Lazy Diffusion Transformer for Interactive Image Editing

arXiv:2404.12382v1 Announce Type: new
Abstract: We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image updates efficiently. Our approach targets interactive image editing applications in which, starting from a blank canvas or an image, a user specifies a sequence of localized image modifications using binary masks and text prompts. Our generator operates in two phases. First, a context encoder processes the current canvas and user mask to produce a compact global context tailored to the region to generate. Second, …

abstract applications arxiv binary canvas cs.ai cs.cv cs.gr diffusion diffusion transformer editing generator image interactive lazy masks novel prompts targets text transformer type updates