In many scientific fields it is imperative to analyze data in numerical or image formats. However, there are many challenges that accompany this process. Image data of experimental signals from materials science often contains features which hinder both qualitative and quantitative analysis in the form of anomalies. These anomalies take the form of unexpected data within images such as scratches or striations, or localized intense signals that do not originate from the sample of interest. In AFM(atomic force microscopy) and INS(inelastic neutron scattering), this is especially challenging as the common analysis techniques in these domains are sensitive to artifacts. Generative machine learning models are becoming a common method for creating images or even correcting parts of an image due their accessibility and generalizability. This project will explore the use of a DDPM (denoising diffusion probabilistic model) to correct anomalies within AFM and INS images.