Abstract
The burgeoning landscape of text-to-image models, exemplified by innovations such as Midjourney and DALLE 3, has revolutionized content creation across diverse sectors. However, these advancements bring forth critical ethical concerns, particularly with the misuse of open-source models to generate content that violates societal norms. Addressing this, we introduce Ethical-Lens, a framework designed to facilitate the value-aligned usage of text-to-image tools without necessitating internal model revision. Ethical-Lens ensures value alignment in text-to-image models across toxicity and bias dimensions by refining user commands and rectifying model outputs. Systematic evaluation metrics, combining GPT4-V, HEIM, and FairFace scores, assess alignment capability. Our experiments reveal that Ethical-Lens enhances alignment capabilities to levels comparable with or superior to commercial models like DALLE 3, ensuring user-generated content adheres to ethical standards while maintaining image quality. This study indicates the potential of Ethical-Lens to ensure the sustainable development of open-source text-to-image tools and their beneficial integration into society. Our code is available at this https URL.
Abstract (translated)
文本转图像模型的迅速发展,如Midjourney和DALLE 3等创新,已经彻底颠覆了内容创作的各个领域。然而,这些进步也带来了关键的伦理担忧,特别是开放源代码模型被用于生成违反社会规范的内容时。为解决这一问题,我们引入了Ethical-Lens,一个框架,旨在促进在不需要修改内部模型的情况下实现文本转图像工具的价值对齐使用。Ethical-Lens通过优化用户命令和纠正模型输出,在毒性 and bias维度上确保文本转图像模型的价值对齐。组合使用GPT4-V、HEIM和FairFace分数的系统评估指标评估了对齐能力。我们的实验结果表明,Ethical-Lens增强了与商业模型如DALLE 3相当或更强的对齐能力,确保用户生成内容符合道德准则,同时保持图像质量。本研究表示Ethical-Lens确保了开源文本转图像工具的可持续发展和有益整合到社会。我们的代码可在此链接下载:https://www.ethical-lens.org/。
URL
https://arxiv.org/abs/2404.12104