dsh-minimax-image
Run the following command in DeepSeek Harness:
dsh plugin install Jack-sun-learner/dsh-minimax-image
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Jack-sun-learner/dsh-minimax-image in your terminal to install this plugin, available at https://github.com/Jack-sun-learner/dsh-minimax-image
About this plugin
Describing a scene in a DSH conversation but only getting text back, then copying the prompt to a separate tool, waiting for the render, and pasting the result back — dsh-minimax-image collapses that entire workflow into one sentence. Powered by the MiniMax image-01 model, it registers an image-gen tool inside DSH so the model can turn a single-line visual description into a real PNG file, saved automatically into the workspace generated/ directory with a fully configurable output path.
Three capabilities stand out: eight aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9) covering vertical posters through ultra-wide banners; transparent credential reuse of MINIMAX_API_KEY from the environment or the DSH credential store with zero extra setup; and a clear configuration precedence chain — profile patch, standalone config file, then environment variables — so the same plugin serves both a quick demo and a production pipeline.
Built for developers and creators already working inside DSH who need product mockups, content thumbnails, concept art, or quick visual explorations without ever leaving the conversation. Describe, get the file, iterate — no context-switching required.
Use Cases
- Describe a visual scene in a DSH conversation and get a PNG back immediately
- Generate quick visuals for product docs, slides, or social media posts
- Explore poster, banner, and square layouts across multiple aspect ratios
Best For
- Developers doing content creation or prototype demos inside DSH
- Visual designers who need fast image iterations for UX exploration
- Full-stack engineers building multimodal workflows with DSH
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.