arXiv cs.CV
· Papers
LCG: Long-Context Consistent Image Generation with Sparse Relational Attention
arXiv:2606.26171v1 Announce Type: new Abstract: Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyboards, and visual narratives. We propose Long-Context Generation (LCG), a framework for long