Home | Publications | SBS+24a

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control and Altering of T2I Models

MCML Authors

Björn Ommer

Prof. Dr.

Principal Investigator

Computer Vision & Learning

Abstract

Text-to-image generative models have become a prominent and powerful tool that excels at generating high-resolution realistic images. However, guiding the generative process of these models to take into account detailed forms of conditioning reflecting style and/or structure information remains an open problem. In this paper, we present. LoRAdapter, an approach that unifies both style and structure conditioning under the same formulation using a novel conditional LoRA block that enables zero-shot control. LoRAdapter is an efficient and powerful approach to condition text-to-image diffusion models, which enables fine-grained control conditioning during generation and outperforms recent state-of-the-art approaches.

inproceedings