Bundle
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.
MC5lan4
Browse
1 results
1 results
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.