LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model

arXiv:2305.11577v3 Announce Type: replace
Abstract: This paper introduces LeftRefill, an innovative approach to efficiently harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis. As the name implies, LeftRefill horizontally stitches reference and target views together as a whole input. The reference image occupies the left side, while the target canvas is positioned on the right. Then, LeftRefill paints the right-side target canvas based on the left-side reference and specific task instructions. Such a task formulation shares some similarities with …

arxiv canvas cs.cv diffusion diffusion model generalized image image diffusion reference text text-to-image through type