MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation
arxiv(2024)
摘要
We introduce a new architecture for personalization of text-to-image
diffusion models, coined Mixture-of-Attention (MoA). Inspired by the
Mixture-of-Experts mechanism utilized in large language models (LLMs), MoA
distributes the generation workload between two attention pathways: a
personalized branch and a non-personalized prior branch. MoA is designed to
retain the original model's prior by fixing its attention layers in the prior
branch, while minimally intervening in the generation process with the
personalized branch that learns to embed subjects in the layout and context
generated by the prior branch. A novel routing mechanism manages the
distribution of pixels in each layer across these branches to optimize the
blend of personalized and generic content creation. Once trained, MoA
facilitates the creation of high-quality, personalized images featuring
multiple subjects with compositions and interactions as diverse as those
generated by the original model. Crucially, MoA enhances the distinction
between the model's pre-existing capability and the newly augmented
personalized intervention, thereby offering a more disentangled subject-context
control that was previously unattainable. Project page:
https://snap-research.github.io/mixture-of-attention
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要