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
2 results
Bundle
dsh-deepseek-vision
Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models
Argonaut7902