研究人员开发了一种新方法，用于从SD3.5、Flux和Infinity等前沿图像生成模型中移除不希望有的概念。该技术通过用一个经过训练的转码器替换内部瓶颈层来实现，该转码器充当过滤器，可以在不降低图像质量的情况下禁用特定概念信号。这种持久的、原地修改实现了最先进的概念移除效果，并能抵御对抗性提示。 AI
影响 能够实现更可控、更安全的先进图像生成模型输出。
排序理由 该集群包含一篇详细介绍图像生成模型新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.25548v1 Announce Type: cross Abstract: Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts. Efficiently removing such concepts from the model generations without degrading the quality of out…
Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts. Efficiently removing such concepts from the model generations without degrading the quality of output images remains challenging. We introduce a nov…