MediSyn: A Generalist Text-Guided Latent Diffusion Model For Diverse Medical Image Synthesis

Joseph Cho, Mrudang Mathur, Cyril Zakka, Dhamanpreet Kaur, Matthew Leipzig, Alex Dalal, Aravind Krishnan, Eubee Koo, Karen Wai, Cindy S. Zhao, Akshay Chaudhari, Matthew Duda, Ashley Choi, Ehsan Rahimy, Lyna Azzouz, Robyn Fong, Rohan Shad, William Hiesinger

Here, we introduce MediSyn: a text-guided, latent diffusion model capable of generating synthetic images from 6 medical specialties and 10 image types. We developed our model on a diverse corpus of over 1 million medical image-text pairs sourced entirely from the public domain.

Please follow this Colab tutorial to generate a synthetic medical image from MediSyn:

Downloads last month: 34

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support