SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18
Vision Model Bridging & Integration
纳入为纯文本模型透明接入视觉能力的桥接Plugin，以及视觉模型后端、provider、网关、凭据和通道配置等接入基础设施；包括图片拦截后转写、视觉模型路由、按需视觉工具和视觉回退。不纳入面向具体图片或文档内容的识别、解析、转换与结构化产出，也不纳入图像生成、编辑或模型训练。
Leaf membership
50 plugins
dsh-vision-bridgelium970320/dsh-vision-bridgeCatalog AnalyzedDSH 视觉桥接Plugin：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）CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-vision-bridge@goodandready/dsh-vision-bridgeCatalog AnalyzedRoutes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.5.29Evidence updated2026-09-07Public signals1 stars · 5416 downloadsdsh-vision-bridgeDreamRift/dsh-vision-bridgeCatalog AnalyzedDeepSeek Harness 多模态视觉桥（dsh-vision-bridge）：贴图经 llm/stream 自动转 VL 文字描述（解决 UNSUPPORTED_CONTENT）+ view_image/ocr_image 主动视觉工具 + 原生多模态路由自动跳过（rc.7）；零依赖。Vision bridge for text-only DeepSeek models.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-bridgecyh12345678910/dsh-vision-bridgeCatalog AnalyzedMulti-backend vision plugin for DeepSeek Harness — API (OpenAI Vision) + CDP (Doubao bridge), cross-platform, cached, configurableCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-linkdsh-vision-linkCatalog AnalyzedLightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact1.2.2Evidence updated2026-09-09Public signals482 downloadsdsh-vision-pro-bridgedsh-vision-pro-bridgeCatalog AnalyzedVision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact1.0.0Evidence updated2026-09-09Public signals0 stars · 0 downloadsdsh-vision-providerlibinyam/dsh-vision-providerCatalog AnalyzedConfig-only DeepSeek Harness bundle for OpenAI-compatible vision models.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-vision-proxydsh-vision-proxyCatalog AnalyzedDeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.CompatibilityDSH 0.1.2-rc.1 · webDependency audit1 reported in bounded auditArtifact0.4.1Evidence updated2026-09-06Public signals15 stars · 5016 downloadsdsh-vision-relayjunhongchashui/dsh-vision-relayCatalog Analyzed零修改、零切换的 DeepSeek Harness 视觉能力Plugin：纯文本模型粘贴即读图片，云端 + 本地 Ollama 双后端自动切换，ModLens v2 风格结构化证据输出。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-web-ui#dsh-tool-describe-imageDamonKoy/dsh-web-uiCatalog AnalyzedGives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals11 starsduhai-visionhamliy-feng/duhai-visionCatalog AnalyzedVisual model adapter for Codex and DeepSeek Harness, powered by PaddleOCR-VL and Qwen.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsGrassVisonmoduqishi/GrassVisonCatalog Analyzed给纯文本大模型装上原生视觉：流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsslcatwujian-dsh-vision-pluginyan5236/slcatwujian-dsh-vision-pluginCatalog Analyzed让不支持图片输入的主模型通过已配置的视觉模型理解图片的 DSH Plugin：自动桥接、像素坐标描述、vision_ask 追问工具与设置页CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsSuperMate-Harness-SystemSuperMate-Ai/SuperMate-Harness-SystemCatalog AnalyzedGive DeepSeek Eyes · 给 DeepSeek 装眼睛 — a DeepSeek Harness (DSH) Skill: local vision models or vision APIs let DeepSeek read images and graphic filesCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.