StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation

TL;DR

StoryMaker is a novel method that ensures holistic consistency of multiple characters in text-to-image generation, maintaining facial features, clothing, hairstyles, and body details to create cohesive narrative images.

Contribution

It introduces a comprehensive personalization approach combining face identities, character features, and pose conditioning, with techniques to prevent inter-character interference and improve image fidelity.

Findings

Effective in maintaining multi-character scene consistency

Supports diverse applications and societal plug-ins

Improves image fidelity with LoRA enhancement

Abstract

Tuning-free personalized image generation methods have achieved significant success in maintaining facial consistency, i.e., identities, even with multiple characters. However, the lack of holistic consistency in scenes with multiple characters hampers these methods' ability to create a cohesive narrative. In this paper, we introduce StoryMaker, a personalization solution that preserves not only facial consistency but also clothing, hairstyles, and body consistency, thus facilitating the creation of a story through a series of images. StoryMaker incorporates conditions based on face identities and cropped character images, which include clothing, hairstyles, and bodies. Specifically, we integrate the facial identity information with the cropped character images using the Positional-aware Perceiver Resampler (PPR) to obtain distinct character features. To prevent intermingling of multiple characters and the background, we separately constrain the cross-attention impact regions of different characters and the background using MSE loss with segmentation masks. Additionally, we train the generation network conditioned on poses to promote decoupling from poses. A LoRA is also employed to enhance fidelity and quality. Experiments underscore the effectiveness of our approach. StoryMaker supports numerous applications and is compatible with other societal plug-ins. Our source codes and model weights are available at https://github.com/RedAIGC/StoryMaker.