import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("nebulette/moss-spectrum-diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]A naive implementation of the Spectrum, a training-free forecaster in the diffusion pipeline.
It was released under a more permissive licence than the Comfy variant.
On the left is the Spectrum (15 seconds) vs the vanilla MOSS (40 seconds) on a low-end computer.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nebulette/moss-spectrum-diffusers
Base model
OpenMOSS-Team/MOSS-Image-Base