Understanding and Mitigating Copying in Diffusion Models
About this talk
A Google TechTalk, presented by Gowthami Somepalli , 2023-08-09 Abstract: Cutting-edge diffusion models produce high-quality and customizable images, enabling their use for commercial art and graphic design purposes. First, I will discuss our study of various frameworks to detect replication. Then, I will show how we used these frameworks to identify memorization in Stable Diffusion 1.4 model. In the second part, I will discuss various factors contributing to memorization in diffusion models. While it is widely believed that duplicated images in the training set are responsible for content replication at inference time, I will show results on how the text conditioning of the model also plays an important role. Lastly, I will discuss several techniques we proposed based on these findings for reducing data replication in both training and inference times.
Topics covered
Stay Updated
Get notified about new features and conference additions.