Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.
- GitHub stars
- 2
- License
- MIT
- Added
- 2026-08-16
GitHub info
- GitHub stars
- 2
- License
- MIT
- Primary language
- TypeScript
- Last push
- Aug 16, 2026, 6:56 AM
- Maintainer
- haiziyao
- Added
- 2026-08-16
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
Mix 生成的 LumaBoard 页面
https://raw.githubusercontent.com/haiziyao/dsh-vision-mix/main/docs/benchmark-mix.png
LumaBoard 参考设计稿
https://raw.githubusercontent.com/haiziyao/dsh-vision-mix/main/docs/benchmark-reference.png
Vision Mix 生图设置页面
https://raw.githubusercontent.com/haiziyao/dsh-vision-mix/main/docs/generation-routing.png
Vision Mix 基础路由与模型图片能力设置
https://raw.githubusercontent.com/haiziyao/dsh-vision-mix/main/docs/settings-routing.png
会话级生图记录
https://raw.githubusercontent.com/haiziyao/dsh-vision-mix/main/docs/generation-history.png
会话级识图记录
https://raw.githubusercontent.com/haiziyao/dsh-vision-mix/main/docs/vision-history.png
Install
dsh plugin --profile web add dsh-vision-mixREADME badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/haiziyao/dsh-vision-mix)Related plugins
Vision & Multimodalmodlens
★ 3768Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-router
★ 1030Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
★ 842Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.