Terrain Diffusion
Collection
3 items • Updated • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("xandergos/terrain-diffusion-30m", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Terrain Diffusion Pipeline trained on the 30m Copernicus GLO-30 dataset.
Paper: arxiv:2512.08309
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support