A team of computer scientists from Google, DeepMind, ETHZ, Princeton University and the University of California, Berkeley, has found that AI-based image generation systems can sometimes generate copies of images used to train them. The group has published a paper describing testing of several image generation software systems on the arXiv preprint server.
Image generation systems such as Stable Diffusion, Imagen and Dall-E 2 have been in the news lately due to their ability to generate high-resolution images based on nothing but natural language prompts. Such systems have been trained on thousands of images as templates.
