Skip to yearly menu bar Skip to main content

Workshop: NeurIPS 2023 Workshop on Machine Learning for Creativity and Design

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

Yuseung Lee · Kunho Kim · Hyunjin Kim · Minhyuk Sung


While ControlNet has enabled pretrained image diffusion models (i.e. Stable Diffusion) to take additional condition inputs, it still has the limitation of only generating images of certain sizes. To this end, we demonstrate an application of SyncDiffusion for conditional image generation, which takes advantage of synchronized joint diffusions to allow conditions of arbitrary size as input and in turn generate globally coherent images.

Chat is not available.