Instructions to use niobures/StableAudio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use niobures/StableAudio with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("niobures/StableAudio", 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
Download stable-audio-3-optimized/MLX/same_l_decoder_f32.npz from niobures/StableAudio: direct link, hf CLI and curl.
- Browser
- Download file 1.7 GB
-
https://huggingface.co/niobures/StableAudio/resolve/main/stable-audio-3-optimized/MLX/same_l_decoder_f32.npz
- Command line
-
hf download hf://niobures/StableAudio/stable-audio-3-optimized/MLX/same_l_decoder_f32.npz
-
curl -L -o same_l_decoder_f32.npz https://huggingface.co/niobures/StableAudio/resolve/main/stable-audio-3-optimized/MLX/same_l_decoder_f32.npz
1.7 GB
- Xet hash:
- a7382fe9b5512a5eef2c298ffbfe02aad63cc975714170062e48d722b3bb65cb
- Size of remote file:
- 1.7 GB
- SHA256:
- 84924be2122d3a20fce443f40b782d9cd88e8e73707476326003ac47659a2287
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.