arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.03286cs.CVcs.AIcs.GRcs.LG
收藏

无需训练的一致性文本到图像生成

Training-Free Consistent Text-to-Image Generation

NVIDIA(英伟达);Tel Aviv University(特拉维夫大学)

Yoad Tewel, Omri Kaduri, Rinon Gal, Yoni Kasten, Lior Wolf, Gal Chechik, Yuval Atzmon

AI总结:

提出无需训练的ConsiStory方法,通过共享预训练模型内部激活及引入主体驱动共享注意力块和特征注入,在多提示词下实现最先进的主体一致性与文本对齐,并支持多主体场景。

摘要:

文本到图像模型通过允许用户使用自然语言引导图像生成过程,提供了一种新层次的创作灵活性。然而,使用这些模型在不同提示词下持续描绘同一主体仍然具有挑战性。现有方法通过对模型进行微调来教授其描述特定用户提供主体的新词,或者向模型添加图像条件。这些方法需要针对每个主体进行漫长的优化或大规模预训练。此外,它们难以将生成的图像与文本提示词对齐,并且在描绘多个主体时面临困难。在此,我们提出了ConsiStory,这是一种无需训练的方法,通过共享预训练模型的内部激活来实现一致性主体生成。我们引入了一个主体驱动的共享注意力块和基于对应关系的特征注入,以促进图像间的主体一致性。此外,我们开发了在保持主体一致性的同时鼓励布局多样性的策略。我们将ConsiStory与一系列基线方法进行比较,并在主体一致性和文本对齐方面展示了最先进的性能,且无需任何优化步骤。最后,ConsiStory可以自然地扩展到多主体场景,甚至实现对常见物体的无需训练的个性化。

英文摘要:

Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to consistently portray the same subject across diverse prompts remains challenging. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects or add image conditioning to the model. These methods require lengthy per-subject optimization or large-scale pre-training. Moreover, they struggle to align generated images with text prompts and face difficulties in portraying multiple subjects. Here, we present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model. We introduce a subject-driven shared attention block and correspondence-based feature injection to promote subject consistency between images. Additionally, we develop strategies to encourage layout diversity while maintaining subject consistency. We compare ConsiStory to a range of baselines, and demonstrate state-of-the-art performance on subject consistency and text alignment, without requiring a single optimization step. Finally, ConsiStory can naturally extend to multi-subject scenarios, and even enable training-free personalization for common objects.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑