A README-backed guide to using dsh-image-studio with DeepSeek Harness, including its documented installation path and capabilities.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-11-05
License
MIT
01What can it help you accomplish?
Use dsh-image-studio inside DeepSeek Harness
Registers imagegenerate and imagelibrary tools plus a web settings UI for reference assets, prompts, and generated images.
DeepSeek Harness users who need the repository README-described workflow
02How to install into DeepSeek Harness
Prerequisites
- DeepSeek Harness (DSH)
Installation steps
- 01
$ dsh plugin --profile desktop add https://github.com/aa1355721445-lgtm/dsh-image-studio
Verify the integration
Not specified by the author
Rollback
- **升级**：DSH 里第三方插件通过「卸载 → 重新安装」升级；素材库、关键词和配置都存在 `<DSH_HOME>\image-studio\`，卸载不会删掉。
03DSH integration and capability boundaries
DSH plugin bundle or extension described by the repository README
README-described plugin capability
DeepSeek Harness session or plugin host→dsh-image-studio · 生图工作室
Documented workflow integration
A configured DSH profile→给 DeepSeek Harness 加一个会「看场合发图」的生图能力：本地四个参考库（人物 / 服饰 / 场景 / 道具），
04Who is it for? When not to use it?
Good for
- DeepSeek Harness users who need the repository README-described workflow
Not for
- 需要：DeepSeek Harness 桌面版，以及一个生图接口（[65535](https://my.65535.space/) 的异步任务接口，或任何 OpenAI 兼容的 /v1/images 接口）。
05Compatibility, maintenance and safety notes
- 需要：DeepSeek Harness 桌面版，以及一个生图接口（[65535](https://my.65535.space/) 的异步任务接口，或任何 OpenAI 兼容的 /v1/images 接口）。
README and repository metadata fetched from GitHub
06Frequently asked questions
What is dsh-image-studio?
Registers image_generate and image_library tools plus a web settings UI for reference assets, prompts, and generated images.
How do I install it?
dsh plugin --profile desktop add https://github.com/aa1355721445-lgtm/dsh-image-studio
What should I check before using it?
给 DeepSeek Harness 加一个会「看场合发图」的生图能力：本地四个参考库（人物 / 服饰 / 场景 / 道具），
07Related DSH workflows
modlens
by liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
agent-vision-toolkit
by anionex
Vision toolkit and skills that give text-only LLMs eyes — multi-image understanding, image Q&A, OCR, frontend UI restoration and GUI automation, with optional agent integration.
dsh-vision-router
by ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh-image-gen
by shanliuling
Adds in-chat multimodal image generation via a `generate_image` tool with multi-provider support (Gemini/OpenAI/Seedream), interactive preview, copy/download, and session-attached results.
08Data and sources
给 DeepSeek Harness 加一个会「看场合发图」的生图能力：本地四个参考库（人物 / 服饰 / 场景 / 道具），
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-11-05. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.