IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation

TL;DR

This paper introduces IFAdapter, a plug-and-play module that improves the accuracy of instance features and positioning in grounded text-to-image generation, addressing limitations of previous spatial control methods.

Contribution

The paper proposes the Instance Feature Adapter (IFAdapter) and an IFG benchmark to enhance feature fidelity and positional accuracy in instance generation tasks.

Findings

IFAdapter outperforms existing models in quantitative evaluations.

The IFG benchmark provides a new standard for assessing instance feature control.

Experimental results show improved feature fidelity and spatial accuracy.

Abstract

While Text-to-Image (T2I) diffusion models excel at generating visually appealing images of individual instances, they struggle to accurately position and control the features generation of multiple instances. The Layout-to-Image (L2I) task was introduced to address the positioning challenges by incorporating bounding boxes as spatial control signals, but it still falls short in generating precise instance features. In response, we propose the Instance Feature Generation (IFG) task, which aims to ensure both positional accuracy and feature fidelity in generated instances. To address the IFG task, we introduce the Instance Feature Adapter (IFAdapter). The IFAdapter enhances feature depiction by incorporating additional appearance tokens and utilizing an Instance Semantic Map to align instance-level features with spatial locations. The IFAdapter guides the diffusion process as a plug-and-play module, making it adaptable to various community models. For evaluation, we contribute an IFG benchmark and develop a verification pipeline to objectively compare models' abilities to generate instances with accurate positioning and features. Experimental results demonstrate that IFAdapter outperforms other models in both quantitative and qualitative evaluations.