uni-medical/UniMedVL

Official implementation of "UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis" - A unified medical vision-language model that integrates multimodal understanding and generation capabilities.

44
/ 100
Emerging

UniMedVL helps medical professionals analyze and generate medical information across various imaging types. It takes medical images (like X-rays, CT scans, MRIs, or histopathology slides) or text descriptions, and can generate diagnostic reports, answer questions about images, or even create new medical images from text. This tool is for clinicians, researchers, and AI developers in the medical field who need to process multimodal medical data.

Use this if you need a single system to both interpret medical images and generate clinical text or new images, supporting tasks like report writing, visual question answering, or data augmentation across nine different imaging modalities.

Not ideal if you primarily need to analyze a single, specific medical image modality with highly specialized, pre-existing tools rather than a broad, unified approach.

medical imaging diagnostic reporting clinical AI multimodal healthcare medical research
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

66

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Jan 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/uni-medical/UniMedVL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.