Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization

arXiv:2403.14155v1 Announce Type: new
Abstract: In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot customization methods encode the image of a specified subject into a visual embedding which is then utilized alongside the textual embedding for diffusion guidance. The visual embedding incorporates intrinsic information about the subject, while the textual embedding provides a new, transient …

abstract arxiv costs cs.cv current customization embeddings encode focus generate image images optimization per text text-to-image textual type visual zero-shot