import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("bhugxer/ddpm-rocole-256-v3", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This is a Diffusion U-Net Model trained on a few images from the RoCoLe dataset to see how it can be used in conjunction with RePaint. Results weren't very good but, I'll keep it around for the time being
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support