---
library_name: diffusers
tags:
- stable diffusion
- lora
- loradapter
- adapter
- conditioning
---
# Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models

[![Project Page](https://img.shields.io/badge/Project-Page-blue)](https://compvis.github.io/LoRAdapter/)[![Paper](https://img.shields.io/badge/arXiv-PDF-b31b1b)](https://arxiv.org/abs/2405.07913)

This repository contains the weights for the paper "CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models".

[Nick Stracke](https://twitter.com/nickstracke_), [Stefan Andreas Baumann](https://stefan-baumann.eu/), [Joshua Susskind](https://twitter.com/jsusskin), [Miguel Angel Bautista](https://twitter.com/itsbautistam), [Björn Ommer](https://ommer-lab.com/people/ommer/)

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.

## 🎓 Citation

If you use this codebase or otherwise found our work valuable, please cite our paper:

```bibtex
@misc{stracke2024loradapter,
  title={CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models},
  author={Nick Stracke and Stefan Andreas Baumann and Joshua Susskind and Miguel Angel Bautista and Björn Ommer},
  year={2024},
  eprint={2405.07913},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}
```