An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

TL;DR

This paper introduces Textual Inversion, a method that enables personalized text-to-image generation by learning new 'words' from just a few images, allowing users to create and modify unique concepts with natural language.

Contribution

It presents a simple, effective approach to personalize text-to-image models by learning new embeddings from limited images, enhancing creative control and fidelity.

Findings

Single embedding can capture diverse concepts

Outperforms baseline methods in concept fidelity

Enables intuitive composition of personalized concepts

Abstract

Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new "words" in the embedding space of a frozen text-to-image model. These "words" can be composed into natural language sentences, guiding personalized creation in an intuitive way. Notably, we find evidence that a single word embedding is sufficient for capturing unique and varied concepts. We compare our approach to a wide range of baselines, and demonstrate that it can more faithfully portray the concepts across a range of applications and tasks. Our code, data and new words will be available at: https://textual-inversion.github.io