How to use Hyeon2/riffusion-musiccaps with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Hyeon2/riffusion-musiccaps", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
How can the generated spectrograms be converted into audio clips? Please advise!
You can check riffusion github repository for this.
· Sign up or log in to comment
