AI Agent Hub
Back to plugins
🤖

dsh-minimax-image

Model Inference Updated 2026.08.19

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