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

Autor:	Stracke, Nick, Baumann, Stefan Andreas, Susskind, Joshua M., Bautista, Miguel Angel, Ommer, Björn
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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 consider 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, powerful, and architecture-agnostic approach to condition text-to-image diffusion models, which enables fine-grained control conditioning during generation and outperforms recent state-of-the-art approaches. Comment: for the project page and code, view https://compvis.github.io/LoRAdapter/
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.07913 Zobrazit plný text záznamu View this record from Arxiv