Customization Assistant for Text-to-image Generation

arXiv:2312.03045v2 Announce Type: replace
Abstract: Customizing pre-trained text-to-image generation model has attracted massive research interest recently, due to its huge potential in real-world applications. Although existing methods are able to generate creative content for a novel concept contained in single user-input image, their capability are still far from perfection. Specifically, most existing methods require fine-tuning the generative model on testing images. Some existing methods do not require fine-tuning, while their performance are unsatisfactory. Furthermore, the interaction between users and models …

abstract applications arxiv assistant capability concept creative cs.cv customization fine-tuning generate image image generation massive novel research text text-to-image type world