ximengxiaolan/dsh-vision-bridge

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Vision & Multimodal ★ 0 updated 2026-08-14
View on GitHub ↗

Install

dsh plugin --profile web add github:ximengxiaolan/dsh-vision-bridge

Details

More plugins in Vision & Multimodal