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.

Vision & Media DSH plugins — Page 8

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1030Memory & Context1293Coding & Developer Tools2799UI & Customization3662Integrations & Communication1903Vision & Media615Search & Research864Security & Access1275Models & Usage1677Productivity & Workflow2232

All plugins

607 plugins
Wv0.1.0
wavespeed-dsh-skill

Wavespeed Dsh Skill

WaveSpeed skill for DeepSeek Harness (dsh): generate and edit AI media (image, video, audio, 3D) via the open-source wavespeed CLI.

vision-media★ 3↓ 0
Updated 8/21/2026
Pv0.2.0
dsh-plugin-video-player

Plugin Video Player

DSH web GUI client plugin: video browsing window (select folder / Douyin-style vertical video browsing / ←→ seek / ↑↓ or drag to switch)

vision-media★ 3↓ 0
Updated 8/21/2026
Vv1.3.0
dsh-vision-imagen

Vision Imagen

DeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转等），生成后自动视觉自检反馈，优于 modlens。

vision-media★ 3↓ 0
Updated 8/21/2026
Mv0.1.0
meow-vision

Meow Vision

dsh plugin: gives text models a pair of eyes + gives multimodal models a pair of eyes to observe UI rendering — settings popup for selecting a vision model + meow_vision tool + meow_preview component screenshot tool

vision-mediaui-customization★ 3↓ 0
Updated 8/21/2026
v0.1.1
@fzhiyu/dsh-image-view

Image View

Show the image a read_image call returned, inline in the tool row it belongs to

vision-media↓ 2
Updated 10/16/2026
v0.1.1
dsh-qr-toolkit

Qr Toolkit

QR code & barcode toolkit for DeepSeek Harness: decode images (PNG/JPEG, local or URL) and generate QR codes as PNG. 二维码/条码工具箱：解码与生成。

vision-media★ 0↓ 2
Updated 10/16/2026
Fv0.2.2
@fhl-plugins/dsh-fhl-image

Fhl Image

Independent DeepSeek Harness bundle for FHL Images generation, editing, worker pools, and chat-configured credentials.

vision-media★ 2↓ 0
Updated 10/14/2026
v1.7.6
dsh-chat-image-lightbox

Chat Image Lightbox

对话里的图值得被认真看：点一下全屏灯箱（缩放/拖拽平移/下载另存/左右翻页），一键把会话内的图收成可调列数的缩略图网格，或整块隐藏（不留空白）；本地图 TIFF/HEIC 自动无损转码，网图被防盗链拦截时自动转存本地显示。| Chat images get a proper look: full-screen lightbox (zoom / drag pan / download / prev-next), a conversation-wide thumbnail grid with adjustable columns, hide/show without leaving blank s

ui-customizationvision-media★ 2↓ 0
Updated 10/14/2026
Cv1.0.0
@cikian/dsh-cture-image

Cture Image

OpenAI-compatible image generation for DeepSeek Harness: text-to-image, image editing and batch generation, with the pictures rendered straight in the conversation — 通过 OpenAI 兼容接口生图与修图。

vision-media★ 2↓ 0
Updated 10/14/2026
Mv0.2.0
dsh-media-gen

Media Gen

Generate images and videos in DSH chat via OpenAI-compatible providers configured in Model settings; dedicated Settings menu and workspace media_gen output.

vision-mediamodels-usage★ 2↓ 0
Updated 10/12/2026
Gv0.3.2
dsh-gpt-sovits

Gpt Sovits

GPT-SoVITS text-to-speech for the DeepSeek Harness web GUI: per-reply read-aloud, an auto-read toggle, native model switching and a settings page. Ships no model weights and no reference audio.

vision-media★ 2↓ 0
Updated 10/9/2026
Cv0.1.0
dsh-comfyui-image

Comfyui Image

Drive a local ComfyUI image workflow (Z-Image-Turbo, Qwen-Image-2.1) from DeepSeek Harness

vision-media★ 2↓ 0
Updated 10/2/2026
Mv0.2.0
dsh-music-code-mv

Music Code Mv

DSH 插件：把一支 MV 写成代码（music-code-mv）。确定性的 Canvas2D / Three.js 镜头在无头 Chrome 里逐帧渲染，再用 ffmpeg 编码；并带一个中文图形界面「MV 工坊」。 / DSH plugin: render code-driven music videos, with a Chinese MV Studio GUI.

vision-mediadeveloper-tools★ 2↓ 0
Updated 10/1/2026
Iv0.3.0
imgpost

Imgpost

图邮 (imgpost): Let your DSH send and view images — local images, web images, AI image generation + image recognition (one eye), sent into the conversation with one click.

vision-mediaintegrations-communication★ 2↓ 0
Updated 9/29/2026
Rv0.1.6
dsh-reel

Reel

Media library for the dsh web UI: browse configured local directories as a grid or list, open images in a viewer, and play videos in a page-fullscreen player with swipe navigation, order/random playlists and a fullscreen wallpaper.

vision-media★ 2↓ 0
Updated 9/29/2026
v0.3.1
@max-null/dsh-capture

Capture

SSiD (思灵) quick screenshot capture: tray/hotkey → fullscreen box-select overlay → cropped image into the current conversation composer

vision-media★ 2↓ 0
Updated 9/28/2026
Qv0.2.0
dsh-qrcode

Qrcode

Offline QR code generator for DeepSeek Harness (dsh): pure-JS, no network, no shell, cross-platform. Model tools (qrcode + barcode) with SVG/PNG/ASCII output.

vision-media★ 2↓ 0
Updated 9/26/2026
Pv0.7.0
@dsh-external/dsh-pseudo-vision

Pseudo Vision

Adds opt-in image-capable sibling routes for text-only providers and converts image blocks into budgeted, locally enhanced OCR, color-statistics, pixel-scan, and metadata evidence before delegation.

vision-media★ 2↓ 0
Updated 9/25/2026
Vv0.5.0
@dsh-external/dsh-vision-skill

Vision Skill

DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.

vision-media★ 2↓ 0
Updated 9/25/2026
Iv0.1.1
@cabeta/dsh-image-theme

Image Theme

Warp-inspired image-to-theme plugin for the DeepSeek Harness web client.

ui-customizationvision-media★ 2↓ 0
Updated 9/7/2026
Xv0.1.1
dsh-xiapan-media

Xiapan Media

DeepSeek Harness native vision, gpt-image-2 image generation, and Seedance video generation via Xiapan Cloud.

vision-mediaintegrations-communication★ 2↓ 0
Updated 9/7/2026
Mv0.6.1
dsh-mmroute

Mmroute

多模态路由 for DeepSeek Harness：纯文本模型的每一步请求里的每张图片（用户上传 / 工具返回 / MCP 渲染）都先经多模态理解模型转述为文字再作答，图片类报错自动转述重试，两类模型全程交叉协作。Multimodal router for DSH: every image in every step of a text-only model's stream is transcribed to text by a multimodal understander first; image-related failures auto-recover with a transcr

vision-mediamodels-usage★ 2↓ 0
Updated 9/7/2026
Pv0.6.1
dsh-pseudo-vision

Pseudo Visionalt · DDDFXYqiming

Adds opt-in image-capable sibling routes for text-only providers and converts image blocks into budgeted, locally enhanced OCR, color-statistics, pixel-scan, and metadata evidence before delegation.

vision-mediamodels-usage★ 2↓ 0
Updated 9/4/2026
v0.2.0
dsh-photo-skins

Photo Skins

Photo skins for the dsh web GUI: import your own photos as UI skins (backdrop layer + auto accent extraction)

ui-customizationvision-media★ 2↓ 0
Updated 8/31/2026
Iv0.1.0
dsh-image-inline

Image Inline

Let the model render an image into the DSH web chat flow (QQ/WeChat style) via a show_image tool: the message content keeps only the path text, the image never enters model context, and the browser shows the picture inline, scrollable with history.

ui-customizationvision-media★ 2↓ 0
Updated 8/30/2026
Sv0.1.0
dsh-show-media

Show Media

Show a local image or short video inside the current DeepSeek Harness conversation card, with click-to-preview. Does not replace the official read_image model path.

vision-mediaui-customization★ 2↓ 0
Updated 8/25/2026
Pv0.8.0
dsh-plugin-grok2api-media-tool

Plugin Grok2api Media Tool

dsh bundle plugin: grok2api image & video generation tools plus image recognition (generate_image / generate_video / recognize_image) for the DeepSeek Harness

vision-media★ 2↓ 0
Updated 8/24/2026
v0.1.1
dsh-voice-plugin

Voice Plugin

Voice input plugin for DeepSeek Harness

vision-media★ 2↓ 0
Updated 8/24/2026
Ev1.0.0
@kobenfang/dsh-eyes

Eyes

Agent Skill for DeepSeek Harness (dsh): eyes.

vision-media★ 2↓ 0
Updated 8/22/2026
Bv0.2.0
dsh-browser-vision

Browser Vision

Browser tool for DeepSeek Harness that can see the page: drives a real Chrome over CDP with browser-use and reads it with deepseek-v4-flash-vision-exp, so canvas text, text inside images and rendered charts are readable. Schema-driven JSON extraction, Markdown output, and per-run token/cost accounti

search-researchvision-media★ 2↓ 0
Updated 8/22/2026
← Previous1…678910…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in