DSH插件商店

dsh-tool-read-tiff

fulander0301

Model-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.

dsh-mindseye

kanchengw

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.

dsh-pro-vision

lasdrder0705

DSH plugin: let DeepSeek-V4-Pro use V4-Flash-Vision-Exp for attached images. Install: dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

dsh-imagegen

little-traincar

Image generation plugin for DeepSeek Harness — Doubao Seedream 5.0 Pro / qwen-image-3.0-pro, watermark-free, verbatim in-image text, inline chat display.

dsh-vision-bridge

lium970320

DSH 视觉桥接插件：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）

oh-my-dsh

llmpolska

oh-my-dsh — tiered model routing plugin for DeepSeek Harness: think/build tiers, vision delegation, image generation. MIT.

chat-deepseek-vision

orrinzeng

A native DeepSeek Harness (DSH) Cordis plugin that analyzes images through the reverse-engineered chat.deepseek.com vision mode (model_type=vision) — free, no third-party vision API key required. DeepSeek Harness（DSH）原生 Cordis 插件：通过逆向 chat.deepseek.com 识图模式（model_type=vision）分析图片，免费、无需第三方视觉 API key。

dsh-vision-suite

princefrogdida-ux

Windows-first vision suite with image understanding, OCR, screenshot diffing, and multi-provider routing for DeepSeek Harness.

mimo-vision

wulusai2333

DeepSeek Harness (DSH) native plugin — describe_image tool: a vision bridge (image → mimo-v2.5 → text description) over the ctx.fs / ctx.credentials seams

dsh-image-vision

xsoc1

Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.

dsh-tool-comfyui

yuehancn

Let DeepSeek Harness generate images: call local or LAN ComfyUI workers directly from chat (status, generate, queue).

tolten-image-attach

EmmanuelMartinez

Attach an image to the DeepSeek Harness composer and the session model switches itself to a vision model — then restores your previous model when the image is removed. Material Design 3 button, native file picker, thumbnails. MIT.

dsh-mingmu

Lab-sku

明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别

dsh-image-question

LonelyHerbivore

DSH Web plugin: ask the user a question with an image, annotate in the browser, get back structured annotations in source-image pixel coordinates.

anima-style-lora-workflow-bundle

Nana7mi0721

DeepSeek Harness 插件包：Anima 风格 LoRA 数据集全流程引擎，覆盖抓图下载 → 去重筛选 → 文字检测修补 → 重排编号 → 打标洗标 → 训练配置。自带 anima_status/anima_stage/anima_job/anima_doctor 四个工具、Agent 预设与图形设置页，另有一套可脱离 DSH 独立运行的 15 阶段 Python CLI。

dsh-image-tiler

Tiko9527

DSH high-resolution image tiler: slices large images into <=800x800 tiles before sending to DeepSeek. Highly AI-native, only DeepSeek participation.

dsh-plugin-glm-vision

baldovinmarques391-design

GLM Vision plugin for DSH: image translation for non-multimodal models via GLM-4V-Flash

dsh-codex-media

binsarjr

Image & document analysis tools for DeepSeek Harness, powered by a local OpenAI Codex CLI (zero deps, 3 transports, pairs with dsh-drop-to-path)

dsh-remote-deliver

demacia1314

🚀 告别繁琐 SCP！远程部署 DSH 一键下载修改后的文件与图片预览交付插件

dsh-image-bridge

hZsFN

Image message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen script

dsh-file-explorer-kit

ice5kysl

dsh (DeepSeek Harness) file explorer: browse the active session's workspace and preview files (Markdown/image/PDF/text/binary) right inside the chat GUI — a standard Cordis bundle plugin (read-only /dsh-files host routes + a conversation.view file tab).

dsh-docs

protoctistmoses143

Convert PDFs, Office docs, scanned images, and more to clean Markdown, JSON, or text locally with offline OCR—no servers, no API keys, fully private.