Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object generation. In this work, we first show the fundamental reasons for such misalignment by identifying issues related to low attention activation and mask overlaps. Then we propose a compositional finetuning framework with two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores, respectively. Unlike conventional test-time adaptation methods, our model, once finetuned on critical parameters, is able to directly perform inference given an arbitrary multi-object prompt, which enhances the scalability and generalizability. Through comprehensive evaluations, our model demonstrates superior performance in image realism, text-image alignment, and adaptability, significantly surpassing established baselines. Furthermore, we show that training our model with a diverse range of concepts enables it to generalize effectively to novel concepts, exhibiting enhanced performance compared to models trained on individual concept pairs.
Bao et al. (2024) studied this question.