Instructions to use stabilityai/stable-audio-open-small 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-small 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-small") 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
Android + OpenCL implementation β latent-diffusion audio on-device on non-flagship phones (Adreno 6xx)
#6
by a8nova - opened
Hi! I wanted to share an Android + OpenCL implementation of Stable Audio Open Small, in case anyone wants to run it on a phone:
- Try it: Edgi on Google Play β runs fully on-device, no cloud.
- Open source: the app is built on top of the open-source adreno-llms inference engine β https://github.com/a8nova/adreno-llms β pure C++/OpenCL with hand-written kernels tuned for Adreno, running the whole pipeline on the GPU: T5 conditioning + 8-step DiT + VAE decode.
It's tuned and tested on Adreno 6xx GPUs β the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) β and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it generates an 11 s stereo 44.1 kHz clip in ~100β130 s (thermal-dependent) β to my knowledge one of the first latent-diffusion audio models running fully on a mid-range phone GPU.
Hope it's useful β happy to answer questions!