GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
This work addresses efficiency and quality optimization in text-to-image generation, though it appears incremental as it builds on existing methods like Stable Diffusion and Yolo.
The paper tackles the challenge of tuning parameters and prompts for text-to-image generation by introducing GreenStableYolo, which reduces GPU inference time by 266% and increases hypervolume by 526% compared to baselines, with only an 18% trade-off in image quality.
Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to both reduce GPU inference time and increase image generation quality using NSGA-II and Yolo. Our experiments show that despite a relatively slight trade-off (18%) in image quality compared to StableYolo (which only considers image quality), GreenStableYolo achieves a substantial reduction in inference time (266% less) and a 526% higher hypervolume, thereby advancing the state-of-the-art for text-to-image generation.