import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("evgmaslov/diffusion-3d-material", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]UNet part of diffusion model provided to generate 3D polycrystal structures.
Generation sample:
Project repo: https://github.com/evgmaslov/structure_generation
Train code: https://github.com/evgmaslov/structure_generation/blob/main/train.ipynb
Inference code: https://github.com/evgmaslov/structure_generation/blob/main/inference.ipynb
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support