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.

V4flash Tiler — DSH Plugin for DeepSeek Harness
← Plugins
V

dsh-v4flash-tiler

V4flash Tiler

DSH plugin: auto-tiles oversized chat images into labelled grid pieces (row/col metadata, overlap-aware, multi-image group isolation) so the DeepSeek vision model keeps fine detail instead of the ~800px downsample.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:doublehappy123/dsh-v4flash-tiler#bfa360e8663996bf4f4ae836ec342c647b920524
READMECompatibilityVersions

Compatibility and provenance

V4flash Tiler is published as dsh-v4flash-tiler and currently resolves to version 0.2.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
9/1/2026

Versions

0.2.0
stable
9/1/2026

Related plugins

Loading related plugins…

Latest
0.2.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
MIT
Source
github
GitHub
★ 1
Weekly downloads
0
Last push
9/18/2026
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-v4flash-tiler

DeepSeek 视觉模型的大图自动分块插件:在聊天里发送超大图片时,宿主自动把它切成多块高清图块(带行列坐标标注)再送入模型,让细小文字、图标、图表细节不再被 800×800 的自动缩放抹掉。本仓库根目录即官方发布说明(publish.zh.md)所述的组合包,可直接 dsh plugin add 安装;Python 切块引擎位于 engine/。

背景

DeepSeek 视觉模型接收图片时会自动缩放(大于约 800×800 等效像素即整体缩小,单张 token 上限约 384),超大截图、密集小字、图表细节因此丢失。本插件把大图切成最多 9 块、15% 重叠的小图块,让每块保持原始清晰度,并向模型提供网格、每块(行,列)坐标、重叠说明,使其能按坐标拼回整图;一条消息多张图时,每张原图的块自成一组并明确禁止跨图混拼。

安装

# 1) Python 引擎(插件在运行时调用 python -m v4flash_tiler.driver)
pip install -e ./engine        # 或 pip install ./engine

# 2) 组合包 → profile(纯 JS 无需构建,GitHub 直装即可)
dsh plugin --profile web add github:doublehappy123/dsh-v4flash-tiler
# 或本地:dsh plugin --profile web add ./dsh-v4flash-tiler

# 3) 重启 DSH(该 profile)

每个 profile 插件栈独立,需按 profile 分别安装。CLI 手动分析模式额外需要 DEEPSEEK_API_KEY;自动分块不调用 API。

使用

  • 聊天自动分块:直接发送任意图片。任一边 > 1024px 自动切块并标注行列;小图原样直通;失败自动回退原图并在消息中说明原因。
  • 命令行(engine/ 安装后):
    v4flash-tiler --image screenshot.png --mode auto --dry-run      # 只看分块计划
    v4flash-tiler --image screenshot.png --prompt "提取全部文字"    # 调 API 分析
    
  • Python API:
    from v4flash_tiler import DeepSeekVisionClient
    result = DeepSeekVisionClient().analyze_image("large.png", prompt="分析这张图")
    

仓库结构(与官方发布说明一致)

package.json            # 组合包 manifest:dsh.bundle.patch
cordis.patch.yml        # 插件行(id: v4flash-tiler)
lib/index.js            # Host 半边:agent/pre-step 自动分块
engine/                 # Python 引擎(v4flash_tiler 包 + CLI + 测试)

配置要点

  • 阈值:任一边 > 1024px 即分块;单图最多 9 块(1024px、15% 重叠、JPEG 质量 90)
  • 每条消息图块总数受 DSH 附件上限保护,超限图片保持原图直通
  • 每块输入 token 约 384,9 块 ≈ 3400 token/图

License

MIT