application development. It is especially suitable for scenarios requiring integrated image generation in conversations, such as creating visual content, assisting design, or educational demonstrations. Whether you're a developer or an end user, you can enjoy the convenience of AI image generation with simple configuration.
Use Cases
- Generate images directly in chat
- Auto-detect and integrate multiple drawing models
- Add visual creation features to AI assistants
Best For
- DeepSeek Harness developers
- AI application users requiring image generation
- Content creators and designers
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.