metadata

tags:
  - pytorch
  - diffusers
  - unconditional-audio-generation
  - diffusion-models-class
liscense: mit

这个扩散模型是用来生成风格音乐的非条件扩散模型

用法

from IPython.display import Audio
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("AlvaroPang/audio-diffusion-electronic")
output = pipe()
display(output.images[0])
display(Audio(output.audios[0], rate=pipe.mel.get_sample_rate()))