We are pleased to share that researchers from the University of Donja Gorica (UDG) presented their latest work at the 2025 IEEE International Symposium on Applied Sciences (ISAS). The paper, titled “Real-time Image Generation Utilizing ARM SBC Architecture”, is now published by IEEE and available at the following [link].
The paper, authored by Igor Ćulafić, Tomo Popović, Ivan Jovović, and Stevan Ćakić, explores the deployment of advanced generative AI models on ARM-based edge devices, specifically the NVIDIA Jetson Orin Nano platform. Traditionally, real-time image generation with models such as Stable Diffusion has required powerful desktop GPUs or HPC clusters. This research demonstrates that, through careful CUDA optimization, ARM compatibility adjustments, and dynamic resource management, real-time performance of 2–6 FPS at 512×512 resolution can be achieved directly on low-power edge hardware.
The work addresses thermal management, memory constraints, and software compatibility challenges, proposing a custom ARM-optimized Docker environment and adaptive workload balancing. The results show how decentralized, low-power edge devices can complement high-performance computing ecosystems, opening new opportunities in fields such as healthcare, automotive, and smart city applications.
This publication also reflects the mission of NCC Montenegro to support academia and young researchers in advancing AI and HPC knowledge. By providing expertise, resources, and collaboration opportunities, NCC Montenegro helps integrate cutting-edge research with the broader European HPC ecosystem.