Medical image synthesis is gaining popularity using generative models. Neural models of diffusion have recently shown promise in producing remarkably lifelike representations of objects. However, their ability to provide medical images has yet to be investigated. We investigate neural diffusion models’ capacity for creating synthetic medical images. First, we create images of legs from an input word prompt using a pretrained DALLE3 model. Second, we develop synthetic images and use 300 leg images to train a stable diffusion model. Through a qualitative study, we assess the synthetic image data by having two impartial radiologists classify randomly selected specimens derived from the created data as genuine, fraudulent, or unclear. Results show that features that are otherwise highly distinctive to an image created using the diffusion model can be translated. We have published the synthetic images at https://www.kaggle.com/datasets/suraahmed56/computer-vision-medical-images .