Instructions to use google/music-spectrogram-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use google/music-spectrogram-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("google/music-spectrogram-diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesfix readme example
README.md
CHANGED
|
@@ -21,9 +21,10 @@ An ideal music synthesizer should be both interactive and expressive, generating
|
|
| 21 |
```python
|
| 22 |
from diffusers import SpectrogramDiffusionPipeline
|
| 23 |
|
| 24 |
-
pipe = SpectrogramDiffusionPipeline.from_pretrained("
|
| 25 |
pipe = pipe.to("cuda")
|
| 26 |
|
|
|
|
| 27 |
output = pipe("beethoven_hammerklavier_2.mid")
|
| 28 |
|
| 29 |
audio = output.audios[0]
|
|
|
|
| 21 |
```python
|
| 22 |
from diffusers import SpectrogramDiffusionPipeline
|
| 23 |
|
| 24 |
+
pipe = SpectrogramDiffusionPipeline.from_pretrained("google/music-spectrogram-diffusion")
|
| 25 |
pipe = pipe.to("cuda")
|
| 26 |
|
| 27 |
+
# Download via: wget http://www.piano-midi.de/midis/beethoven/beethoven_hammerklavier_2.mid
|
| 28 |
output = pipe("beethoven_hammerklavier_2.mid")
|
| 29 |
|
| 30 |
audio = output.audios[0]
|