import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kronosta/orchwell", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Orchwell is a Dance Diffusion model trained on an inexperienced orchestra with a disjoint sound. It didn't go quite as well as expected, but it produces good samples 50-75% of the time. It's also really the only current digital solution for making orchestra music that isn't perfectly composed (which makes it more unique).
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support