multimodal-bridge
multimodal-bridge 是一个多模态能力桥：把 Qwen 的视觉理解（Qwen-VL）与图像生成（Qwen-Image）带给没有原生多模态能力的纯文本模型（如 DeepSeek）。它有两种形态、同一套后端： MCP Server（qwen_vision / qwen_generate 工具）：任何支持 MCP 的宿主（Claude Code、Kimi Code 等）直接挂载； DSH 插件（npm 包 dsh-multimodal-bridge，DeepSeek Harness bundle）：dsh plugin add 一行安装，含模型自动 fallback、尺寸自适应与图片结果卡片。
This plugin is a GitHub repository with the dsh-plugin topic — the repository README is the authoritative install source. Use the template below, adapting the package name / path from the README:
dsh plugin --profile web add $multimodal-bridgeLocal development? dsh --profile web --patch ./cordis.yml with an absolute plugin path — see Plugin Development.GitHub source? dsh plugin --profile web add github:$Spirit4471/$multimodal-bridge — needs a prepare script in the repo (see packaging).
| Repository | Spirit4471/multimodal-bridge |
| License | MIT |
| Category | Tool |
| Status | Unverified |
| Last commit | 2026-08-13 |
| Indexed | 2026-08-14 |
🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.
View
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).
View
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
ViewQuestions or feedback? Official Discussions is the project’s canonical support channel; Discord has an active community. dsh.so itself improves via plugin submissions and your feedback.