DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Plugin Use Images — DSH Plugin for DeepSeek Harness
← Plugins
P

dsh-plugin-use-images

Plugin Use Images

Use image-generation HTTP APIs as native image models in DeepSeek Harness

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:chuling-lingling/dsh-plugin-use-images#1608c61c0f9c68d2dd652809b0e520df5ca9eb15
READMECompatibilityVersions

Compatibility and provenance

Plugin Use Images is published as dsh-plugin-use-images and currently resolves to version 0.2.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
9/11/2026

Versions

0.2.1stable
9/11/2026

Related plugins

Loading related plugins…

Latest
0.2.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
9/11/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIDeepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.Imagegen@dickpy/dsh-imagegenAI image generation plugin for the dsh web GUI: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana a

README

dsh-plugin-use-images

把生成图片的 HTTP API 适配成 DeepSeek Harness (dsh) 可选模型。用户在聊天框选中图片模型后,最后一条用户文本会作为 prompt 发送给图片 API;响应会被转换为 DSH 原生图片块,持久化到会话附件存储中。

支持的响应

  • JSON URL,如 data[*].url
  • JSON base64,如 data[*].b64_json
  • JSON data URL
  • text/plain 的 URL 或 data URL
  • HTTP 直接返回 image/png / image/jpeg / image/webp / image/gif

请求 body 是可配置的 JSON 模板,可用 {{prompt}}、{{model}}、{{n}} 和 {{apiKey}}。响应字段使用简化路径,例如 data[*].url、output.images[*]。

在设置页添加 API

安装并重启 DSH 后,打开「设置 → 图片 / 视频 API」。点击「新增 API」并选择接口预设,填写 Base URL、API Key 和模型 ID 即可。高级接口还可在同一页调整请求 JSON、Headers 和响应提取路径。

页面内可以直接新增、编辑和删除接口,保存后 DSH 模型列表会热更新,无需手工编辑 settings.yaml。

安装

# 从 GitHub 直接安装(推荐)
dsh plugin --profile web add github:chuling-lingling/dsh-plugin-use-images

# 卸载
dsh plugin --profile web remove dsh-plugin-use-images

安装后重启 dsh web 即可生效。完整的接口配置见 EXAMPLE.md。

YAML 备用配置方式

通常不需要手工改 YAML。如果 Web 设置页不可用,仍可用 inbox 导入:

use-images:
  inbox: |-
    {"把 EXAMPLE.md 中的 JSON 粘贴到这里": true}

如果解析失败,错误会保留在 use-images.lastError。已生效的路由保存在 use-images.routes,修改设置后会热更新模型列表。

关键字段

字段用途
idDSH 供应商 id,只能用小写字母、数字和 -
models在聊天模型选择器中显示的模型
request发送给生图 API 的 JSON 模板
extractUrls从 JSON 响应提取 URL 的路径
extractB64从 JSON 响应提取 base64 的路径
responseModeauto、json 或 binary
maxResponseBytes单张下载图片上限,默认 20 MiB
timeoutMs生成及下载的总超时,默认 120 秒

设计说明

DSH 的 LLM runtime 只接收统一的流事件,而图片 API 通常是一次性 JSON 或二进制响应。本插件实现自定义 LlmAdapter:先执行图片 HTTP 请求,再把结果存入 attachments,最后发出 block-start(image) / block-end(image) / finish 事件。因此不需要修改 DSH 的文本适配器。