We introduce a new approach, Generative mOdel finetun-ing with Reward-driven Sample selection (GORS), to boost the compositional text-to-image generation abilities of pretrained text-to-image models.

To address these problems, in this paper we explore a simple yet effective decompositional approach towards both evaluation and improvement of text-to-image alignment.

We curate 62 scenarios encompassing these aspects and evaluate 26 state-of-the-art text-to-image models on this benchmark.

We curate 62 scenarios encompassing these aspects and evaluate 26 state-of-the-art text-to-image models on this benchmark.

We then propose to employ layout, a very abstract and easy-to-obtain prior, as the spatial guidance for subject arrangement.

Each block uses edge-supervised cross-attention learning to further improve image quality.

Text-to-image generation has recently witnessed remarkable achievements.