Text-to-image (T2I) generative models have attracted significant attention
and found extensive applications within and beyond academic research. For
example, the Civitai community, a platform for T2I innovation, currently hosts
an impressive array of 74,492 distinct models. However, this diversity presents
a formidable challenge in selecting the most appropriate model and parameters,
a process that typically requires numerous trials. Drawing inspiration from the
tool usage research of large language models (LLMs), we introduce DiffAgent, an
LLM agent designed to screen the accurate selection in seconds via API calls.
DiffAgent leverages a novel two-stage training framework, SFTA, enabling it to
accurately align T2I API responses with user input in accordance with human
preferences. To train and evaluate DiffAgent's capabilities, we present
DABench, a comprehensive dataset encompassing an extensive range of T2I APIs
from the community. Our evaluations reveal that DiffAgent not only excels in
identifying the appropriate T2I API but also underscores the effectiveness of
the SFTA training framework. Codes are available at
this https URL

通过使用 DiffAgent 和 SFTA 训练框架，该研究针对 T2I API 提供了准确和有效的模型选择，并使用 DABench 数据集进行了评估。