DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

TL;DR

DreamBooth introduces a fine-tuning method for text-to-image diffusion models that personalizes them to generate photorealistic images of specific subjects in diverse contexts using only a few reference images.

Contribution

The paper presents a novel fine-tuning approach with a class-specific prior preservation loss for subject-driven image generation, enabling high-quality personalization with minimal data.

Findings

Effective subject recontextualization and view synthesis.

Preserves key features of subjects across diverse scenes.

Outperforms previous methods in personalized image generation.

Abstract

Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a given reference set and synthesize novel renditions of them in different contexts. In this work, we present a new approach for "personalization" of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. Once the subject is embedded in the output domain of the model, the unique identifier can be used to synthesize novel photorealistic images of the subject contextualized in different scenes. By leveraging the semantic prior embedded in the model with a new autogenous class-specific prior preservation loss, our technique enables synthesizing the subject in diverse scenes, poses, views and lighting conditions that do not appear in the reference images. We apply our technique to several previously-unassailable tasks, including subject recontextualization, text-guided view synthesis, and artistic rendering, all while preserving the subject's key features. We also provide a new dataset and evaluation protocol for this new task of subject-driven generation. Project page: https://dreambooth.github.io/