Echopath
Collection
Pathology conditioned echocardiogram video generation. • 3 items • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("marshallhamzah/EchoPath", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]BibTeX:
@misc{muhammad2025echopathpathologyconditionedechovideo, title={Echo-Path: Pathology-Conditioned Echo Video Generation}, author={Kabir Hamzah Muhammad and Marawan Elbatel and Yi Qin and Xiaomeng Li}, year={2025}, eprint={2509.17190}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2509.17190}, }