first commit
Browse files
README.md
CHANGED
@@ -71,4 +71,18 @@ prompt = "Rolling thunder with lightning strikes"
|
|
71 |
output = pipeline(prompt=prompt, num_inference_steps=100, guidance_scale=7.5)
|
72 |
audio = output.audios[0]
|
73 |
IPython.display.Audio(data=audio, rate=16000)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
```
|
|
|
71 |
output = pipeline(prompt=prompt, num_inference_steps=100, guidance_scale=7.5)
|
72 |
audio = output.audios[0]
|
73 |
IPython.display.Audio(data=audio, rate=16000)
|
74 |
+
```
|
75 |
+
|
76 |
+
|
77 |
+
## Citation
|
78 |
+
|
79 |
+
Please consider citing the following article if you found our work useful:
|
80 |
+
|
81 |
+
```bibtex
|
82 |
+
@article{xue2024auffusion,
|
83 |
+
title={Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation},
|
84 |
+
author={Jinlong Xue and Yayue Deng and Yingming Gao and Ya Li},
|
85 |
+
journal={arXiv preprint arXiv:2401.01044},
|
86 |
+
year={2024}
|
87 |
+
}
|
88 |
```
|