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.

翻译：尽管文本到图像（T2I）扩散模型在生成单个实例的视觉吸引图像方面表现出色，但在准确定位和控制多个实例的特征生成方面仍存在困难。布局到图像（L2I）任务通过引入边界框作为空间控制信号来解决定位挑战，但在生成精确实例特征方面仍有不足。为此，我们提出实例特征生成（IFG）任务，旨在确保生成实例同时具备位置准确性和特征保真度。针对IFG任务，我们提出了实例特征适配器（IFAdapter）。该适配器通过引入额外外观标记并利用实例语义图将实例级特征与空间位置对齐，从而增强特征描绘能力。IFAdapter作为即插即用模块引导扩散过程，使其能够适配多种社区模型。为进行评估，我们构建了IFG基准数据集并开发了验证流程，以客观比较模型在生成具有准确定位和特征的实例方面的能力。实验结果表明，IFAdapter在定量和定性评估中均优于其他模型。