CATEGORY
Vision & Media DSH plugins
Verified manifests and exact versions in this category.
All plugins
377 pluginsdsh-plugin-grok2api-media-toolPlugin Grok2api Media Tool
dsh bundle plugin: grok2api image & video generation tools plus image recognition (generate_image / generate_video / recognize_image) for the DeepSeek Harness
dsh-vision-tilerVision Tiler
Loss-aware, full-coverage image tiling for DeepSeek Harness vision models
dsh-visionVision
Local vision bridge for DeepSeek Harness
dsh-antv-infographicAntv Infographic
AntV Infographic renderer for DeepSeek Harness: render AI-generated infographic fences inline with streaming, editing, and SVG/PNG export.
@dsh-external/dsh-ocr1-memoryOcr1 Memory
Based on the DeepSeek-OCR1 optical compressed memory system: renders memories as images for storage, with support for SoM segmentation, age-based decay/blur, activation-based recall, and DSH Agent retrieval
meow-visionMeow 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
@xiaoyuink/dsh-image-createImage 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。
@allmodels/dsh-speechSpeech
Speech-to-text and spoken answer summaries for DeepSeek Harness using AllModels.io.
dsh-mmrouteMmroute
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
dsh-file-convertFile Convert
Local-first file conversion for DeepSeek Harness - images, PDF, data, audio/video and office documents. No API keys, no uploads, no token cost.
dsh-vision-analysisVision Analysis
Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.
dsh-auto-imageAuto 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.
dsh-photo-skinsPhoto Skins
Photo skins for the dsh web GUI: import your own photos as UI skins (backdrop layer + auto accent extraction)
@crosery/dsh-viewerViewer
Renders images, video, audio, PDF and Office documents inline in the dsh web UI through a display_file tool, streaming bytes over a signed HTTP route with range support.
dsh-glm-visionGlm Vision
GLM vision model plugin: registers the glm-vision provider route (glm-4.6v series, with image+text input declaration) and provides the glm_vision tool, allowing text-based primary models such as DeepSeek to directly call Zhipu vision models to analyze images.
@max-null/dsh-captureCapture
SSiD (思灵) quick screenshot capture: tray/hotkey → fullscreen box-select overlay → cropped image into the current conversation composer
dsh-show-mediaShow 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.
taxue-dsh-artisanTaxue 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).
dsh-visibridgeVisibridge
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
dsh-medomniMedomni
Medical imaging specialist tools for deepseek-harness: MAIRA-2 and MedGemma report generation for chest X-ray/CT/MRI/retinal (fundus) images, TotalSegmentator organ segmentation, BiomedCLIP zero-shot ultrasound classification, and BiomedParse text-prompted segmentation across X-ray, CT, MRI, ultraso
@kobenfang/dsh-eyesEyes
Agent Skill for DeepSeek Harness (dsh): eyes.
dsh-browser-visionBrowser 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
dsh-image-vision-bridgeImage Vision Bridge
DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.
@chenjie1129/dsh-remotion-video-pluginRemotion Video Plugin
Remotion video creation and verified rendering plugin for DeepSeek Harness
@deepseek-ai/dsh-tool-vision-readTool 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
wavespeed-dsh-skillWavespeed Dsh Skill
WaveSpeed skill for DeepSeek Harness (dsh): generate and edit AI media (image, video, audio, 3D) via the open-source wavespeed CLI.
dsh-vision-skillVision 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.
dsh-vision-imagenVision 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。
@lp181818/dsh-vision-pluginVision Plugin
DSH vision/image-recognition plugin: enables AI to understand images with a configurable vision model
@wisdoverse/dsh-inline-media-viewerInline Media Viewer
Persistent inline image, video, and audio previews for DeepSeek Harness Web conversations, with workspace-confined local reads and an optional ComfyUI proxy.