Diffusion models are generating ever more realistic images. Yet, when gener-
ating images repeatedly with the same prompt, practitioners often obtain slight
variations of the same, highly-likely mode. As a result, most models fail to re-
flect the inherent diversity seen in data, which hinders their relevance to creative
tasks or ability to power world models. This work proposes a highly effective and
general method to repel generated images away from a reference set of images.
This is achieved by introducing data-driven repellence terms within diffusions dy-
namically, throughout their…
Source link
