AI RESEARCH
ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors
arXiv CS.CV
•
ArXi:2603.24270v1 Announce Type: new While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often triggers catastrophic structural failures, such as object repetition and spatial fragmentation. This limitation fundamentally stems from a lack of robust spatial priors, as static text-to-image models are primarily trained on image distributions with conventional dimensions.