Instructions to use FastVideo/stable-audio-open-small-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/stable-audio-open-small-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-small-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
Update transformer/config.json: parametric configs (qk_norm, sub-conditioner specs)
Browse files- transformer/config.json +2 -12
transformer/config.json
CHANGED
|
@@ -3,18 +3,8 @@
|
|
| 3 |
"io_channels": 64,
|
| 4 |
"embed_dim": 1024,
|
| 5 |
"depth": 16,
|
| 6 |
-
"num_heads": 8,
|
| 7 |
"cond_token_dim": 768,
|
| 8 |
"global_cond_dim": 768,
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"qk_norm": "ln"
|
| 12 |
-
},
|
| 13 |
-
"cross_attention_cond_ids": [
|
| 14 |
-
"prompt",
|
| 15 |
-
"seconds_total"
|
| 16 |
-
],
|
| 17 |
-
"global_cond_ids": [
|
| 18 |
-
"seconds_total"
|
| 19 |
-
]
|
| 20 |
}
|
|
|
|
| 3 |
"io_channels": 64,
|
| 4 |
"embed_dim": 1024,
|
| 5 |
"depth": 16,
|
|
|
|
| 6 |
"cond_token_dim": 768,
|
| 7 |
"global_cond_dim": 768,
|
| 8 |
+
"num_attention_heads": 8,
|
| 9 |
+
"qk_norm": "ln"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
}
|