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.

Image Tiler — DSH Plugin for DeepSeek Harness
← Plugins
I

@dsh-external/dsh-image-tiler

Image Tiler

DSH agent tool: slice a large image into labeled ~800x800 tiles plus an overview thumbnail, preserving detail for vision models.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:meng-114/dsh-image-tiler#fd841d937bfd9b4278f040bddc286f4d8fa23106
READMECompatibilityVersions

Compatibility and provenance

Image Tiler is published as @dsh-external/dsh-image-tiler and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
8/21/2026

Versions

0.1.0stable
8/21/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 1
Weekly downloads
0
Last push
9/16/2026
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.Image Gendsh-image-genBring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.

README

dsh-image-tiler

面向 DeepSeek Harness（DSH）的 host 工具插件：把一张大图切成带坐标标注的 ~800×800 切片，并生成一张全局缩略图与 manifest，供视觉模型逐张读取，避免单张图被整体缩到约 800×800 等效像素而丢失细节。

功能

  • 工具：tile_image，参数包括 file_path、tile_size（默认 800）、overlap（默认 40px）、output_dir（默认 tiles）、format（png/jpeg/webp）、label、overview_size、max_tiles（默认 64）。
  • 输出：每个切片文件（文件名含 r<c>c<col> 与 x/y 坐标）、一张 *-overview.* 缩略图、一份 manifest.json。
  • 路径安全：输入与输出都限制在当前会话工作区（session.header.cwd）内。
  • 与 read_image 配合：先调用 tile_image，再用 read_image 逐张读取切片。

安装

通过受保护的 DSH 插件安装流程（plugin_install 或 dshpm）安装本目录为 bundle 插件；cordis.patch.yml 会被合并进 profile roster，安装后重启 Web 一次。

使用

让模型调用：

tile_image({
  file_path: "large.png",
  tile_size: 800,
  overlap: 40,
  format: "png"
})

返回切片路径后，再对每个切片调用 read_image。先看 overview 了解整体布局，再按坐标逐片细看。

设置

在 Web 的 设置 → 插件 中找到 image-tiler 卡片，可调整（即时生效，无需重启）：

  • 自动切片：开启后，用户发送大图时工具描述会引导模型先 tile_image 再逐张读取，而不是读被缩小的原图。
  • 切片边长 / 重叠 / 输出格式 / 最大切片数 / 缩略图边长 / 坐标标注 / 输出目录：作为 tile_image 的默认值；模型调用时显式传参仍可覆盖。
  • 清除覆盖：移除用户设置，回落到内置默认值（800px、40px、png、64 片等）。

限制

  • 输入仅限 PNG / JPEG / GIF / WebP；GIF 按首帧处理。
  • 单次最多 600 张（工具默认 64，可通过 max_tiles 上调），与 DeepSeek 官方 API 的 600 张/请求一致。
  • 输出写入会话工作区内的 tiles 目录；如需其他位置，请用工作区相对路径。