MediSyn: A Generalist Text-Guided Latent Diffusion Model For Diverse Medical Image Synthesis
Paper • 2405.09806 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("hiesingerlab/MediSyn", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]A Generalist Model For Diverse Text-Guided 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
- 16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support