Overview
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 / EN
Package documentation
Registry summary
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 verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.
Read the full README on GitHub