PALP: Prompt Aligned Personalization of Text-to-Image Models

TL;DR

PALP introduces a prompt-aligned personalization technique for text-to-image models that enhances complex prompt fidelity and subject personalization, outperforming existing methods in alignment and versatility.

Contribution

The paper presents a novel prompt-aligned personalization approach that improves complex prompt fidelity and subject personalization in text-to-image models, addressing limitations of prior methods.

Findings

Improves text alignment for complex prompts

Enables multi- and single-shot personalization

Supports composition of multiple subjects and reference images

Abstract

Content creators often aim to create personalized images using personal subjects that go beyond the capabilities of conventional text-to-image models. Additionally, they may want the resulting image to encompass a specific location, style, ambiance, and more. Existing personalization methods may compromise personalization ability or the alignment to complex textual prompts. This trade-off can impede the fulfillment of user prompts and subject fidelity. We propose a new approach focusing on personalization methods for a \emph{single} prompt to address this issue. We term our approach prompt-aligned personalization. While this may seem restrictive, our method excels in improving text alignment, enabling the creation of images with complex and intricate prompts, which may pose a challenge for current techniques. In particular, our method keeps the personalized model aligned with a target prompt using an additional score distillation sampling term. We demonstrate the versatility of our method in multi- and single-shot settings and further show that it can compose multiple subjects or use inspiration from reference images, such as artworks. We compare our approach quantitatively and qualitatively with existing baselines and state-of-the-art techniques.