LoRA方向提取用于FLUX.1 Kontext中的可控灯光切换
LoRA Direction Extraction for Controllable Light Toggling in FLUX.1 Kontext
浏览论文内容
中文总结 AI 辅助
提出一种流匹配扩散模型微调方法，通过LoRA方向训练提取纯方向并配合专用损失函数，实现无需大型数据集的可控室内灯光开关编辑，同时保持场景几何与视觉身份，并利用增量图精确调整灯光颜色与色温。
中文摘要 AI 辅助
我们提出了一种针对流匹配扩散模型的微调方法，旨在无需大型训练数据集的情况下实现逼真的人工光建模。我们处理可控室内图像编辑任务，目标是在保持原始图像的场景几何、物体布局、材质和视觉身份的同时，打开或关闭人工光源。为实现这一目标，我们将任务分解为两个独立的公式。我们引入了LoRA方向训练方法，该方法在扩散模型流场中提取LoRA适配器效果的纯方向，并且我们还引入了专门的损失函数以确保逆变换的逼真性。此外，生成的增量图用于更精确地调整灯光颜色和色温。
英文摘要
We propose a fine-tuning method for flow-matching diffusion models aimed at realistic artificial light modeling without the need for a large training dataset. We address the task of controllable interior image editing, where the goal is to turn artificial light sources on or off while preserving the scene geometry, object placement, materials, and visual identity of the original image. To achieve this, we decompose the task into two independent formulations. We introduce the LoRA Direction Training Method, which extracts the pure direction of the LoRA adapter effect in the diffusion model flow field, and we also introduce specialized loss functions to ensure the realism of the inverse transformation. Additionally, the resulting increment map is used for more precise adjustment of the lighting color and temperature.
发表机构
- BURO.io Research Lab（BURO.io 研究实验室）
机构由 AI 辅助整理，请以论文原文为准。
