The Chosen One: Consistent Characters in Text-to-Image Diffusion Models

arXiv:2311.10093v3 Announce Type: replace-cross
Abstract: Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, these models struggle with generation of consistent characters, a crucial aspect for numerous real-world applications such as story visualization, game development asset design, advertising, and more. Current methods typically rely on multiple pre-existing images of the target character or involve labor-intensive manual processes. In this work, we propose a fully automated solution for consistent character generation, with the sole input being …

arxiv characters consistent cs.cv cs.gr cs.lg diffusion diffusion models image image diffusion text text-to-image type