一句话：提出基于搜索的 SustainDiffusion，在不微调模型下降低 SD 的性别/族裔偏见与能耗。
Stable Diffusion 等文生图模型被广泛使用，但其生成的性别与族裔偏见以及高能耗引发社会和环境可持续性担忧。本文提出 SustainDiffusion，一种基于搜索的方法，通过寻找最优的超参数与提示结构组合，在保持图像质量与原模型相当的前提下，同时降低生成图像中的性别/族裔偏见和图像生成能耗。作者在 56 个提示上与 6 个基线进行系统实验，结果表明该方法在 SD3 上将性别偏见降低 68%、族裔偏见降低 59%，并将能耗（CPU 与 GPU 能耗之和）降低 48%；结果在多次运行中保持一致，并可泛化到不同任务中描绘类人形象的各种提示。该工作说明无需微调或改变模型架构即可提升文生图模型的社会与环境可持续性。
Background: Text-to-image generation models are widely used across numerous domains. Among these models, Stable Diffusion (SD) – an open-source text-to-image generation model – has become the most popular, producing over 12 billion images annually. However, the widespread use of these models raises concerns regarding their social and environmental sustainability. Aims: To reduce the harm that SD models may have on society and the environment, we introduce SustainDiffusion, a search-based approach designed to enhance the social and environmental sustainability of SD models. Method: SustainDiffusion searches the optimal combination of hyperparameters and prompt structures that can reduce gender and ethnic bias in generated images while also lowering the energy consumption required for image generation. Importantly, SustainDiffusion maintains image quality comparable to that of the original SD model. Results: We conduct a comprehensive empirical evaluation of SustainDiffusion, testing it against six different baselines using 56 different prompts. Our results demonstrate that SustainDiffusion can reduce gender bias in SD3 by 68%, ethnic bias by 59%, and energy consumption (calculated as the sum of CPU and GPU energy) by 48%. Additionally, the outcomes produced by SustainDiffusion are consistent across multiple runs and can be generalised to various prompts depicting human-like figures in different tasks. Conclusions: With SustainDiffusion, we demonstrate how enhancing the social and environmental sustainability of text-to-image generation models is possible without fine-tuning or changing the model’s architecture.
@inproceedings{abs-2507-15663,
title = {SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models},
author = {Giordano d’Aloisio and Tosin Fadahunsi and Jay Choy and Rebecca Moussa and Federica Sarro},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773174}
}