Generates images in DeepSeek Harness through configured OpenAI-compatible image models or a local MiniMax CLI, and displays the result in chat.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:corrinehu/dsh-chat-imagine
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time. Only install sources you trust, and pin a commit (github:owner/repo#sha).
README
English | 中文
Use image-generation tools already available to DeepSeek Harness (DSH) directly from the chat, then display the generated image in the conversation.

Overview
Two image-generation methods are supported:
- API: Uses OpenAI-compatible providers already configured in DSH and finds their available image models.
- CLI: Scans the local machine for the MiniMax CLI (
mmx). When it is found, it becomes an available image-generation backend.
Install
dsh plugin --profile web add github:corrinehu/dsh-chat-imagine
Usage
After installing the plugin, start a new conversation and ask for an image:
Create a cute blue whale logo.
The plugin checks available channels and models, then asks which one to use as the default:

Once you set a default, later requests can go straight to generation:
Generate a 16:9 sunrise over snowy mountains.
Create a minimal illustration for a technical blog cover.
The result appears in the chat.
You can also use another image backend:

Just name the backend you want in the conversation, for example:
Use a GPT image model to generate a WeChat article cover.
Notes
- Currently tested only in the DSH Web profile.
- Images are kept in DSH process memory. Historical image links stop working after restart; save images you want to keep from the chat UI.
License
Links
More in this category
liustack/modlens★ 1963
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
Anionex/dsh-vision-toolkit★ 440
Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.
superdesigndev/treg★ 419
Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.
Lum1104/dsh-browser★ 167
Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.
ysr666/dsh-vision-router★ 155
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
zhaoolee/notes★ 141
Export DSH conversations as Smartisan Notes-style PNGs, or create and update Markdown notes in a configured account-scoped workspace.