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 a text prompt. We introduce an iterative procedure that, at each stage, identifies a coherent set of images sharing a similar identity and extracts a more consistent identity from this set. Our quantitative analysis demonstrates that our method strikes a better balance between prompt alignment and identity consistency compared to the baseline methods, and these findings are reinforced by a user study. To conclude, we showcase several practical applications of our approach. Project page is available at https://omriavrahami.com/the-chosen-one

翻译：近期文本到图像生成模型的进展为视觉创意释放了巨大潜力。然而，这些模型在生成一致角色方面仍存在困难，而这是诸多现实应用（如故事可视化、游戏开发资产设计、广告等）的关键要素。当前方法通常依赖目标角色的多张现有图像，或涉及劳动密集型的人工流程。在这项工作中，我们提出了一种全自动的一致角色生成方案，唯一的输入仅为文本提示。我们引入了一个迭代流程，在每个阶段，识别出一组共享相似身份的一致图像，并从该集合中提取出更一致的身份。我们的定量分析表明，与基线方法相比，我们的方法在提示对齐与身份一致性之间实现了更优的平衡，用户研究也进一步强化了这些发现。最后，我们展示了该方法在若干实际应用中的效果。项目页面请访问 https://omriavrahami.com/the-chosen-one。