Scholarlink

<p>In this paper, we tackle the issue of customized image and video generation, encompassing both single-object and multi-object customization. Current methods primarily concentrate on single-object customization and struggle with more complex scenarios involving multiple concepts. Additionally, these methods often necessitate retraining or fine-tuning with a few examples, leading to a time-consuming process that impedes rapid adaptability. To address these weaknesses, we present <b>FreerCustom</b>, a method that eliminates the need for additional training to generate customized images and videos featuring both single and multi-concept compositions, using only one reference image per concept. Our method features a novel multi-reference self-attention (MRSA) mechanism coupled with a weighted mask strategy, allowing the model to better capture and the desired concepts in the generated images. Additionally, MRSA leverages our critical observation that customized generation is more effective when the images provided have contextual interactions. Experimental results show that our method not only closely aligns the generated results with the target concepts and text inputs, but also performs equally well or even surpasses existing training-based methods in both multi-concept and single-concept scenarios. Homepage: <a href="https://aim-uofa.github.io/FreerCustom/">https://aim-uofa.github.io/FreerCustom/</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

FreerCustom: Training-Free Multi-Concept Customization for Image and Video Generation

  • 期刊论文

  • 发表日期：

    2025年12月26日

查看全文
  • Canyu Zhao,
  • Ganggui Ding,
  • Wen Wang,
  • Zhen Yang,
  • Zide Liu,
  • Hao Chen,
  • Chunhua Shen

摘要

In this paper, we tackle the issue of customized image and video generation, encompassing both single-object and multi-object customization. Current methods primarily concentrate on single-object customization and struggle with more complex scenarios involving multiple concepts. Additionally, these methods often necessitate retraining or fine-tuning with a few examples, leading to a time-consuming process that impedes rapid adaptability. To address these weaknesses, we present FreerCustom, a method that eliminates the need for additional training to generate customized images and videos featuring both single and multi-concept compositions, using only one reference image per concept. Our method features a novel multi-reference self-attention (MRSA) mechanism coupled with a weighted mask strategy, allowing the model to better capture and the desired concepts in the generated images. Additionally, MRSA leverages our critical observation that customized generation is more effective when the images provided have contextual interactions. Experimental results show that our method not only closely aligns the generated results with the target concepts and text inputs, but also performs equally well or even surpasses existing training-based methods in both multi-concept and single-concept scenarios. Homepage: https://aim-uofa.github.io/FreerCustom/.