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 7

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categories

All pluginsAgents & Orchestration710Memory & Context854Coding & Developer Tools1.9kUI & Customization2.5kIntegrations & Communication1.3kVision & Media463Search & Research614Security & Access860Models & Usage1.1kProductivity & Workflow1.5k

All plugins

465 plugins
Ov0.1.0
dsh-omni-workstation

Omni Workstation

Omni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task). Backed by an ordered multi-card list (OpenAI/Anthropic/Gemini protocols; Custom/Ollama plus 28 built-in

↓ 0★ 3
Updated 9/11/2026
Xv0.1.1
dsh-xiapan-media

Xiapan Media

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

↓ 0★ 3
Updated 9/7/2026
Iv2.9.2
@xiaoyuink/dsh-image-vision

Image Vision

Image recognition plugin: Automatically detects whether the current model has vision capabilities. If so, it uses the current model with the plugin’s preset prompts for analysis; otherwise, it calls the vision model configured in the plugin. Text models can paste, upload, or drag images directly int

↓ 0★ 3
Updated 9/4/2026
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.

↓ 0★ 3
Updated 8/30/2026
Vv1.2.0
dsh-visibridge

Visibridge

Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.

↓ 0★ 3
Updated 8/23/2026
Vv0.1.0
dsh-vision

Vision

Local vision bridge for DeepSeek Harness

↓ 0★ 3
Updated 8/22/2026
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.

↓ 0★ 3
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)

↓ 0★ 3
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。

↓ 0★ 3
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

↓ 0★ 3
Updated 8/21/2026
Cv1.6.2
@loyalchiiina/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），会话内一键把图收成可调列数的缩略图网格或整块隐藏，还能跳到下一张/上一张图片位置；本地图支持 TIFF/HEIC 自动转码。| Chat images get a proper look: full-screen lightbox (zoom / drag pan / download / prev-next), plus one-click conversation-wide thumbnail grid (configurable columns) or hide, jump-to-image navigatio

↓ 0★ 2
Updated 9/18/2026
v0.3.3
dsh-labnana

Labnana

Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.

↓ 0★ 2
Updated 9/13/2026
v0.1.4
@mokuyoaxis/dsh-iris

Iris

Multi-provider image, video, and speech generation, transcription, visual understanding, and prompt optimization with an integrated Iris workbench for DeepSeek Harness.

↓ 0★ 2
Updated 9/10/2026
Iv0.1.1
@cabeta/dsh-image-theme

Image Theme

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

↓ 0★ 2
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

↓ 0★ 2
Updated 9/7/2026
v0.3.0
@max-null/dsh-capture

Capture

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

↓ 0★ 2
Updated 9/5/2026
Pv0.6.1
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.

↓ 0★ 2
Updated 9/4/2026
Iv1.5.0
@xiaoyuink/dsh-image-create

Image Create

AI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint, with multi-provider support, model discovery, and agent tool registration. 与 @xiaoyuink/dsh-image-vision 同系列的图像插件。

↓ 0★ 2
Updated 9/4/2026
Av0.1.3
dsh-auto-image

Auto Image

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

↓ 0★ 2
Updated 8/31/2026
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)

↓ 0★ 2
Updated 8/31/2026
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.

↓ 0★ 2
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

↓ 0★ 2
Updated 8/24/2026
Tv0.2.0
taxue-dsh-artisan

Taxue Dsh Artisan

taxue 画师: an integrated DSH toolkit for reverse-engineering image/video prompts, deterministic color palette extraction, audit optimization, and multi-provider image generation (with optional image-to-image control).

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

Voice Plugin

Voice input plugin for DeepSeek Harness

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

Eyes

Agent Skill for DeepSeek Harness (dsh): eyes.

↓ 0★ 2
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

↓ 0★ 2
Updated 8/22/2026
Rv0.4.0
@chenjie1129/dsh-remotion-video-plugin

Remotion Video Plugin

Remotion video creation and verified rendering plugin for DeepSeek Harness

↓ 0★ 2
Updated 8/22/2026
Tv0.1.0-rc.6
@deepseek-ai/dsh-tool-vision-read

Tool Vision Read

DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images

↓ 0★ 2
Updated 8/21/2026
Av0.1.1
dsh-antv-infographic

Antv Infographic

AntV Infographic renderer for DeepSeek Harness: render AI-generated infographic fences inline with streaming, editing, and SVG/PNG export.

↓ 0★ 2
Updated 8/21/2026
Vv0.4.4
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.

↓ 0★ 2
Updated 8/21/2026
← Previous1…56789…16Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in