README.md

metadata

license: mit
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image

Dance Diffusion is now available in 🧨 Diffusers.

FP32

# !pip install diffusers[torch] accelerate scipy
from diffusers import DiffusionPipeline
import scipy

model_id = "harmonai/maestro-150k"
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline = pipeline.to("cuda")

audios = pipeline(audio_length_in_s=4.0).audios

# To save locally
for audio in audios:
    scipy.io.wavfile.write(f"maestro_test_{i}.wav", pipe.unet.sample_rate, audio.transpose())
    
# To dislay in google colab
import IPython.display as ipd
for audio in audios:
    display(ipd.Audio(audio, rate=pipe.unet.sample_rate))

FP16

Faster at a small loss of quality

# !pip install diffusers[torch] accelerate scipy
from diffusers import DiffusionPipeline
import scipy
import torch

model_id = "harmonai/maestro-150k"
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipeline = pipeline.to("cuda")

audios = pipeline(audio_length_in_s=4.0).audios

# To save locally
for i, audio in enumerate(audios):
    scipy.io.wavfile.write(f"maestro_test_{i}.wav", pipe.unet.sample_rate, audio.transpose())
    
# To dislay in google colab
import IPython.display as ipd
for audio in audios:
    display(ipd.Audio(audio, rate=pipe.unet.sample_rate))