Personalized Residuals for Concept-Driven Text-to-Image Generation
This addresses the problem of slow and parameter-heavy concept personalization in text-to-image diffusion models for users, though it is incremental.
The paper tackles efficient concept-driven text-to-image generation by introducing personalized residuals and localized attention-guided sampling, achieving concept capture in about 3 minutes on a single GPU with fewer parameters than prior models.
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.