Text-to-image models, which aim to convert text input into images, have gained popularity partly due to their flex-ibility and user-friendliness. However, there are still weaknesses in the generation of images intended to display emotions, visual text, multiple objects, relative positioning, and attribute binding. This study analyzes the weaknesses of three open-source models: Stable Diffusion v2-1, Openjourney, and Dreamlike Photoreal 2.0. The models are compared based on scores for quality, alignment, and aesthetics. The evaluation is based on (a) the metrics ClipS core, Frechet Inception Distance (FID), and Large-scale Artificial Intelligence Open Network (LAION) and (b) human perception obtained in user surveys. The evaluation revealed that all models show predominantly unsatisfactory performance, and the identified weaknesses were confirmed.

Following the awareness of the need to optimize the sustainability of public transportation resources, we conduct a systematic literature review of the current Internet of Things-based approaches and technologies improving sustainable public transportation in smart cities. Using internationally peer-reviewed literature, we analyze the current state of research and identify research gaps. Major findings include the flexibility of various sensors for different use cases, data collection hot spots in public transportation, and the quality of service enhancements for passengers. Our study aims to provide practitioners and researchers with guidance on applying Internet of Things-based approaches to develop smart and sustainable transportation solutions in smart cities.