GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Pre-Trained Language Models for Text Generation: A SurveyACM Computing Surveys, 2024
- NSGA-II-DL: Metaheuristic Optimal Feature Selection With Deep Learning Framework for HER2 Classification in Breast CancerIEEE Access, 2024
- StableYolo: Optimizing Image Generation for Large Language Models2023
- An Enhanced NSGA-II for Solving Berth Allocation and Quay Crane Assignment Problem With Stochastic Arrival TimesIEEE Transactions on Intelligent Transportation Systems, 2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Towards the use of the readily available tests from the release pipeline as performance tests2020
- Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval2019
- You Only Look Once: Unified, Real-Time Object Detection2016
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002