This model is a latent diffusion model for unconditional image generation of mammograms of size 512vs512. The model was trained with 1000 images using the DDPM architecture. The model was trained for 50 epochs with a batch size of 8 and gradient accumulation of 4, using around 9 GB of GPU memory.

Usage

from diffusers import DDPMPipeline

pipeline = DDPMPipeline.from_pretrained({hub_model_id})
image = pipeline().images[0]
image