EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generation
Paper • 2503.22357 • Published • 1
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("HReynaud/EchoFlow", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]EchoFlow
This repository contains the models described in EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generation.
Try out the model at https://huggingface.co/spaces/HReynaud/EchoFlow.
- Downloads last month
- -