Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
|
| 2 |
+
|
| 3 |
+
[](https://compvis.github.io/LoRAdapter/)[](https://arxiv.org/abs/2405.07913)
|
| 4 |
+
|
| 5 |
+
This repository contains the weights for the paper "CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models".
|
| 6 |
+
|
| 7 |
+
[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/)
|
| 8 |
+
|
| 9 |
+
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.
|
| 10 |
+
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.
|
| 11 |
+
|
| 12 |
+
## 🎓 Citation
|
| 13 |
+
|
| 14 |
+
If you use this codebase or otherwise found our work valuable, please cite our paper:
|
| 15 |
+
|
| 16 |
+
```bibtex
|
| 17 |
+
@misc{stracke2024loradapter,
|
| 18 |
+
title={CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models},
|
| 19 |
+
author={Nick Stracke and Stefan Andreas Baumann and Joshua Susskind and Miguel Angel Bautista and Björn Ommer},
|
| 20 |
+
year={2024},
|
| 21 |
+
eprint={2405.07913},
|
| 22 |
+
archivePrefix={arXiv},
|
| 23 |
+
primaryClass={cs.CV}
|
| 24 |
+
}
|
| 25 |
+
```
|