分块LoRA：重思细粒度LoRA在文本生成图像中的有效个性化与风格化
Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation
AI总结：
针对文本生成图像现有高效微调方法难以兼顾有效个性化与风格化的问题，提出分块LoRA对SD不同模块细粒度微调，实现图像贴合提示、保留目标特征且符合目标风格，经实验验证有效。
摘要：
文本生成图像中的个性化与风格化任务，目标是让预训练扩散模型分析用户引入的新概念，并将其融入预期风格中。近年来，参数高效微调（PEFT）方法被广泛用于解决该任务，极大推动了领域发展。尽管这类方法应用广泛，现有高效微调方法仍难以在文本生成图像（T2I）中实现有效的个性化与风格化。为解决这一问题，我们提出分块低秩适配（LoRA），对稳定扩散（SD）的不同模块进行细粒度微调，生成的图像既忠实于输入提示词与目标身份特征，又具备所需风格。大量实验验证了所提方法的有效性。
英文摘要：
The objective of personalization and stylization in text-to-image is to instruct a pre-trained diffusion model to analyze new concepts introduced by users and incorporate them into expected styles. Recently, parameter-efficient fine-tuning (PEFT) approaches have been widely adopted to address this task and have greatly propelled the development of this field. Despite their popularity, existing efficient fine-tuning methods still struggle to achieve effective personalization and stylization in T2I generation. To address this issue, we propose block-wise Low-Rank Adaptation (LoRA) to perform fine-grained fine-tuning for different blocks of SD, which can generate images faithful to input prompts and target identity and also with desired style. Extensive experiments demonstrate the effectiveness of the proposed method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
