SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18
Image Understanding & Analysis
让模型理解已有图片内容并输出语义结果：图像描述、视觉问答、截图或界面分析、物体与场景识别、图像比较及视觉模型桥接。不含以文字提取为核心的 OCR、确定性图像处理、屏幕采集与图像生成。
Leaf membership
51 plugins
adatile-mcpMutton-hub/adatile-mcpCatalog AnalyzedAdaTile-MCP: high-resolution image adaptive tiling MCP server for DeepSeek vision model (deepseek-v4-flash-vision-exp). L1-L6 pipeline (fastpath, saliency, adaptive tiling, Files API assembly, streaming VLM, rule-based merge) + eval harness. Setup: clone, run setup.bat, add your agent MCP config -> see README.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdeepseek-mcp-pluginYNM10086/deepseek-mcp-pluginCatalog AnalyzedDSH 宿主级图片理解Plugin：vision_describe 工具，MiniMax → 智谱 → Ollama 三层后端自动降级，随 DSH 启动自动挂载CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsDeepSeek-VisionPlusqq247505/DeepSeek-VisionPlusCatalog AnalyzedDeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-analyze-image-toolCaseyTso/dsh-analyze-image-toolCatalog Analyzed给纯文本 DeepSeek Harness 模型加上识图能力：analyze_image 把图片转发到任意 OpenAI 兼容视觉端点 | Vision bridge for text-only DSH modelsCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-eyewenliang9527/dsh-eyeCatalog AnalyzedDSH plugin from wenliang9527/dsh-eyeCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-highres-visionazwosile/dsh-highres-visionCatalog AnalyzedFor the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals8 starsdsh-image-bridgeSeryta/dsh-image-bridgeCatalog AnalyzedDSH plugin from Seryta/dsh-image-bridgeCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-image-visionVeryInt/dsh-image-visionCatalog AnalyzedDSH plugin from VeryInt/dsh-image-visionCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-image-visionxiaoyuink/dsh-image-visionCatalog AnalyzedImage understanding for any DSH model: vision, OCR, grounding, and crop tools with domain presets for histopathology, cell biology, anatomy, clinical images and scientific figures.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-image-visionniushuanan/dsh-image-visionCatalog AnalyzedLet vision-capable models read native attachments while giving text-only models an image tool that supports follow-up questions.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-llm-vision-bridgedsh-llm-vision-bridgeCatalog AnalyzedNative LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.2Evidence updated2026-09-07Public signals4 stars · 234 downloadsdsh-medomnibowang-lab/dsh-medomniCatalog Analyzeddeepseek harness plugin for medical image analysisCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-mindseyedsh-mindseyeCatalog AnalyzedPlug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.2.8Evidence updated2026-09-07Public signals2 stars · 2313 downloadsdsh-multimodalMC5lan/dsh-multimodalCatalog Analyzed给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-multimodal-bridgedsh-multimodal-bridgeCatalog AnalyzedDeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image and image editing) tools for text-only modelsCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.2Evidence updated2026-09-08Public signals563 downloadsdsh-open-eyeshyper-dsh-plugins/dsh-open-eyesCatalog AnalyzedA lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-plugin-glm-visionbaldovinmarques391-design/dsh-plugin-glm-visionCatalog AnalyzedGLM Vision plugin for DSH: image translation for non-multimodal models via GLM-4V-FlashCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-pluginsBernardxu123/dsh-pluginsCatalog AnalyzedDeepSeek Harness (dsh) 官方 bundle 规范Plugin集合: dsh-vision 看图 + dsh-sensenova-image 生图 + dsh-client-stats-decimal 统计两位小数CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.