Personalized Residuals for Concept-Driven Text-to-Image Generation

TL;DR

This paper introduces a novel method for personalized concept-driven text-to-image generation that learns residuals in a diffusion model to efficiently generate localized, personalized concepts with minimal training time.

Contribution

The authors propose personalized residuals and localized attention-guided sampling, enabling efficient, localized concept adaptation in diffusion models without extensive retraining.

Findings

Personalized residuals capture concept identity in ~3 minutes on a single GPU.

The method requires fewer parameters than previous models.

Localized sampling effectively combines learned concepts with the original diffusion prior.

Abstract

We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models. Our method first represents concepts by freezing the weights of a pretrained text-conditioned diffusion model and learning low-rank residuals for a small subset of the model's layers. The residual-based approach then directly enables application of our proposed sampling technique, which applies the learned residuals only in areas where the concept is localized via cross-attention and applies the original diffusion weights in all other regions. Localized sampling therefore combines the learned identity of the concept with the existing generative prior of the underlying diffusion model. We show that personalized residuals effectively capture the identity of a concept in ~3 minutes on a single GPU without the use of regularization images and with fewer parameters than previous models, and localized sampling allows using the original model as strong prior for large parts of the image.