LILAC：用于扩散模型多概念定制的分层独立LoRAs和级联条件处理
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
浏览论文内容
中文总结 AI 辅助
研究个性化文本到图像扩散模型渲染特定主题的难题，提出LILAC框架，通过分层独立训练低秩适配器并级联条件处理，避免参数干扰，无需联合训练，线性扩展且与主干无关，效果良好。
中文摘要 AI 辅助
将文本到图像的扩散模型个性化以在连贯图像中渲染多个特定主题仍然具有挑战性。本文提出LILAC框架，在推理时组合独立训练的低秩适配器，每次仅一个适配器激活，避免参数级干扰，无需联合训练，线性扩展且与主干无关，实验效果良好。
英文摘要
Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independently trained concept adapters in a shared weight space (via federated averaging, gradient fusion, or orthogonality constraints) suffer from identity confusion and style bleeding. In this work, we show that composing concepts as separate image layers, instead of merging their adapters in a shared weight space, avoids parameter-level interference. We introduce LILAC, a framework that composes independently trained low-rank adapters at inference time: each subject is conditioned on the frozen composite of previously placed subjects, with exactly one adapter active at a time, therefore identities never interfere at the parameter level. LILAC composes the adapters without joint training, scales linearly with the number of concepts, and is backbone-agnostic. Under the Orthogonal Adaptation protocol, LILAC applied on Qwen-Image-Edit+Qwen-Image-Layered reaches an ArcFace detection rate of 0.861. Code is available at https://github.com/marianlupascu/LILAC.
发表机构
- Adobe Research, Romania（罗马尼亚Adobe研究院）
- Department of Computer Science, University of Bucharest, Romania（罗马尼亚布加勒斯特大学计算机科学系）
- International Computer High School of Bucharest, Romania（罗马尼亚布加勒斯特国际计算机高中）
机构由 AI 辅助整理，请以论文原文为准。
