StyleFactory: Towards Better Style Alignment in Image Creation through Style-Strength-Based Control and Evaluation

要旨

Generative AI models have been widely used for image creation. However, generating images that are well-aligned with users' personal styles on aesthetic features (e.g., color and texture) can be challenging due to the poor style expression and interpretation between humans and models. Through a formative study, we observed that participants showed a clear subjective perception of the desired style and variations in its strength, which directly inspired us to develop style-strength-based control and evaluation. Building on this, we present StyleFactory, an interactive system that helps users achieve style alignment. Our interface enables users to rank images based on their strengths in the desired style and visualizes the strength distribution of other images in that style from the model's perspective. In this way, users can evaluate the understanding gap between themselves and the model, and define well-aligned personal styles for image creation through targeted iterations. Our technical evaluation and user study demonstrate that StyleFactory accurately generates images in specific styles, effectively facilitates style alignment in image creation workflow, stimulates creativity, and enhances the user experience in human-AI interactions.

著者
Mingxu Zhou
Zhejiang University, Hangzhou, Zhejiang, China
Dengming Zhang
Zhejiang University, Hangzhou, Zhejiang, China
Weitao You
Zhejiang University, Hangzhou, Zhejiang, China
Ziqi Yu
Zhejiang University, Hangzhou, Zhejiang, China
Yifei Wu
Zhejiang University, Hangzhou, Zhejiang, China
Chenghao Pan
Zhejiang University, Hangzhou, Zhejiang, China
Huiting Liu
Zhejiang University, Hangzhou, Zhejiang, China
Tianyu Lao
Zhejiang University, Hangzhou, Zhejiang, China
Pei Chen
Zhejiang University, Hangzhou, Zhejiang, China
論文URL

https://doi.org/10.1145/3654777.3676370

動画

会議: UIST 2024

ACM Symposium on User Interface Software and Technology

セッション: 3. Generating Visuals

Westin: Allegheny 3
4 件の発表
2024-10-16 18:00:00
2024-10-16 19:00:00