Latent Diffusion Models have recently emerged as the state-of-the-art approach for synthetic image generation. In the Web context, their adoption may significantly impact the way it is currently approached, from both sides of content generation and exploration. For example, future Web platforms may create alternative and personalised images for individual users rather than improve the accessibility for users with disabilities. However, due to the nascent stage of this research area, there remains a knowledge gap in effectively utilising these models, which can clutter the digital space with poor-quality AI-generated, thus diminishing the overall perceived impact and the user experience. To address this issue, we propose a novel methodology aimed at generating high-quality prompts with minimal user effort. In particular, we present BLACK (Background, Lighting, Amenities, Context, and Kinesis), a simple prompt generation model directly designed for achieving high-quality images satisfying a proposed set of five desiderata. Through concrete examples, we demonstrate the impact of the prompting model in improving the generation quality. As a second contribution, we publicly release a structured resource of prompts along with expected results.
The data provided is organized in multiple formats to cater to different preferences and use cases. The first format is a CSV file, which is a popular choice for data storage and can be easily imported into various data analysis tools. This can be downloaded from the CSV link. Secondly, the data is also available in an HTML format, which can be viewed through web browsers or parsed by web scraping tools. This can be obtained by downloading the HTML zip file.