Instructions to use stabilityai/stable-audio-open-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Stable Audio Tools
How to use stabilityai/stable-audio-open-1.0 with Stable Audio Tools:
import torch import torchaudio from einops import rearrange from stable_audio_tools import get_pretrained_model from stable_audio_tools.inference.generation import generate_diffusion_cond device = "cuda" if torch.cuda.is_available() else "cpu" # Download model model, model_config = get_pretrained_model("stabilityai/stable-audio-open-1.0") sample_rate = model_config["sample_rate"] sample_size = model_config["sample_size"] model = model.to(device) # Set up text and timing conditioning conditioning = [{ "prompt": "128 BPM tech house drum loop", }] # Generate stereo audio output = generate_diffusion_cond( model, conditioning=conditioning, sample_size=sample_size, device=device ) # Rearrange audio batch to a single sequence output = rearrange(output, "b d n -> d (b n)") # Peak normalize, clip, convert to int16, and save to file output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu() torchaudio.save("output.wav", output, sample_rate) - Notebooks
- Google Colab
- Kaggle
Great model!
#12
by ztsvvstz - opened
This model seems to work really good for generating single samples to be used in music sampling :)
As a musician, this is actually quite usable.
Seems like the dataset was well curated, thank you very much for this!
I like how it just generates a single hit if I for example ask it for a cymbal and just fades that out instead of generating other random sounds after that (mostly).
I wonder whats the prompt for getting it to generate those deep tribal percussion sounds, things like "percussion loop" seem to generate mostly hihat / high frequency content, "latin percussion loop" gets me kinda more what I want but not quite^^