InstantBooth：无需测试时微调的个性化文本到图像生成
InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning
AI总结：
提出InstantBooth方法，通过可学习图像编码器和适配器层实现无需测试时微调的即时个性化文本到图像生成，在保持图像质量的同时速度提升100倍。
摘要：
个性化图像生成的最新进展允许预训练的文本到图像模型从一组图像中学习新概念。然而，现有的个性化方法通常需要为每个概念进行繁重的测试时微调，这既耗时又难以扩展。我们提出了InstantBooth，这是一种基于预训练文本到图像模型的新方法，无需任何测试时微调即可实现即时文本引导的图像个性化。我们通过几个主要组件实现了这一点。首先，我们通过将输入图像转换为文本标记的可学习图像编码器，来学习输入图像的通用概念。其次，为了保留身份的精细细节，我们通过向预训练模型引入少量适配器层来学习丰富的视觉特征表示。我们仅在文本-图像对上训练我们的组件，而不使用相同概念的配对图像。与基于测试时微调的方法（如DreamBooth和Textual-Inversion）相比，我们的模型在未见概念上的语言-图像对齐、图像保真度和身份保持方面能够生成具有竞争力的结果，同时速度快100倍。
英文摘要：
Recent advances in personalized image generation allow a pre-trained text-to-image model to learn a new concept from a set of images. However, existing personalization approaches usually require heavy test-time finetuning for each concept, which is time-consuming and difficult to scale. We propose InstantBooth, a novel approach built upon pre-trained text-to-image models that enables instant text-guided image personalization without any test-time finetuning. We achieve this with several major components. First, we learn the general concept of the input images by converting them to a textual token with a learnable image encoder. Second, to keep the fine details of the identity, we learn rich visual feature representation by introducing a few adapter layers to the pre-trained model. We train our components only on text-image pairs without using paired images of the same concept. Compared to test-time finetuning-based methods like DreamBooth and Textual-Inversion, our model can generate competitive results on unseen concepts concerning language-image alignment, image fidelity, and identity preservation while being 100 times faster.
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。
