import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Sijvert/roofscape", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Roofscape Dreambooth model trained by Sijvert with TheLastBen's fast-DreamBooth notebook
Test the concept via A1111 Colab fast-Colab-A1111 or a huggingface space.
This is my first model to visualise a better use of city rooftops, it doesn't work great yet
- Downloads last month
- 24