Instructions to use FastVideo/stable-audio-open-1.0-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/stable-audio-open-1.0-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/stable-audio-open-1.0-Diffusers", 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
Rename num_heads -> num_attention_heads in conditioner/config.json (FastVideo arch field name)
Browse files- conditioner/config.json +9 -0
conditioner/config.json
CHANGED
|
@@ -26,5 +26,14 @@
|
|
| 26 |
"max_val": 512
|
| 27 |
}
|
| 28 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
]
|
| 30 |
}
|
|
|
|
| 26 |
"max_val": 512
|
| 27 |
}
|
| 28 |
}
|
| 29 |
+
],
|
| 30 |
+
"cross_attention_cond_ids": [
|
| 31 |
+
"prompt",
|
| 32 |
+
"seconds_start",
|
| 33 |
+
"seconds_total"
|
| 34 |
+
],
|
| 35 |
+
"global_cond_ids": [
|
| 36 |
+
"seconds_start",
|
| 37 |
+
"seconds_total"
|
| 38 |
]
|
| 39 |
}
|