IntentTuner: An Interactive Framework for Integrating Human Intentions in Fine-tuning Text-to-Image Generative Models

要旨

Fine-tuning facilitates the adaptation of text-to-image generative models to novel concepts (e.g., styles and portraits), empowering users to forge creatively customized content. Recent efforts on fine-tuning focus on reducing training data and lightening computation overload but neglect alignment with user intentions, particularly in manual curation of multi-modal training data and intent-oriented evaluation. Informed by a formative study with fine-tuning practitioners for comprehending user intentions, we propose IntentTuner, an interactive framework that intelligently incorporates human intentions throughout each phase of the fine-tuning workflow. IntentTuner enables users to articulate training intentions with imagery exemplars and textual descriptions, automatically converting them into effective data augmentation strategies. Furthermore, IntentTuner introduces novel metrics to measure user intent alignment, allowing intent-aware monitoring and evaluation of model training. Application exemplars and user studies demonstrate that IntentTuner streamlines fine-tuning, reducing cognitive effort and yielding superior models compared to the common baseline tool.

著者
Xingchen Zeng
Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
Ziyao Gao
Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China/Guangdong, China
Yilin Ye
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
Wei Zeng
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China
論文URL

https://doi.org/10.1145/3613904.3642165

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Creativity: Visualizations and AI

318B
5 件の発表
2024-05-13 23:00:00
2024-05-14 00:20:00