概览
dsh-multimodal
Multimodal eyes and hands for DeepSeek Harness: vision transcription, OCR, and text-to-image via OpenAI-compatible backends, with an in-conversation generated-image card.
README / ZH
插件文档
目录摘要
Multimodal eyes and hands for DeepSeek Harness: vision transcription, OCR, and text-to-image via OpenAI-compatible backends, with an in-conversation generated-image card.
dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。
在 GitHub 阅读完整 README