Text-to-Audio
Diffusers
Safetensors
StableAudioPipeline
audio
sound-effects
ambient
diffusion
stable-audio
maestraea
Instructions to use AEmotionStudio/stable-audio-open-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AEmotionStudio/stable-audio-open-models with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AEmotionStudio/stable-audio-open-models", 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
Mirror scheduler/scheduler_config.json from stabilityai/stable-audio-open-1.0
Browse files
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "CosineDPMSolverMultistepScheduler",
|
| 3 |
+
"_diffusers_version": "0.30.0.dev0",
|
| 4 |
+
"euler_at_final": false,
|
| 5 |
+
"final_sigmas_type": "zero",
|
| 6 |
+
"lower_order_final": true,
|
| 7 |
+
"num_train_timesteps": 1000,
|
| 8 |
+
"prediction_type": "v_prediction",
|
| 9 |
+
"rho": 7.0,
|
| 10 |
+
"sigma_data": 1.0,
|
| 11 |
+
"sigma_max": 500,
|
| 12 |
+
"sigma_min": 0.3,
|
| 13 |
+
"sigma_schedule": "exponential",
|
| 14 |
+
"solver_order": 2,
|
| 15 |
+
"solver_type": "midpoint"
|
| 16 |
+
}
|