FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models

TL;DR

This paper introduces FiVA, a comprehensive dataset and framework for decomposing and transferring specific visual attributes like lighting and texture in text-to-image models, enabling more precise and customizable image generation.

Contribution

The work presents the first fine-grained visual attribute dataset (FiVA) and a novel adaptation framework (FiVA-Adapter) for improved attribute manipulation in image synthesis.

Findings

FiVA dataset contains around 1 million images with detailed attribute annotations.

FiVA-Adapter enables selective transfer of visual attributes from multiple sources.

Enhanced customization in image generation with better attribute control.

Abstract

Recent advances in text-to-image generation have enabled the creation of high-quality images with diverse applications. However, accurately describing desired visual attributes can be challenging, especially for non-experts in art and photography. An intuitive solution involves adopting favorable attributes from the source images. Current methods attempt to distill identity and style from source images. However, "style" is a broad concept that includes texture, color, and artistic elements, but does not cover other important attributes such as lighting and dynamics. Additionally, a simplified "style" adaptation prevents combining multiple attributes from different sources into one generated image. In this work, we formulate a more effective approach to decompose the aesthetics of a picture into specific visual attributes, allowing users to apply characteristics such as lighting, texture, and dynamics from different images. To achieve this goal, we constructed the first fine-grained visual attributes dataset (FiVA) to the best of our knowledge. This FiVA dataset features a well-organized taxonomy for visual attributes and includes around 1 M high-quality generated images with visual attribute annotations. Leveraging this dataset, we propose a fine-grained visual attribute adaptation framework (FiVA-Adapter), which decouples and adapts visual attributes from one or more source images into a generated one. This approach enhances user-friendly customization, allowing users to selectively apply desired attributes to create images that meet their unique preferences and specific content requirements.