teohyc/Covid-XRay-Diffusion-Model

1---2tags:3- Lung4- Pneumonia5- Covid-196- PyTorch7license: mit8language:9- en10pipeline_tag: unconditional-image-generation11library_name: diffusers12---13---14# Diffusion Model for COVID-19 X-ray Generation15This is a diffusion model designed for generating synthetic COVID-19 X-ray images. The model takes random noise as input and iteratively denoises it to produce realistic X-ray images.16Used to generate synthetic xray image for scarce COVID-19 positive cases, which can be used for data augmentation in training diagnostic models.17 18Training data from https://data.mendeley.com/datasets/9xkhgts2s6/419Full project file at https://github.com/teohyc/covid_xray_diffusion20 21##Usage22```python23from diffusers import DDPMPipeline24import matplotlib.pyplot as plt25 26# Load the pipeline27pipeline = DDPMPipeline.from_pretrained("teohyc/Covid-XRay-Diffusion-Model")28 29# Generate a synthetic X-ray30image = pipeline(num_inference_steps=500).images[0] #default is 1000 steps, but you can reduce it for faster generation (at the cost of quality)31 32# Display33plt.imshow(image, cmap='gray')34plt.axis('off')35plt.show()36```