The World Health Organization (WHO) is issuing new guidance on the ethical and governance aspects of Large Multi-Modal Models (LMMs), a rapidly growing form of generative artificial intelligence (AI) with applications in healthcare. The guidance comprises over 40 recommendations for governments, technology firms, and healthcare providers, focusing on responsible LMM use to safeguard public health. LMMs can accept diverse data inputs and mimic human communication, prompting their rapid adoption. The guidance emphasizes the potential benefits and risks of LMMs in areas like diagnosis, patient-guided use, clerical tasks, medical education, and scientific research. It addresses challenges such as biases, inaccuracies, and cybersecurity risks, urging stakeholder engagement and ethical considerations in LMM development and deployment.